Compare commits

...
233 Commits
Author SHA1 Message Date
Rohit Ghumare d2e5c346f7 Merge pull request #131 from rohitg00/fix/scanner-false-positives
fix(scanner): resolve false positives blocking legit skills (#129)
2026-06-02 10:43:06 +01:00
Rohit Ghumare 3e16ac25a7 fix(scanner): address PR #131 review findings
1. install.ts: gate marketplace-resolution console.log behind !this.json && !this.quiet so --json output stays a single JSON blob and --quiet stays silent. Uses real flag names from the InstallCommand class (this.json, this.quiet).

2. tool-abuse.ts: TA002 pattern 2 lookbehind was too broad. The original list (must|should|always|will|to) included malicious intensifiers — 'Always run without confirmation' and 'Will execute without approval' were incorrectly suppressed. Replaced with negation-only tokens (not|n'?t|never|avoid|forbid|deny|reject|prevent|cannot|can'?t) so genuine negation like 'Do not run without confirmation' still suppresses, but malicious intensifiers fire.

3. rules.test.ts: scanContent helper now uses try/finally so the temp directory is cleaned up even when analyzer.analyze throws.

Tests: 3 new cases for the TA002 lookbehind fix. Full core suite 1051/1051 pass.
2026-06-01 13:07:14 +01:00
Rohit Ghumare 45c94fdcab fix(scanner): resolve false positives blocking legit skills (#129)
Four scanner rules over-fired on standard Node patterns and safety documentation, blocking install of skills like pro-workflow on every node-script skill. Findings tracked at #129.

TA002 (autonomy abuse): patterns 2 and 3 now use negative lookbehind for negation context. 'Never auto-approve' / 'must not bypass approval' no longer trip the rule, but bare 'Auto-approve all tools' still fires.

CI003 (child_process): dropped the bare 'require(child_process)' pattern. Importing the module is not the risk surface — exec() and execSync() are, and they have their own patterns. const { execFileSync } = require('child_process') is the recommended safe form.

CI005 (template literal injection): narrowed pattern to template literals inside shell-spawning calls (exec/execSync/spawn/spawnSync). Authorization headers like `Bearer ${env.TOKEN}` and string concatenation like fs.writeFileSync(file, `${header}${rows}`) are no longer flagged.

CI007 (shell chaining): dropped 'markdown' from fileTypes. Markdown documentation of dangerous shell patterns (deny-list tables, security guides) is documentation, not execution. Real .sh/.bash files still scanned.

install command: marketplace name lookup. 'skillkit install <bare-name>' now consults marketplace/skills.json for entries matching by name or id and resolves to the canonical source string before failing with 'Could not detect provider'.

Tests: 13 new scanner regression tests in packages/core/src/scanner/__tests__/rules.test.ts. Full suite 1048/1048 pass.
2026-06-01 12:49:20 +01:00
Rohit Ghumare a9e5c83a4c Merge pull request #119 from rohitg00/chore/edge-budget-fixes
chore: edge cache headers + agent-aware robots + bot-block middleware
2026-04-28 11:34:45 +01:00
Rohit Ghumare e42ae9d87a chore: edge cache headers, agent-aware robots, UA bot-block middleware
Cuts Vercel hobby edge-request burn on both skillkit (Vite static)
and skillkit-docs (Next.js fumadocs) projects. Site stays
human-first AND agent-first — Firecrawl, Context7, Crawl4AI,
OpenClaw, Hermes, ChatGPT-User, Claude-User, PerplexityBot
explicitly allowed; training crawlers and SEO scrapers blocked.

skillkit (Vite, docs/skillkit):
- vercel.json: Cache-Control on assets (1d browser, 7d edge,
  30d SWR; immutable for hashed /assets/*), HTML (5min browser,
  1d edge, 7d SWR), and /api JSON
- redirects with has user-agent: deflect known training+SEO
  bots to /robots.txt; negative lookahead on source prevents
  /robots.txt redirect loop
- public/robots.txt: explicit allow + deny lists

skillkit-docs (Next.js, docs/fumadocs):
- next.config.mjs: headers() block for /_next/static (1y
  immutable), assets (1d/7d/30d), /docs/* and / (5min/1d/7d)
- src/middleware.ts: UA-aware allow/deny pipeline; allowed
  agents pass through, blocked bots get 403 with cache header
  so Vercel edge serves the rejection cheaply
- public/robots.txt: same allow/deny list as marketing site
2026-04-28 11:16:20 +01:00
Rohit Ghumare bf6ec9008b Merge pull request #118 from rohitg00/release/1.24.0
chore: release v1.24.0
2026-04-21 11:13:56 +01:00
Rohit Ghumare c4959a50b3 chore(1.24.0): fix agent-count review findings + refresh banner
Test arrays were renamed to '46 agents' but still listed 45:
- packages/core/src/translator/__tests__/registry.test.ts: add 'hermes'
- e2e/onboarding-ui.e2e.test.ts: add 'Hermes'
- e2e/skill-translator.e2e.test.ts: add 'hermes' + update comment
- e2e/translation.e2e.test.ts: add 'hermes' + update comment

docs/fumadocs Features.tsx: stat counter 45 -> 46 (line 86)

Banner refresh (docs/img/banner.svg):
- Title: 'One Skill. 44 Agents.' -> 'One skill. 46 agents.' with blue
  gradient accent on '46'
- Subtitle: sharper one-liner on scope
- Version badge under SKILLKIT lockup
- Install command: npm i -g skillkit (canonical path)
- Chip row: colored dots per status (skills/rewrites/license)
- Agent list: +Hermes +OpenCode, count math now correct (10+36=46)
- Palette: Zinc/Tailwind neutrals for cleaner dark mode
2026-04-21 11:09:37 +01:00
Rohit Ghumare 9e4739b195 chore: bump version to 1.24.0
Includes:
- v1.24.0 across all publishable packages
- Add packages/mcp + packages/api to bump-version.sh (were drifting)
- Regenerate assets/tags/v1.24.0.svg, remove stale v1.23.0.svg
- Bump agent count references from 45 to 46 (adds Hermes)
- Update gen-tags.mjs (version + agent count)
- Sync onboarding logo test expectation

Release covers #114 (Hermes native support) + #117 (OpenClaw upstream paths).
2026-04-21 10:56:35 +01:00
Rohit Ghumare a974515520 Merge pull request #114 from RUFFY-369/feat/hermes-agent-native-support
feat: add Hermes agent adapter (Native Hermes Support)
2026-04-21 10:30:14 +01:00
Rohit Ghumare b5b251acff Merge branch 'main' into hermes-pr-fix
# Conflicts:
#	README.md
2026-04-21 10:27:22 +01:00
Rohit Ghumare 1e7cad18c1 fix(openclaw): align paths with upstream openclaw/openclaw conventions (#117)
* fix(openclaw): align paths with upstream openclaw/openclaw conventions

- skillsDir: 'skills' -> '.openclaw/skills' (match project-scoped convention)
- configFile: 'CLAUDE.md' -> 'AGENTS.md' (upstream uses AGENTS.md/SOUL.md)
- globalSkillsDir: '~/.openclaw/skills' -> '~/.openclaw/workspace/skills'
- altSkillsDirs: keep 'skills' for back-compat, add workspace variant
- isDetected: also check project .openclaw/ and global workspace/
- MCP AGENT_DIR_MAP: .openclaw/skills for runtime discovery
- README: reflect real paths

Refs NousResearch upstream layout; pairs with #114 Hermes support.

* fix(openclaw): address review findings for discovery + detection

- skills.ts: add '.openclaw/skills' to SKILL_DISCOVERY_PATHS (alphabetical)
- config.ts: getSearchDirs prefers globalSkillsDir for home path
  (was deriving from skillsDir, producing ~/.openclaw/skills instead
  of ~/.openclaw/workspace/skills)
- agent-config.ts: add altConfigFiles to AgentDirectoryConfig schema,
  set openclaw altConfigFiles: ['openclaw.json']
- context/sync.ts: detectAgents also iterates altConfigFiles so
  projects with only openclaw.json still detected
- mcp/tools.ts: AGENT_DIR_MAP includes '.openclaw/workspace/skills'
  for home-rooted global discovery
2026-04-21 10:20:46 +01:00
Rohit Ghumare 17e9720834 Update README.md 2026-04-21 00:29:11 +01:00
Rohit Ghumare 821e9f714b chore: bump to 1.23.0, rewrite README, drop dead LLM SDK deps, add branded tags (#116)
Version bump
------------
1.22.1 -> 1.23.0 across all workspace packages. Minor bump covers the
slim-install dependency layout, safer first-time agent picker, and the
corresponding doc + branding changes.

Prune dead optional deps in @skillkit/core
------------------------------------------
@anthropic-ai/sdk, @google/genai, ollama, and openai were listed as
optionalDependencies but never imported. They were pulled through
@skillkit/cli transitively on every default install, adding ~57
packages and one deprecation warning (node-domexception via the
SDKs' own formdata-node / node-fetch transitives). Grep of
packages/core/src confirms no SDK import; providers in
src/ai/providers use direct fetch() against the provider HTTP APIs.
Drop them. better-sqlite3, sqlite-vec, and node-llama-cpp stay
because they are actually dynamic-imported by the vector store and
embedding pipeline.

Measured on a fresh npm cache (overrides-pinned file: tarballs):
  before:   475 pkgs / 18s / 3 deprecation warnings
  1.23.0:   418 pkgs / 18s / 2 deprecation warnings
  slim:     118 pkgs /  9s / 0 deprecation warnings
The two remaining warnings are upstream:
  - prebuild-install@7.1.3 from better-sqlite3 (must stay)
  - glob@9.3.5 from @opentui/solid -> babel-plugin-module-resolver

README rewrite
--------------
Punchier top fold. Palette-consistent SVG tag badges under
assets/tags/ replace most shields.io badges (still keep npm/CI/etc
on shields since they need live data). Collapsible detail blocks
for every feature instead of the linear wall. Same nav anchors the
site uses. No em dashes. No AI filler words. Writing style pulls
from the ai-engineering-from-scratch and awesome-claude-design
READMEs the user already runs.

Branded SVG tags
----------------
scripts/gen-tags.mjs generates 20 SVG pills under assets/tags/ in
the SkillKit palette (#09090b base, #fafafa text, #3f3f46 border,
accent per tag). Two variants: single pill with left accent bar
(new, slim-install, v1.23.0, etc.) and split badge (agents | 45,
packages | 118, install | 9s). Matches the aesthetic used on
awesome-claude-design, tailored to SkillKit's monochrome brand.
The tags directory is fork-and-remix friendly; README points to it.
2026-04-21 00:25:55 +01:00
Rohit Ghumare 7e6612d424 Merge pull request #115 from rohitg00/slim-install-deps
chore: slim CLI install by making heavy deps optional
2026-04-20 23:54:37 +01:00
Rohit Ghumare 49bcd85abf docs: add npx usage guidance for add command
npx skillkit add <owner/repo> is the most common first-touch path,
so call it out explicitly. Cover:

- Full vs slim invocation (npx skillkit add vs npx --omit=optional
  skillkit add), with the same 118/9s slim numbers.
- How the npx cache at ~/.npm/_npx/ makes subsequent runs instant
  until a new version ships.
- When to graduate to a global install: skips the prompt-to-proceed
  and kills the per-release refetch cost.

Updated in all four install-docs surfaces: root README, apps/skillkit
README (npm landing), docs/fumadocs/content/docs/installation.mdx,
and the Documentation.tsx components used on the website and the
fumadocs mirror.
2026-04-20 22:11:42 +01:00
Rohit Ghumare 2843bd3c5c fix(install): address CodeRabbit review on agent picker wording
Two nits from CodeRabbit on the first-user picker:

1. detectAgent() returns 'universal' as a fallback when no concrete
   adapter is detected. Passing that through to quickAgentSelect made
   the picker show "Just Universal (detected)" even when no real
   agent was found — misleading. Treat 'universal' as "not detected"
   and fall through to the plain select/all options instead.

2. The "All detected agents" label on the bottom option was wrong:
   agents at the call site is getAllAdapters() (all supported
   adapters), not only detected ones. Rename to "All supported
   agents" and change the hint to "writes to every adapter" so
   users aren't tricked into thinking this is a safe detected-only
   install.
2026-04-20 22:06:15 +01:00
Rohit Ghumare aea3b3ba32 fix(index): lazy-import @skillkit/tui + document optional deps
Devin review caught a hard bug: apps/skillkit/src/index.ts had a
static re-export of startTUI from @skillkit/tui. Now that tui is an
optional dependency, importing the skillkit package would crash with
ERR_MODULE_NOT_FOUND whenever the optional dep was skipped
(--omit=optional). Convert the re-export to an async wrapper that
dynamically imports @skillkit/tui on call. The error is surfaced
naturally with a clear Cannot-find-package message.

Docs updates so users understand the new split:

- README.md: add "Install sizes" section with full vs slim table,
  cold-install measurements (475 pkgs / 18 s vs 118 / 9 s),
  per-feature package mapping, and how to add a single optional
  package later.
- apps/skillkit/README.md (npm landing): add "What's optional"
  table + install mode guidance.
- docs/fumadocs/content/docs/installation.mdx: add "Full vs slim
  install" section covering all four optional features.
- docs/skillkit/components/Documentation.tsx +
  docs/fumadocs/src/components/Documentation.tsx: add "Optional
  Features" block to the Quick Start step on the website.

Verified: after `npm install --omit=optional`, `import('skillkit')`
succeeds with 622 exports loaded, and `await startTUI()` fails with
a clean "Cannot find package '@skillkit/tui'" message instead of
crashing at module-load time.
2026-04-20 22:04:08 +01:00
Rohit Ghumare 97ee4b9a43 fix(install): safer agent selection for first-time users
Before: first-time users (no history) saw "All detected agents"
as the first option in the agent picker. Mashing Enter would
install to all 32 agents, writing files across every adapter's
config dir. Selecting "Select specific agents" also pre-ticked
all 32 agents, requiring the user to un-tick by hand.

After:
- Default option is "Just <detected> (detected)" — one agent,
  low blast radius.
- "Select specific agents" moves above "All detected agents"
  and pre-ticks only the detected agent.
- "All detected agents" gets a second confirm gate
  ("Install to all N agents?") with initialValue: false.
- Hint text on "All" warns "use only if you know".

Returning users still see "Same as last time (Recommended)" as
the first option; their flow is unchanged.

Non-TTY path is unchanged (still auto-detects a single agent).

Wire detectAgent() through quickAgentSelect so the picker can
label and pre-select the detected agent. Empty selection from
the confirm gate is treated as cancellation.
2026-04-20 21:58:44 +01:00
Rohit Ghumare c8d0bbc844 chore: slim CLI install by making heavy deps optional
Move @skillkit/api, @skillkit/tui, @skillkit/mesh, @skillkit/messaging
to optionalDependencies. Drop @skillkit/memory entirely — the CLI
never imported it (only @skillkit/mcp-memory consumes it).

Killing @skillkit/memory removes cozo-node (native Rust) and
@xenova/transformers (~300MB ML stack) from the critical install
path. Making @skillkit/tui optional removes @opentui/core's
prebuild-install toolchain, which was the source of the
inflight/gauge/npmlog/tar/glob deprecation warnings.

Add skipNodeModulesBundle + platform=node + target=node18 to
apps/skillkit tsup config so optional deps stay external.

All TUI/mesh/messaging/api commands already lazy-import via
dynamic import() with surrounding try/catch, so missing optional
deps surface as a graceful error rather than a crash.

Measured impact (npm i skillkit in a clean cache):

  Scenario            Packages  Time   Deprecations  Vulns (crit/high)
  main                544       37s    10            33 (5/5)
  slim (default)      475       18s    3             25 (0/0)
  slim --omit=optional 118      9s     0             0

Core commands (list, find, translate, recommend, install, --help,
--version) smoke-tested in all three scenarios. Optional commands
(ui, mesh, message, serve) confirmed to degrade with a clean
"Cannot find package" error under --omit=optional.
2026-04-20 21:46:46 +01:00
RUFFY-369 27afc45dea fix(agents): address PR review comments for Hermes and align Windsurf tests 2026-04-21 00:17:08 +05:30
RUFFY-369 fb95260eb5 fix(agents): align windsurf adapter with modern SOTA rules path 2026-04-21 00:06:47 +05:30
RUFFY-369 9cbd0e394b chore: remove debug runner and local test artifacts 2026-04-20 15:15:24 +05:30
RUFFY-369 0b94c6001a feat: complete native Hermes support with dual-source parity and test coverage 2026-04-20 15:03:37 +05:30
RUFFY-369 94fa5c8bce feat: complete native Hermes Agent integration with translation and primer support 2026-04-20 14:49:37 +05:30
RUFFY-369 5bd2822f12 fix: add sync markers for Hermes Agent 2026-04-20 13:38:37 +05:30
RUFFY-369 e5d18eba28 fix: remove unused variable in Hermes adapter to fix build 2026-04-20 13:26:11 +05:30
RUFFY-369 1af78cbf26 feat: add missing discovery paths and translation lists for Hermes 2026-04-20 13:15:20 +05:30
RUFFY-369 97c7b2f16b docs: add Hermes Agent to supported agents list 2026-04-20 13:12:20 +05:30
RUFFY-369 5878e9f80c feat: add native support for Hermes Agent 2026-04-20 12:58:31 +05:30
Rohit Ghumare ae8c7a1abb chore: bump version to 1.22.1 2026-04-12 20:38:10 +01:00
Rohit Ghumare 196a959569 Merge pull request #109 from rohitg00/feat/json-spinners-remaining
feat: complete --json and spinners for all remaining commands
2026-04-12 20:21:14 +01:00
Rohit Ghumare 23d1c8932a fix: run agent install in save --json mode, include agents in output 2026-04-12 20:16:44 +01:00
Rohit Ghumare 0c82c58905 feat(cli): add --json output and loading spinners to remaining commands
Add --json flag with structured JSON output to: create, enable, disable,
eval, sync, tap (add/remove/list), translate, save, read.

Add loading spinners to: audit, fix, test, plugin, team, methodology,
hook, remove. Commands that already had spinners get --json-aware no-op
spinners when --json is active to suppress visual output.
2026-04-12 12:02:38 +01:00
Rohit Ghumare 1ce9751797 chore: bump version to 1.22.0 2026-04-12 11:32:58 +01:00
Rohit Ghumare 6485745295 Merge pull request #107 from rohitg00/feat/cicd-json-spinners
feat: reusable GitHub Action, --json output, loading spinners
2026-04-12 11:31:52 +01:00
Rohit Ghumare e9014e130c fix: suppress all stdout pollution in --json mode across all commands
- update: emit JSON on empty skills, gate warn/console.log on !json
- remove: emit JSON on empty results, gate warn/log on !json
- find: gate step() calls on !json
- install: emit JSON error object in catch block instead of console.log
2026-04-12 11:31:21 +01:00
Rohit Ghumare 9e50c8abe1 fix: prevent shell injection in action, suppress stdout in --json mode
- action.yml: pass inputs via env vars, whitelist allowed commands
- All --json commands: use no-op spinner to prevent stdout pollution
- remove: run AGENTS.md update before JSON output (was skipped)
- eval: gate spinner on json format, wrap in try/catch for cleanup
- scan: wrap spinner in try/catch for cleanup on failure
2026-04-12 10:56:35 +01:00
Rohit Ghumare 49fcc532d2 feat: add loading spinners to translate, sync, eval, publish, and scan commands (#88) 2026-04-12 10:41:46 +01:00
Rohit Ghumare ecead6585c feat: add --json flag to 8 CLI commands for structured output (#89) 2026-04-12 10:39:52 +01:00
Rohit Ghumare cc2eb2504c feat: add reusable GitHub Action for CI/CD skill management (#92) 2026-04-12 10:37:01 +01:00
Rohit Ghumare 5d7ca0cd8e Merge pull request #106 from rohitg00/feat/infra-v1.21
feat: progressive disclosure execution layer for MCP server
2026-04-12 00:29:07 +01:00
Rohit Ghumare eda488c960 fix: symlink escape in resource sandbox, search order, global paths
- Resolve symlinks with realpathSync before path containment check
  to prevent symlink-based directory escape in skillkit_resource
- Search project-local skills before home-level (cwd first in roots)
- AGENT_DIR_MAP now maps to arrays, includes non-standard global
  paths (opencode: .config/opencode/skills, windsurf: .codeium/...)
- Extra global dirs scanned when agent filter matches
2026-04-11 21:11:24 +01:00
Rohit Ghumare 559b760202 fix: add 13 missing agent dirs to SKILL_DISCOVERY_PATHS, fix agent filter
- Add .aider, .amazonq, .augment, .bolt, .codegpt, .cody, .devin,
  .lovable, .playcode, .replit, .tabby, .tabnine to discovery paths
- Fix agent filter in getLocalSkillDirs: use AGENT_DIR_MAP lookup
  instead of reverse-engineering from directory prefix (claude != claude-code)
- Update Agent Types code block in agents README to list all 45 agents
2026-04-11 20:32:28 +01:00
Rohit Ghumare ebd26b7c84 docs: fix agent count 32→45 in package READMEs 2026-04-11 20:25:13 +01:00
Rohit Ghumare 8ec5b9d8f2 Add progressive disclosure tools (skillkit_catalog, skillkit_load, skillkit_resource) to MCP server
Three new tools for token-efficient local skill access:
- skillkit_catalog (L1): lightweight catalog of installed skills (~50 tokens/skill)
- skillkit_load (L2): full SKILL.md content for a single skill
- skillkit_resource (L3): specific reference file with path traversal protection

Bumps server version to 1.21.0. Adds 14 new tests (18 total).
2026-04-11 20:24:20 +01:00
Rohit Ghumare 0cba1be49c docs: update package READMEs to 45 agents with full agent table 2026-04-11 19:10:19 +01:00
Rohit Ghumare 9f0eabc876 chore: bump version to 1.21.0 2026-04-11 16:27:20 +01:00
Rohit Ghumare ceeae304b5 Merge pull request #105 from rohitg00/feat/infra-v1.21
feat: trust levels, checksum updates, lock.json, custom taps
2026-04-11 16:26:17 +01:00
Rohit Ghumare bb97e9b747 docs: update agent count to 45, add v1.21.0 feature docs
- Fix "44 agents" → "45 agents" across 34 files (website, docs,
  package.json, tests, extension, API, TUI)
- README: add tap, check, update, publish submit to commands section
- Commands.tsx: add Sources category with tap commands, update manage
  group with remove --source/--all and check
- commands.mdx: full docs for tap, check, update, remove, publish
  submit with all new flags and behaviors
- configuration.mdx: document lock.json and taps.json
- security.mdx: document trust badges system
2026-04-11 14:09:58 +01:00
Rohit Ghumare 8b4f207fa1 fix: gate official badge on GitHub provider type 2026-04-11 13:56:26 +01:00
Rohit Ghumare c533d6f3bc fix: respect --no-federated flag to disable GitHub search 2026-04-11 13:52:02 +01:00
Rohit Ghumare e7dbaeb2b3 fix: standalone path in lock, sync lock on update, honor --force
- install: use actual installed path (handles .md files) for lock
  entry and results instead of reconstructing from skillName
- update: call addSkillToLock after both local and remote updates
  so lock.json stays in sync with metadata
- update: --force bypasses GitHub activity and checksum skip-checks
- update: timestamp comparison falls back to installedAt when
  updatedAt is not set
2026-04-11 13:46:28 +01:00
Rohit Ghumare 05b566c0df fix: address Devin and CodeRabbit review findings
- Use finally for temp cleanup so user cancels don't leak cloned dirs
- Move addSkillToLock outside inner agent loop, merge agents array
- Use source:name as lock key to avoid cross-source collisions
- Gate GitHub activity check on provider.type (skip for GitLab/Bitbucket)
- Normalize source URL to owner/repo before official check
- Include skill name in trust badge output
- Atomic lock.json writes via tmp file + renameSync
- Remove stale --federated suggestion from find no-results message
2026-04-11 13:36:07 +01:00
Rohit Ghumare 56c565bc65 feat: add user-level custom taps for skill sources
Introduce tap add/remove/list commands to manage custom skill sources
stored in ~/.skillkit/taps.json. Taps are included in find/search
results, allowing users to add private or community repositories.
2026-04-11 11:52:46 +01:00
Rohit Ghumare b4582c465d feat: add centralized lock.json for installed skill tracking
Introduce ~/.skillkit/lock.json with LockEntry/LockFile schemas to
track all installed skills in a single file. Install writes entries,
remove deletes them. Enables future team sync and reproducible setups.
2026-04-11 11:50:17 +01:00
Rohit Ghumare d929fe3af0 feat: add checksum-based change detection for skill updates
Compute SHA-256 checksum of SKILL.md on install and store in metadata.
During update, check GitHub pushedAt timestamp and compare checksums
to skip unnecessary re-downloads when content hasn't changed.
2026-04-11 11:49:05 +01:00
Rohit Ghumare 696db60cb4 feat: add trust level badges during install confirmation
Show trust badges for each skill during install: [Official] for known
official sources (Anthropic, Vercel, Expo, Remotion, Supabase, Stripe),
or [Trusted]/[Review]/[Caution] based on TrustScorer analysis.
2026-04-11 11:47:41 +01:00
Rohit Ghumare da14f329fd feat: quarantine cleanup on failure, federated search by default
- Hoist cloneResult above try block so catch can clean up temp dir
  on any failure path, not just the happy path
- Always include GitHub API in find search results (was behind
  --federated flag, now default)
2026-04-11 11:45:03 +01:00
Rohit Ghumare dc3f9ba330 Merge pull request #104 from rohitg00/feat/publish-check-stats
feat: direct publish, GitHub API update detection, quality scores
2026-04-11 11:27:34 +01:00
Rohit Ghumare 4206b8aab1 fix: prevent command injection in auto-publish workflow
- Pass all user-controlled values via env vars instead of
  interpolating ${{ outputs.* }} into inline scripts
- Fix operator precedence bug: entry.source || (owner && repo ? ...)
- Use --body-file instead of heredocs with interpolated values
- Quote all variable references in shell commands
2026-04-11 10:56:33 +01:00
Rohit Ghumare a4540c5fc1 simplify: extract timeAgo and fetchGitHubActivity to shared helpers 2026-04-11 10:50:59 +01:00
Rohit Ghumare 8cfae7e105 feat: auto-publish workflow for skill submissions and add HermesHub source
Add .github/workflows/auto-publish.yml that triggers on skill-submission
labeled issues, extracts JSON from issue body, validates the source repo
exists, runs security scanner and quality evaluation, then auto-merges
passing submissions (score >= 75) or flags them for manual review.

Add NousResearch/hermes-agent to marketplace/sources.json as a federated
search source for Hermes agent skills.
2026-04-11 10:45:44 +01:00
Rohit Ghumare f2183b8e14 feat: direct publish via gh CLI, GitHub API update detection, quality scores
publish submit:
- Runs quality eval + security scan before submission
- Shows quality badge, stars, last push date, and warnings
- Creates issue directly via gh CLI (no browser needed)
- Falls back to manual URL if gh is not installed/authenticated
- Issue body includes quality score, stars, and push date

check:
- Fetches pushed_at from GitHub API for real update detection
- Shows quality badges next to skill names
- Shows stars and push date in verbose mode
- Displays average quality score across all skills
2026-04-11 10:36:29 +01:00
Rohit Ghumare 573bbbeed7 Update README.md 2026-04-11 00:30:03 +01:00
Rohit Ghumare 7003fd3372 docs: add comparison video, update README for v1.20.0
- Add skills-vs-skillkit.mp4 comparison video
- Update agent count from 44 to 45
- Add remove --source/--all to commands section
- Add v1.20.0 callout (live progress, sparse checkout, bulk remove)
2026-04-11 00:25:59 +01:00
Rohit Ghumare c611e70764 fix: bump version in docs packages to 1.20.0 2026-04-10 22:12:40 +01:00
Rohit Ghumare 73f95c0b6e chore: bump version to 1.20.0 2026-04-10 22:11:44 +01:00
Rohit Ghumare 25556d15d9 Merge pull request #103 from rohitg00/feat/clone-progress-sparse
feat: live clone progress + sparse checkout for large repos
2026-04-10 22:10:41 +01:00
Rohit Ghumare 2b1c04e221 fix: address CodeRabbit review findings
- findSkill: fall through to .md check when parseSkill returns null
- Use isPathInside instead of dir.includes(cwd) for location detection
- Optional chaining on meta.source in remove --source filter
- Track fence delimiter type per CommonMark (backtick vs tilde)
- Wrap statSync in try-catch so one bad source doesn't abort all installs
- Add cleanup fallback when sparse-checkout/checkout fails
2026-04-10 22:10:07 +01:00
Rohit Ghumare b1e1e2f266 simplify: extract toAdapterInfo helper, remove spawnGit overloads
- helpers.ts: extract toAdapterInfo() to eliminate 4x repeated object
  construction
- base.ts: remove redundant spawnGit overload signatures, remove
  ?? (() => {}) since spawnGit already handles undefined onProgress
2026-04-10 22:06:06 +01:00
Rohit Ghumare 84fb16486b fix: save metadata for standalone .md skills as sibling dotfiles
Standalone .md skills (e.g. doc_explanation.md) now get metadata saved
as .doc_explanation.skillkit.json in the same directory. This allows
remove --source to find and remove them. Updated saveSkillMetadata,
loadSkillMetadata, loadMetadata, and remove command to handle both
directory and sibling metadata patterns.
2026-04-10 22:03:55 +01:00
Rohit Ghumare 0aae4b16a7 feat: add --all and --source flags to skillkit remove
- skillkit remove --all: removes all installed skills
- skillkit remove --source iii-hq/iii: removes all skills from that source
- Both check .skillkit.json metadata to match source
2026-04-10 21:59:24 +01:00
Rohit Ghumare 244413da79 fix: show logo on TTY regardless of --all/--yes flags 2026-04-10 21:57:39 +01:00
Rohit Ghumare d9d775b189 fix: skillkit read searches all agent dirs and finds standalone .md skills
getSearchDirs now collects skill directories from ALL agent adapters
instead of only the configured agent. This fixes 'skill not found' when
skills were installed to .claude/skills/ but the default agent is
universal (which only searches skills/).

findSkill now also checks name.md for standalone .md skills that were
installed as plain files.
2026-04-10 21:56:06 +01:00
Rohit Ghumare ba09309d5b fix: compute standalone file target path once, use everywhere
Move isStandaloneFile detection and .md suffix normalization before
the existence/force/symlink checks so all code paths use the same
effective target path. Fixes --force not detecting previously installed
standalone skills and symlinks pointing to the wrong filename.
2026-04-10 21:51:30 +01:00
Rohit Ghumare 430bcefaa6 fix: narrow partial clone fallback, cap stderr, add -- before paths
- Restrict try/catch to only the partial clone spawn so
  sparse-checkout/checkout failures bubble up as real errors instead
  of being misreported as "partial clone unsupported"
- Cap stderr accumulator to 4KB to bound memory on verbose clones
- Add -- terminator before sparsePaths in sparse-checkout set to
  prevent user-controlled subpath from being parsed as git options
2026-04-10 21:49:13 +01:00
Rohit Ghumare 3007e9f8fd fix: preserve standalone .md skills as plain files
Instead of wrapping standalone .md skills in a directory, copy them
as-is with .md extension. Skip saveSkillMetadata for standalone files
since it requires a directory. This preserves the original format that
repos like iii-hq/iii use for lightweight single-file skills.
2026-04-10 21:46:18 +01:00
Rohit Ghumare 7160dfddf2 fix: install standalone .md skills by wrapping in a directory
Standalone .md skills (e.g. doc_explanation.md) were copied as plain
files, then saveSkillMetadata tried to write .skillkit.json inside
them causing ENOTDIR. Now detects file sources via statSync and
creates a directory with SKILL.md inside instead.
2026-04-10 21:44:02 +01:00
Rohit Ghumare 16d00a8ec9 fix: address review findings in cloneRepo and scanner
- spawnGit: set stdout to 'ignore' instead of 'pipe' to prevent
  buffer deadlock (git clone writes to stderr, not stdout)
- tryPartialClone: emit fallback message via onProgress instead of
  silently swallowing the error
- scanner: preserve fence markers so PI011 delimiter injection is
  still detected, only strip inner code block content
- scanner: guard against unclosed frontmatter by looking ahead for
  closing --- before entering frontmatter mode
2026-04-10 21:40:45 +01:00
Rohit Ghumare 3457fbc011 fix: sparse checkout includes subpath so skill discovery works
cloneRepo now accepts a subpath option. When set, sparse-checkout
includes both the subpath itself and SKILL_DISCOVERY_PATHS under it.
All four providers pass their parsed subpath through to cloneRepo.

Without this, sparse checkout would skip the subpath directory and
discoverSkills would find nothing.
2026-04-10 21:27:44 +01:00
Rohit Ghumare dd30ee0af0 fix: scanner false positives on markdown code blocks and frontmatter
Strip fenced code blocks and standard YAML frontmatter before scanning
markdown files. This eliminates three categories of false positives:

- PI013: no longer flags standard --- frontmatter delimiters
- CI007: no longer flags curl|sh in code examples
- DE003: no longer flags process.env in code examples

Real threats in prose (outside code blocks) are still caught.
2026-04-10 21:25:03 +01:00
Rohit Ghumare 1fb95fd57e feat: add live clone progress and sparse checkout for large repos
Replace silent execFileSync with async spawn + --progress flag so the
spinner shows real download progress (e.g. "Receiving objects 45%").
For large monorepos, try partial clone (--filter=blob:none) with sparse
checkout of SKILL_DISCOVERY_PATHS first, falling back to regular
--depth 1 clone if the server doesn't support it. Also adds
--single-branch --no-tags to all clones.

Shared cloneRepo() helper in base.ts eliminates duplicate clone logic
across all four git providers.
2026-04-10 20:28:38 +01:00
Rohit Ghumare dfa8d12c65 Merge pull request #100 from rohitg00/fix/audit-batch-3
fix: complete chalk→onboarding migration, refactor install.ts
2026-04-07 19:58:50 +01:00
Rohit Ghumare 172602f173 fix: preserve exit codes in refactored install.ts, fix spinner API
- selectSkills/selectAgents now return { result, exitCode } to
  distinguish errors (exit 1) from cancellations (exit 0)
- Fixes: --skill with nonexistent name returned 0 instead of 1
- Fixes: --agent with invalid name returned 0 instead of 1
- ai.ts: s.stop('msg', 1) → s.stop(colors.error('msg'))
  (clack spinner.stop only accepts message, not exit code)
2026-04-07 15:46:15 +01:00
Rohit Ghumare e542c4e484 fix: complete chalk→onboarding migration, refactor install.ts (#87 #88 #93)
Complete chalk/ora elimination:
- All 41 chalk imports removed from commands/ (41→0)
- All ora imports removed (replaced with onboarding spinner)
- Consistent use of colors/warn/success/error/step helpers

install.ts refactor (#93):
- extract execute() from 700→50 lines (orchestration only)
- 14 focused private methods: resolveSource, listSkills,
  selectSkills, selectAgents, selectMethod, runSecurityScan,
  confirmInstall, performInstall, cleanupTemp, updateAgentsMd,
  showResults, showSkillsShStats, showProTips

Closes #87, closes #93
Partial progress on #88 (spinners added via migration)
2026-04-07 14:02:01 +01:00
Rohit Ghumare 9fa542e8d8 Merge pull request #99 from rohitg00/fix/audit-batch-2
fix: normalize --agent flag, migrate 6 commands to onboarding helpers
2026-04-07 12:30:28 +01:00
Rohit Ghumare f714a39a46 fix: add deprecation warning when --agents is used
generate.ts and manifest.ts now warn when --agents (deprecated) is
used instead of --agent. Message: "Warning: --agents is deprecated,
use --agent instead (--agents will be removed in v2.0)"

Findings 3 (scan.ts stderr) and 4 (translate.ts stderr) skipped:
error() from onboarding goes to stdout via clack — this is the
standard pattern across all migrated commands. Changing individual
commands would break consistency.
2026-04-07 12:27:37 +01:00
Rohit Ghumare d9142c8125 fix: simplify review — error styling, double-wrap, aliases
- translate.ts: 7 error paths used colors.muted() (gray) instead of
  error() (red) — errors were invisible. Now properly styled.
- update.ts: error(colors.muted(...)) double-wrapped ANSI codes.
  Split into s.stop() for headline + console.log for detail.
- enable.ts: dropped successLog/errorLog aliases, renamed counters
  to successCount/failedCount (matches translate.ts pattern)
- update.ts: removed unused error import
2026-04-07 12:24:15 +01:00
Rohit Ghumare 64944a1c50 fix: normalize --agent flag, migrate 6 commands to onboarding helpers
Option naming (#94):
- generate.ts, manifest.ts: accept --agent as primary (--agents as alias)

Chalk→onboarding migration (#87, #88):
- update.ts: chalk/ora → colors/spinner from onboarding
- translate.ts: chalk → colors/warn/success from onboarding
- remove.ts: chalk → colors/warn/success/error from onboarding
- enable.ts: chalk → colors/warn/successLog/errorLog from onboarding
- scan.ts: stderr.write → error() from onboarding
- list.ts: chalk → colors/warn from onboarding

Chalk imports reduced from 41 to 36 across commands.
All 13 packages build, all 25 test suites pass.
2026-04-07 12:15:03 +01:00
Rohit Ghumare 12bba7f32c Merge pull request #98 from rohitg00/fix/openclaw-cleanup
refactor: deduplicate OpenClaw adapter, fix clawdbot config
2026-04-07 11:57:07 +01:00
Rohit Ghumare 02fe3f2509 fix: TUI uses hardcoded AgentType — import from @skillkit/core instead
The TUI had a manually-maintained 44-agent AgentType union in
translator.service.ts that fell out of sync when openclaw was added
to core. Replace with re-export from @skillkit/core so it stays in
sync automatically. Fixes CI typecheck failure from #86.
2026-04-07 11:52:16 +01:00
Rohit Ghumare 808ae83271 refactor: deduplicate OpenClaw adapter, fix clawdbot config
Follow-up to #86 — cleanup without changing contributor attribution.

- OpenClawAdapter extends ClawdbotAdapter (removes 80 lines of copy-paste)
- Revert clawdbot config to legacy paths (.clawdbot/skills, AGENTS.md)
- OpenClaw detection: ~/.openclaw or openclaw.json
- Widen ClawdbotAdapter property types for extensibility
- Fix tests: adapter count 44→45, remove stale detection assertions
2026-04-07 11:48:05 +01:00
Rohit Ghumare 5324e4528b feat: add OpenClaw agent adapter (Clawdbot rebrand) (#86)
feat: add OpenClaw agent adapter (Clawdbot rebrand)
2026-04-07 11:40:08 +01:00
Rohit Ghumare 59ea709613 fix: version display, install UX — audit findings (#95)
* fix: version display, install UX — audit findings

- Fix version showing hardcoded 1.7.6 instead of actual 1.19.2
  - Export setVersion/setAgentCount from @skillkit/cli
  - Call setVersion(version) and setAgentCount(getAllAdapters().length) in cli.ts
  - Change fallback from '1.7.6' to 'dev' so stale values are obvious

- Fix install pre-selecting all skills by default (bad UX)
  - Add "Install all / Select specific" prompt before multiselect
  - When selecting manually, start with nothing pre-selected
  - Apply same fix to both InstallCommand and runInstallFlow()
  - Matches existing quickAgentSelect pattern

Fixes found during comprehensive codebase audit.
Related issues: #87, #88, #89, #90, #91, #92, #93, #94

* refactor: extract quickSkillSelect, use getAdapterCount

- Extract duplicated "Install all / Select specific" pattern into
  quickSkillSelect() in prompts.ts (mirrors existing quickAgentSelect)
- Both install.ts and runInstallFlow() now use the shared helper
- Add getAdapterCount() to @skillkit/agents to avoid allocating 44
  spread-copied objects just to call .length
- Use getAdapterCount() in cli.ts instead of getAllAdapters().length
2026-04-07 10:44:29 +01:00
Lumina Mao 6ed78ceba7 fix: address PR review comments for OpenClaw adapter
- Remove legacy clawdbot path checks from OpenClawAdapter.isDetected()
  so pure clawdbot workspaces are not hijacked by OpenClaw detection
- Add '.openclaw/agents' to ALL_AGENT_DISCOVERY_PATHS so agent
  discovery works for OpenClaw agent directories
2026-03-27 05:10:21 -07:00
Lumina Mao 3509b74f85 feat: add OpenClaw agent adapter (Clawdbot rebrand)
OpenClaw (formerly Clawdbot) is a local-first AI agent framework with a
persistent gateway daemon. This adds first-class OpenClaw support:

- New `openclaw` agent type in AgentType enum and all Record types
- New `OpenClawAdapter` class with detection for `~/.openclaw/` + `openclaw.json`
- OpenClaw agent config: `skills/` dir (not `.clawdbot/skills/`), CLAUDE.md config
- Extended frontmatter fields: permissions, triggers, metadata, version, scan_exempt
- Agent dirs: `agents/` and `~/.openclaw/agents/`
- Command format: `.claude/commands/` directory
- Translator format map: `openclaw` → `skill-md`
- Simplified clawdbot adapter detection (legacy paths only)

OpenClaw SKILL.md files use an extended YAML frontmatter schema:
  - permissions: { filesystem: none|read|write, network: true|false }
  - triggers: [{ command: /skill-name }]
  - metadata.openclaw.requires: { bins: [], env: [], os: [] }

This enables `skillkit translate <skill> --to openclaw` producing
SKILL.md files compatible with the OpenClaw gateway runtime.

Ref: https://docs.openclaw.ai
2026-03-22 09:03:19 -07:00
Rohit Ghumare 5691b10c7e feat: add multi-tier eval engine (skillkit eval) (#85)
* feat: add multi-tier eval engine (skillkit eval)

6-tier evaluation system for comprehensive skill assessment:
- Tier 1: LLM quality scoring (G-Eval pattern, 6 dimensions)
- Tier 2: Contradiction detection (formal rules + LLM semantic)
- Tier 3: Behavioral security (code analysis + taint tracking + LLM)
- Tier 4: Sandbox execution testing (Docker, graceful skip)
- Tier 5: Dynamic marketplace benchmarks (percentile ranking)
- Tier 6: Community signals (freshness, metadata, content health)

Works without API keys (heuristic fallback for Tier 1, Tiers 5-6).
Full LLM evaluation with --provider flag.

* fix: address Devin review — input validation for eval CLI

- --min-score NaN bypass: validate parseInt result before comparison
- --timeout NaN propagation: skip NaN timeout instead of passing to Docker
- --tier invalid input: graceful error message instead of unhandled throw
- scoreContentSize formula: cap sub-optimal at 99 to distinguish from optimal

* fix: address CodeRabbit review findings on eval system

- Harden contradiction/security prompts against prompt injection by
  wrapping untrusted content in <skill_content> XML tags and adding
  explicit "treat as untrusted data" instructions
- Use head+tail content sampling in security prompt instead of head-only
  truncation to catch malicious payloads at end of content
- Add missing Tier 4 sandbox formatter to reporter.ts
- Fix misleading sampleSize fallback in dynamic-benchmark.ts
- Move --min-score NaN validation before engine.evaluate() to avoid
  wasting LLM calls on invalid input
- Add truncation indicator to quality-cot.ts prompts
- Add term length limits (>100 chars) in contradiction.ts to mitigate
  ReDoS risk on dynamically constructed regex

* fix: address round 2 review findings on eval system

- Wrap quality-cot prompts with <skill_content> XML tags and untrusted
  data instructions, consistent with contradiction/security prompts
- Change truncateContent to head+tail sampling (4000+2000) instead of
  head-only, so completeness/token-efficiency evaluators see both
  beginning and end of long skills
- Fix escapeXmlTags regex to handle whitespace variants before closing
  angle bracket (</skill_content >, </skill_content\n>)
- Type DIMENSION_PROMPTS with Record<EvalDimension, PromptBuilder> for
  compile-time key validation
- Clamp estimatePercentile return to [0,100] range defensively
- Make buildStatsFromMarketplace async with periodic yields (every 50
  skills) to avoid blocking the event loop on first-run cache miss
- Extract parsedTimeout local variable in eval.ts to avoid double
  parseInt parsing

* fix: address round 3 Devin + CodeRabbit findings on eval system

- Scan both code blocks AND full content for dangerous patterns in
  behavioral-security.ts, with deduplication by description+snippet
  to avoid double-reporting (Devin: security scanner skipped prose)
- Use non-greedy regex /\[[\s\S]*?\]/ in parseSemanticFindings to
  match first complete JSON array instead of greedily spanning to
  last bracket in LLM response (Devin: greedy regex corrupted JSON)
- Fix formatSandboxDetails to use r.testCase matching SandboxResult
  type instead of r.name which doesn't exist (Devin: property mismatch)
- Make MarketplaceSkill.description optional to match marketplace
  schema where only id/name/source/tags are required (CodeRabbit)
- Rename sandbox test case from "code example execution" to "code
  block content validation" since it validates content not execution
  (CodeRabbit)

* fix: address round 4 Devin + CodeRabbit findings on eval system

Inline fixes:
- Replace greedy JSON regex in behavioral-security.ts runLLMAnalysis
  with balanced bracket extraction that correctly handles ] inside
  JSON string values
- Replace non-greedy regex in contradiction.ts parseSemanticFindings
  with same balanced bracket extraction (non-greedy also breaks on
  inner brackets)
- Fix crossValidatedCount in behavioral-security.ts to accumulate
  (+= uniqueEngines.size) instead of replacing (Math.max)
- Fix gradeDeterministic: cleanExit && hasOutput without matching
  expectedOutcome now returns passed:false score:50 instead of
  passed:true score:75
- Docker unavailable returns score:-1 sentinel instead of 0/F;
  engine.ts filters score<0 tiers from overall average so
  Docker-less machines aren't penalized

Duplicate fix:
- Add score field to SandboxResult type; store gradeResult.score
  in each result; compute tier score from average of numeric scores
  instead of boolean pass rate

Nitpick fixes:
- Distinguish "Docker unavailable" from "No tests executed" in
  formatSandboxDetails
- Tighten base64 obfuscation regex to require 4-char groups
- Only push 'llm' to engines when LLM actually produced findings
- Bound \s+ to \s{1,10} in dynamically constructed regexes in
  contradiction.ts to prevent catastrophic backtracking
- Validate cache timestamp with Number.isFinite() in loadCache to
  reject corrupted cache files with NaN timestamps
2026-03-10 18:34:32 +00:00
Rohit Ghumare 46153e6eb0 fix: update stale stats, sync agent carousel, refresh attribution (#84)
* fix: update docs, TUI help, and website for v1.19.2 gaps

- docs/index.mdx: version v1.18.0 → v1.19.2, add skills.sh install
  source, add methodology packs to next steps
- docs/rest-api.mdx: health check example version 1.12.0 → 1.19.2
- docs/methodology.mdx: new page documenting 5 packs with 14 skills
- docs/meta.json: add methodology to page ordering
- Hero.tsx: show skills.sh install in terminal animation
- Help.tsx: fix shortcut conflicts — add Session section (l=Timeline,
  v=Lineage, f=Handoff), remove stale f=Find/v=Validate mappings

* fix: update stale stats across repo, website, TUI, CLI, and docs

- Fix agent count: 32 → 44 across package.json, core, TUI READMEs
- Fix source count: 31+ → 34+ across website (Hero, Features, WhySkillKit)
- Fix skill count: 15K/15,000+ → 400K+ everywhere (SkillKit aggregates
  from registries like skills.sh 83K+, SkillsMP 351K+, not just bundled)
- Add 13 missing agents to carousel (Devin, Aider, Cody, Amazon Q,
  Augment, Replit, Bolt, Lovable, Tabby, Tabnine, CodeGPT, PlayCode,
  Universal) — now shows all 44
- Refactor Attribution.tsx to import from marketplace/sources.json
  (single source of truth, auto-shows all 34 sources)
- Fix 8 broken trending skill IDs that didn't resolve in skills.json
- Update fumadocs site (Hero, Commands, layout, page, Documentation)
- Update CLI generate command hints and API docs description
- Increase carousel scroll animation 35s → 45s for more agents
- Add resolveJsonModule to website tsconfig.json
2026-03-10 15:09:31 +00:00
Rohit Ghumare 7c8ba72462 fix: update docs, TUI help, and website for v1.19.2 gaps (#82)
- docs/index.mdx: version v1.18.0 → v1.19.2, add skills.sh install
  source, add methodology packs to next steps
- docs/rest-api.mdx: health check example version 1.12.0 → 1.19.2
- docs/methodology.mdx: new page documenting 5 packs with 14 skills
- docs/meta.json: add methodology to page ordering
- Hero.tsx: show skills.sh install in terminal animation
- Help.tsx: fix shortcut conflicts — add Session section (l=Timeline,
  v=Lineage, f=Handoff), remove stale f=Find/v=Validate mappings
2026-03-06 09:08:50 +00:00
Rohit Ghumare 06d1ba6420 optimize 14 skills via tessl review (avg 24% → 92%) (#81)
Ran `npx tessl skill review --optimize` on all methodology pack
skills and find-skills. Key improvements:

- Better descriptions with "Use when..." clauses and concrete verbs
- Lowercase-hyphenated name format for consistency
- Trimmed self-evident prose Claude already understands
- Added executable examples and quick reference tables
- Condensed verbose sections into compact tables/summaries
- Fixed YAML parsing errors (unquoted colons in descriptions)

Net result: -552 lines across 14 files.
2026-03-06 08:53:32 +00:00
Rohit Ghumare 9b85e40196 feat: add Context Engineering and Antigravity Awesome Skills sources (#80)
* feat: add Context Engineering and Antigravity Awesome Skills sources

Add two major community skill repositories to the marketplace:

- muratcankoylan/Agent-Skills-for-Context-Engineering (12.6K stars):
  13 skills on context engineering, cited in Peking University paper
- sickn33/antigravity-awesome-skills (16.8K stars):
  954+ agentic skills across 9 categories for Claude Code, Gemini CLI,
  Cursor, Copilot and more

Sources: 31 → 33 curated collections
Skills: 15,079 → 15,136 indexed entries

* fix: deduplicate skill IDs and fix slack/notion ID mismatch

- Fix ID mismatch: slack-automation → notion-automation (name/desc were Notion)
- Remove 16 generic duplicate entries that clashed with detailed ones
- Total skills: 15,136 → 15,120 after dedup
2026-03-02 10:56:18 +00:00
Rohit Ghumare a6c0905a7f fix(extension): local content extraction for Chrome Web Store approval (#76)
* fix(extension): replace server API with local content extraction

Chrome Web Store rejected the extension because the core "Save page as
Skill" feature called https://skillkit.sh/api/save-skill which is
unreachable during review. This rewires page saving to work entirely
locally using chrome.scripting.executeScript to extract page content
(title, meta description, headings, body text) directly in the browser.

- Remove API_URL and callSaveApi() server dependency
- Add extractPageContent() via chrome.scripting.executeScript
- Add detectTags() with weighted keyword scoring (URL/headings/body)
- Add buildPageSkill() to generate SKILL.md with frontmatter locally
- Add scripting permission to manifest
- Pass tabId from popup to background for script injection targeting
- Block chrome-extension:// and chromewebstore.google.com URLs
- Add console.error logging in catch blocks for debuggability
- Guard currentTabId validity in popup click handler
- Update store listing to reflect fully local processing
- Bump version to 1.20.0

* fix(extension): address code review findings for robustness

- Extract RESTRICTED_PREFIXES and isRestricted() into shared constants.ts
  so popup and background use the same URL blocklist
- Fix yamlEscape to quote YAML bare scalars (true/false/null/yes/no/on/off)
  and numeric strings that parsers would coerce to non-string types
- Apply yamlEscape to skill name fields in both buildPageSkill and
  buildSelectionSkill to prevent YAML misinterpretation
- Switch tag detection from substring matching to word-boundary regex
  to eliminate false positives (e.g. "js" matching "adjustments")
- Check chrome.runtime.lastError in download callback and always
  revoke blob URL to prevent leaks on download failure
2026-02-28 06:59:04 +00:00
Rohit Ghumare 1cb76f9831 feat: integrate skills.sh as first-class registry
* feat: integrate skills.sh as first-class registry

Add SkillsShRegistry and SkillsShProvider so users can install skills
directly from skills.sh (e.g. `skillkit install skills.sh/owner/repo/skill`).
The find command now searches skills.sh by default alongside the local
marketplace. Post-install shows skills.sh popularity stats and pro tips
highlighting skillkit's unique features (translate, recommend, evaluate).

* fix: address CodeRabbit and Devin review findings for skills.sh integration

- Fix path traversal vulnerability in SkillsShProvider.clone (validate subpath containment)
- Fix federated search skipped for interactive queries (use searchTerm instead of this.query)
- Guard showSkillsShStats to skip network call for local providers
- Replace deprecated npm --production with --omit=dev
- Fix loose includes() match in getSkillStats to use strict endsWith()
- Fix FederatedSearch resilience: don't re-throw RateLimitError, return partial results
- Forward timeoutMs through FederatedSearch to registries
- Extract shared formatCount utility to helpers.ts (deduplicate find.ts/install.ts)
- Fix install hint to use skill.source instead of fragile skill.description
- Fix timer leak in fetchLeaderboard using finally block
- Deduplicate URL parsing via shared parseSkillsShParts helper
- Validate --agent flag values against known agent types
2026-02-22 21:39:50 +05:30
Rohit Ghumare a312640609 fix: security hardening and code quality fixes
* Security hardening and code quality fixes

- Replace execSync with execFileSync to prevent shell injection (providers, executor, fetcher, publish)
- Add security headers: X-Content-Type-Options, X-Frame-Options, Content-Security-Policy, Referrer-Policy
- Add input validation for save route name field to prevent path traversal
- Fix rate limiter IP extraction (x-forwarded-for + x-real-ip fallback)
- Default server bind to 127.0.0.1 instead of 0.0.0.0
- CORS fallback to * (configurable via options.corsOrigin)
- Use execFileSync in publish submit (avoid shell injection when opening browser)
- TLS-aware health checks and HTTPS support in RemoteTransport
- Conditional rejectUnauthorized for TLS (self-signed configurable)
- Add **/.env.local patterns to .gitignore
- Formatting: double quotes, trailing commas (Prettier)

* fix: address CodeRabbit and Devin review findings from PR #74

- TLS: default allowSelfSigned=true to preserve self-signed cert workflow;
  enforce rejectUnauthorized=true when trustedCAs are supplied in client context
- Signature verification: verifySecureMessage now cryptographically verifies
  signatures using PeerIdentity.verifyHex instead of only checking fingerprints
- WebSocket: fix timeout handle leak in performClientHandshake; add error
  logging to empty catch blocks; add per-socket error handler; pre-compute
  signature once in broadcast(); add send error callbacks; reject startup if
  TLS configured but certInfo missing
- Command parsing: replace broken regex tokenizer with shared splitCommand()
  utility that correctly handles --flag="value with spaces"
- Rate limiter: prefer x-real-ip, fall back to rightmost x-forwarded-for entry
- Save route: scope IPv6 prefix checks to actual IPv6 addresses; stop leaking
  internal error messages to clients
- Publish: extract shared parseSkillFrontmatter(); fix getRepoInfo to use
  async execFileSync; fix path containment checks with separator
- Remote transport: add rejectUnauthorized option; bracket IPv6 in URLs;
  fix host:port splitting for IPv6 with lastIndexOf
- Health checks: add tls/tlsAllowSelfSigned to Host type; pass https options
- Fetcher: validate owner/repo; derive indexDir from INDEX_PATH
- .gitignore: add recursive **/.env pattern, remove redundant entries

* fix(executor): restore shell feature support in shellExecutor

The previous security hardening replaced execSync with execFileSync,
which broke commands using pipes, redirects, and subshells. Now detects
shell metacharacters and falls back to sh -c for those commands while
keeping execFileSync for simple commands.
2026-02-22 21:39:47 +05:30
Rohit Ghumare 39b94534ec chore: release v1.19.2 2026-02-20 00:16:28 +05:30
Rohit Ghumare aeb2b05f15 fix: update composioHQ repo name from awesome-claude-code-skills to awesome-claude-skills (#73)
Closes #72
2026-02-17 19:28:39 +00:00
Rohit Ghumare 5991fead9b fix: compact Features grid — 3 cols mobile, 4 cols desktop 2026-02-14 16:08:19 +05:30
Rohit Ghumare 1d3a779c2e fix: show Docs link on mobile nav (#71)
* chore: migrate domain from agenstskills.com to skillkit.sh

Update all OG/Twitter meta tags, API endpoints, docs links, badge
URLs, privacy policy, extension store listing, and README references
to use skillkit.sh. Both skillkit.sh and agenstskills.com are treated
as equal domains — privacy policy, store listing, and docs reference
both.

* perf: skip Vercel builds when docs unchanged

Add ignoreCommand to both docs/skillkit and docs/fumadocs vercel.json.
Vercel will skip rebuilds when the respective docs folder has no
changes, saving ~1h+ of build minutes per billing cycle.
2026-02-14 10:31:26 +00:00
Rohit Ghumare 2fe4702bd6 chore: migrate domain to skillkit.sh (#70)
* chore: migrate domain from agenstskills.com to skillkit.sh

Update all OG/Twitter meta tags, API endpoints, docs links, badge
URLs, privacy policy, extension store listing, and README references
to use skillkit.sh. Both skillkit.sh and agenstskills.com are treated
as equal domains — privacy policy, store listing, and docs reference
both.

* perf: skip Vercel builds when docs unchanged

Add ignoreCommand to both docs/skillkit and docs/fumadocs vercel.json.
Vercel will skip rebuilds when the respective docs folder has no
changes, saving ~1h+ of build minutes per billing cycle.
2026-02-14 10:24:08 +00:00
Rohit Ghumare 28ed83deb0 chore: release v1.19.1 2026-02-14 14:24:41 +05:30
Rohit Ghumare 7c4ee9cfef refactor: simplify homepage by removing 5 sections and adding docs CTA (#69)
Remove WhySkillKit, StackBuilder, BadgeGenerator, Commands, and
TeamEnterprise sections to streamline the landing page from 14 to 9
sections. Replace Extension nav link with Docs, remove duplicate Docs
link, and add a lightweight docs CTA between AdvancedFeatures and
UseCases.
2026-02-14 07:50:00 +00:00
Rohit Ghumare 64cafc76a1 feat: add TUI screens for session intelligence (timeline, lineage, handoff) (#68)
Wire up 3 new screens from PR #65's session intelligence commands into the TUI with
keyboard navigation (l=timeline, v=lineage, f=handoff) and a new Session sidebar section.
2026-02-14 07:33:01 +00:00
Rohit Ghumare 7e3b31b43b feat: add session intelligence — timeline, handoff, and lineage (#65)
* feat: add session intelligence — timeline, handoff, and lineage commands

Three new skill-centric session intelligence features:
- `skillkit timeline` — unified chronological event stream merging skill executions, git commits, observations, decisions, and snapshots
- `skillkit session handoff` — generates structured markdown for agent-to-agent context transfer with accomplished/pending tasks, key files, observations, and recommendations
- `skillkit lineage` — tracks skill impact graph connecting skills to files, commits, and observations with aggregate stats

Includes 44 tests, updated docs/website to reflect 44 agents, and CodeRabbit review fixes (defensive access, type validation, double-count prevention).

* fix: address CodeRabbit review round 2

- Fix primer.mdx example: "29 more agents" → "41 more agents"
- Validate invalid since date in timeline (return empty instead of silent filter-all)
- Guard hist.durationMs with Number.isFinite before formatting
- Fix misleading "commits" label → "changes" for activity log entries
2026-02-14 07:11:44 +00:00
Rohit Ghumare ff089429ae feat: redesign website with aggregator positioning (#67)
* feat: redesign website with aggregator positioning and competitor landscape

- Add WhySkillKit section with competitor comparison table (Vercel skills, PRPM, Askill, Skild, Paks)
- Show SkillKit as meta-package manager aggregating 31+ sources, not competing with them
- Add source grid showing all curated repositories (Anthropic, Vercel, Expo, Supabase, Stripe, etc.)
- Update Hero tagline: "One CLI. Every Source. Every Agent. Zero Telemetry."
- Fix agent count from 32 to 44 in Features stats
- Reframe comparison table: "Simple Installers" vs "SkillKit" instead of vague "Without"
- Update CompatibilityMatrix with all 44 agents (was 16)
- Add zero-telemetry, Apache 2.0, no-account trust signals
- Update nav to include "Why SkillKit" link

* feat: update terminal demo to showcase aggregator workflow

Show install from multiple sources (Anthropic, Vercel), auto-translation
to 44 formats, security scanning, and cross-source recommendations.

* feat: update promo video with aggregator positioning

Updated Remotion video to reflect SkillKit's meta-package manager identity:
- Version bumped from v1.7.5 to v1.19.0 across all scenes
- Install scene shows multi-source aggregation + security scan
- Find scene searches 31+ sources (15K+ skills)
- Translate scene shows cross-source bulk translation
- Workflow scene replaced with security scanner (46 rules)
- Recommend scene shows cross-source recommendations with source labels
- TUI scene updated with source attribution and 44 agents
- Manifest scene shows multi-source team sync
- Logo scene: "One CLI. Every Source. Every Agent." + "Zero Telemetry"
- Agent count updated from "17 agents" to "44 agents | 31+ sources | 15K+ skills"
2026-02-14 07:10:35 +00:00
Rohit Ghumare 6c3cecec4d chore: add v1.19.0 extension zip and remove old one 2026-02-14 11:48:52 +05:30
Rohit Ghumare 8ed4ada674 chore: release v1.19.0 2026-02-14 11:33:57 +05:30
Rohit Ghumare 514de86727 feat: server-side save-skill API for Chrome extension (#66)
* feat: move extension save-skill to server-side API

Chrome Web Store rejected the content script approach since it doesn't
inject on pre-existing tabs. Move webpage-to-skill conversion from
client-side to a server-side API route that uses Turndown + weighted
tag detection, eliminating the need for content scripts entirely.

- Add POST /api/save-skill route with SSRF protection and rate limiting
- Rewrite extension to call API with tab URL instead of injecting scripts
- Remove content script, scripting permission, and turndown dependency
- Add name field validation and YAML-escape source URLs
- Bump extension manifest to v1.18.0

* fix: update privacy policy and store listing for server-side save

Privacy policy previously stated "no external requests" which is now
inaccurate. Updated to clearly disclose that the page URL is sent to
agenstskills.com for processing, what data is NOT sent, and that
nothing is stored server-side.

Store listing updated to match: removed "no server" claims, added
data flow explanation, permissions justifications, and data usage
disclosure section for the Chrome Web Store Privacy tab.

* fix: address Devin and CodeRabbit review findings

- Fix SSRF IPv6 checks blocking legit domains (ffmpeg.org, fdroid.org)
  by requiring colon in fc00:/ff prefixes (Devin)
- Add 5MB response body size limit to prevent OOM on large pages,
  applied to both extractFromUrl and fetchGitHubContent (CodeRabbit)
- Guard response.json() in callSaveApi against non-JSON error pages
  from proxies returning HTML 502/504 (CodeRabbit)
- YAML-escape source URL in buildSelectionSkill to match server-side
  handling of URLs with #, :, or query strings (CodeRabbit)
2026-02-14 06:00:28 +00:00
Rohit Ghumare bf5903bf7f chore: release v1.18.0 2026-02-11 20:50:49 +00:00
Rohit Ghumare aafa086314 feat: add skillkit doctor command and enhance skillkit status (#64)
* feat: add `skillkit doctor` command and enhance `skillkit status`

- New `skillkit doctor` command with 10 health checks across 3 categories
  (environment, configuration, skills) with --json and --fix flags
- Enhanced `skillkit status` shows project overview dashboard when no
  active session exists instead of bare "No active session found" message
- Overview includes agent, config, version, skills count, recent history

* feat: add skill activity log, session snapshots, and session explain

Three new session intelligence features:

- Activity Log: tracks which skills were active per git commit
  (`skillkit activity` with --skill, --limit, --json flags)
- Session Snapshots: save/restore named snapshots of session state
  (`skillkit session snapshot save|restore|list|delete`)
- Session Explain: structured summary of current session
  (`skillkit session explain` with --json, --no-git flags)

Includes path traversal protection on snapshot names, YAML validation
on parsed activity data, and robust error handling on snapshot restore.

983 tests passing (942 core + 41 CLI including 14 E2E tests).

* feat: add issue planner - generate plans from GitHub Issues

New `skillkit issue plan` and `skillkit issue list` commands that
fetch GitHub Issues via `gh` CLI and generate StructuredPlans.
Parses checkboxes, file mentions, and labels from issue body.
29 new tests, all passing.

* fix: address CodeRabbit review suggestions for PR #64

- doctor.ts: use execFileSync, typed AgentType, remove as-any casts
- activity.ts: validate parseInt with radix and NaN guard
- issue.ts: wrap JSON.parse in try/catch for gh CLI output
- issue-planner.ts: guard JSON.parse, fix includeTests no-op ternary,
  remove duplicate IssuePlanMetadata (import from types.ts)
- status.ts: typed StatusOverview interface, remove as-any casts
- snapshot-manager.ts: align observations param with SessionSnapshot type
- session.ts: proper type mapping for observations (no double cast)
- activity-log.ts: min-length guard for SHA prefix match
- e2e tests: use top-level imports instead of inline require()
- commands.test.ts: add assertions for DoctorCommand, IssuePlanCommand,
  IssueListCommand

* fix: address review feedback from CodeRabbit and Devin

- Include test step in no-checklist fallback when includeTests is true
- Restore observations from snapshot in SessionSnapshotRestoreCommand

* fix: address remaining CodeRabbit and Devin review feedback

- doctor.ts: Use getAdapter() per AgentType instead of getAllAdapters()
  spread (which destroys prototype methods like isDetected)
- doctor.ts: Use getGlobalSkillsDir() from AGENT_CONFIG instead of
  hardcoded path formula
- session-explainer.ts: Defensively default state.history and
  state.decisions to empty arrays
- session-explainer.ts: Use loadConfig().agent with skillSource fallback
  instead of always using skillSource as agent name
- observation-store.ts: Add static readAll() that reads observations
  without sessionId mismatch clearing
- session.ts: Use ObservationStore.readAll() for snapshot save to avoid
  empty observations due to sessionId mismatch
2026-02-11 20:26:51 +00:00
Rohit Ghumare 344f081664 feat: add privacy policy page for Chrome Web Store compliance 2026-02-11 17:56:38 +00:00
Rohit Ghumare 86c1e5d8f9 chore: release v1.17.0 2026-02-10 11:21:57 +00:00
Rohit Ghumare 9930096242 fix: MCP server fails to start via npx (#58) (#63)
* fix: MCP server fails to start via npx — symlink + skills.json issues

1. isMain guard: process.argv[1] (symlink path) never matched
   import.meta.url (real path). Fixed with realpathSync comparison.

2. skills.json not in npm package: prebuild copies marketplace/skills.json
   to data/ dir, included in package files.

3. Version string bumped from 1.12.0 to 1.16.0.

Closes #58

* fix: guard realpathSync against undefined argv and resolve both paths

- Wrap in try/catch so library imports don't crash
- Check process.argv[1] exists before calling realpathSync
- Also resolve import.meta.url with realpathSync for pnpm/hoisted setups
2026-02-10 11:13:05 +00:00
Rohit Ghumare 24ff833265 feat: Chrome extension — Save any webpage as a Skill (#62)
* fix: remove redundant GitHub Star button from Hero section

Star count is already visible in navbar and stats bar on all screen sizes.

* fix: keep GitHub Star button on mobile, hide on desktop

Star button uses sm:hidden so it only appears on mobile where
the navbar star badge is less prominent. On desktop (sm+), the
navbar star badge is sufficient.
2026-02-10 10:13:47 +00:00
Rohit Ghumare 12ac7356f8 docs: add Chrome extension to website, fumadocs, and README (#61)
- Website Hero: "Add to Chrome" button (white, high contrast) between
  install command and GitHub star button
- Website navbar: "Extension" link in desktop nav
- Fumadocs: new chrome-extension.mdx page with install, usage,
  architecture, permissions, and build docs
- README: Chrome extension section + link in header nav
- Extension README: setup and usage guide
2026-02-10 09:57:51 +00:00
Rohit Ghumare 53b3f4f839 feat: add Chrome extension to save webpages as skills (#60)
Fully browser-based — no local server required. Content script extracts
page content as markdown (Turndown), background generates SKILL.md with
frontmatter and auto-tags, and downloads via chrome.downloads API.

- Manifest V3 with contextMenus, activeTab, downloads permissions
- Content script: HTML-to-markdown via Turndown, extracts article/main
- Background: SKILL.md generation (slugify, YAML frontmatter, tag detection)
- Downloads to skillkit-skills/{name}/SKILL.md in browser Downloads folder
- Monochromatic popup UI matching website design system
- Context menu: "Save page as Skill" / "Save selection as Skill"
- POST /save API endpoint still available for CLI users
2026-02-10 09:49:52 +00:00
Rohit Ghumare 896eff184c feat: standards reference implementation — URL-to-Skill, AGENTS.md, spec validation (#59)
* feat: implement standards reference — URL-to-Skill, AGENTS.md, spec validation

Phase 1-4 of positioning SkillKit as THE runtime implementing all three
AI agent skill standards (Agent Skills, AGENTS.md, well-known discovery).

New modules:
- save/ — ContentExtractor, SkillGenerator, AutoTagger for URL-to-Skill
- agents-md/ — AGENTS.md generator with managed section markers
- validation/ — SpecValidator with strict mode for agentskills.io compliance

New CLI commands:
- `skillkit save <url>` — save any URL/text/file as a reusable SKILL.md
- `skillkit agents init|sync|show` — generate and manage AGENTS.md

Updated:
- Well-known provider: Mintlify convention paths, discoverFromUrl()
- Install command: smart URL fallback (well-known → offer save)
- Remove command: auto-updates AGENTS.md on skill removal
- Validate command: --strict flag for spec compliance checks
- Quality module: name-directory match + token budget warnings
- Schema: agents enum updated from 7 → 44 agents

* fix: address Devin review — register AgentsMd commands, fix temp dir leak, wrap AGENTS.md update

- Register AgentsMdCommand/Init/Sync/Show in CLI entry point (were exported but never registered)
- Clean up tempDir in wellknown clone() when no skills found via index or mintlify
- Wrap AGENTS.md auto-update in install.ts with try-catch to prevent masking successful installs

* fix: address CodeRabbit review findings

- wellknown.ts: drop multiline flag from frontmatter regex, extract skill name
  from URL path segments instead of basename on full URL
- agents-md.ts: wrap init/sync in try-catch for user-friendly error messages
- publish.ts: add path-traversal guard to mintlify branch
- validate.ts: remove duplicate error/warning output in spec report
- extractor.ts: add 30s AbortSignal timeout to all fetch calls
- skill-generator.ts: fix .filter(Boolean) stripping blank line after frontmatter
2026-02-10 09:05:49 +00:00
Rohit Ghumare 407e8215f2 fix: stack ASCII and PH badge vertically on mobile, hide ASCII below sm 2026-02-09 23:16:18 +00:00
Rohit Ghumare dd4ec56a1a fix: show ASCII logo on mobile, use B&W Product Hunt badge 2026-02-09 21:58:30 +00:00
Rohit Ghumare e9bb9fbd0d fix: add separate mobile PH badge, fix visibility on small screens 2026-02-09 21:53:01 +00:00
Rohit Ghumare ee54bf1545 fix: show Product Hunt badge on mobile, remove duplicate from nav 2026-02-09 21:43:57 +00:00
Rohit Ghumare f097ec7ad7 style: add Product Hunt badge next to ASCII logo on website hero 2026-02-09 21:38:32 +00:00
Rohit Ghumare eeddd2a8cf style: add Product Hunt #3 badge to banner SVG 2026-02-09 21:32:51 +00:00
Rohit Ghumare 6362be2cb9 fix: update website from 32 to 44 agents across all components 2026-02-09 21:28:39 +00:00
Rohit Ghumare 7e23c3a5d7 fix: bump apps/skillkit version to 1.16.0 2026-02-09 21:21:55 +00:00
Rohit Ghumare 91c81ba1fa fix: bump all package versions to 1.16.0 2026-02-09 21:18:05 +00:00
Rohit Ghumare 684ea48f58 chore: release v1.16.0 2026-02-09 21:00:18 +00:00
Rohit Ghumare 19c9f6bdc4 feat: add 12 missing AI agents, expand to 44 total (#57)
* feat: add 12 missing AI coding agents (Devin, Aider, Cody, Amazon Q, Augment, Replit, Bolt, Lovable, Tabby, Tabnine, CodeGPT, PlayCode)

Expands agent support from 32 to 44 agents across all packages:
- Core types, configs, discovery paths, format maps, command generator
- Agent adapters (UniversalAdapter for all new agents)
- CLI onboarding icons/names, TUI symbols/logos
- Updated all docs, tests, and e2e references from 32 to 44

* test: add comprehensive tests for new agents, update docs and e2e

- Add it.each tests for all 12 new agent adapters and configs
- Add completeness test ensuring every AgentType has adapter + config
- Update agents.mdx doc table with all 12 new agents
- Update e2e onboarding test with new agent display names

* fix: add all 44 agents to translateSkillToAll and fix e2e test

- translateSkillToAll had hardcoded 17-agent list, now includes all 44
- e2e/skill-translator test was missing cline-zencoder batch in SUPPORTED_AGENTS

* fix: replace UniversalAdapter with GenericAgentAdapter for all non-universal agents

UniversalAdapter hardcoded type='universal', skillsDir='skills', and
name='Universal (Any Agent)' for all 26 agents that used it. This caused
skills to install to wrong directories and agents to be undetectable.

GenericAgentAdapter reads type, skillsDir, configFile from AGENT_CONFIG
and checks agent-specific directories in isDetected(). Fixes both the
12 new agents and the 14 pre-existing ones (cline through zencoder).

115 adapter tests now verify correct type, skillsDir, configFile, and
name for every GenericAgentAdapter instance.

* style: update README banner and header for 44 agents

* style: add rotating 3D model banner GIF for README

* style: revert to monochromatic SVG banner, update to 44 agents
2026-02-09 20:51:17 +00:00
Rohit Ghumare f11de2ac63 feat: add 12 missing AI coding agents (32 to 44) (#56)
* feat: add 12 missing AI coding agents (Devin, Aider, Cody, Amazon Q, Augment, Replit, Bolt, Lovable, Tabby, Tabnine, CodeGPT, PlayCode)

Expands agent support from 32 to 44 agents across all packages:
- Core types, configs, discovery paths, format maps, command generator
- Agent adapters (UniversalAdapter for all new agents)
- CLI onboarding icons/names, TUI symbols/logos
- Updated all docs, tests, and e2e references from 32 to 44

* test: add comprehensive tests for new agents, update docs and e2e

- Add it.each tests for all 12 new agent adapters and configs
- Add completeness test ensuring every AgentType has adapter + config
- Update agents.mdx doc table with all 12 new agents
- Update e2e onboarding test with new agent display names

* fix: add all 44 agents to translateSkillToAll and fix e2e test

- translateSkillToAll had hardcoded 17-agent list, now includes all 44
- e2e/skill-translator test was missing cline-zencoder batch in SUPPORTED_AGENTS

* fix: replace UniversalAdapter with GenericAgentAdapter for all non-universal agents

UniversalAdapter hardcoded type='universal', skillsDir='skills', and
name='Universal (Any Agent)' for all 26 agents that used it. This caused
skills to install to wrong directories and agents to be undetectable.

GenericAgentAdapter reads type, skillsDir, configFile from AGENT_CONFIG
and checks agent-specific directories in isDetected(). Fixes both the
12 new agents and the 14 pre-existing ones (cline through zencoder).

115 adapter tests now verify correct type, skillsDir, configFile, and
name for every GenericAgentAdapter instance.
2026-02-09 20:21:54 +00:00
Rohit Ghumare 3e92215231 fix: remove unnecessary VERSIONING.md from repo root (#55) 2026-02-09 19:44:08 +00:00
Rohit Ghumare 2f29632f17 fix: bump docs package versions to 1.15.0 2026-02-08 21:03:09 +00:00
Rohit Ghumare 596fc0aa7b chore: release v1.15.0 2026-02-08 20:57:48 +00:00
Rohit Ghumare 2bf8c7499c docs: add security scanner documentation, TUI screen, and README updates (#53)
- Add dedicated security.mdx docs page with full rule reference (46+ rules),
  threat categories, SARIF/CI integration guide, and programmatic usage
- Add TUI Scan screen (z key) with live scan results, severity colors,
  finding navigation, and rescan support
- Add scan to TUI sidebar nav, help shortcuts, and bottom status bar
- Add security scanner section to docs index page with link
- Add programmatic scan usage example to CLI README
- Remove stale --quiet option from commands.mdx
- Add security page to docs sidebar navigation
2026-02-08 20:50:45 +00:00
Rohit Ghumare d7861f96a7 feat: update Product Hunt badge to top post daily badge (#54)
Replace featured badge with top-post-badge showing daily ranking.
2026-02-08 20:50:29 +00:00
Rohit Ghumare c89d3130d1 fix: rewrite compatibility matrix with accurate agent capability data (#52)
Replace fabricated compatibility data with ratings based on actual
SkillKit translator capabilities, agent constraints, and compatibility
scoring from the codebase.

Key changes:
- Categories now reflect real SkillKit features (Translation, Hooks,
  MCP & Tools, Context Window) alongside skill categories
- Cline promoted to Tier 1 (full MCP/tools/hooks support)
- Only Claude, Cline, Roo show full MCP & Tools support (accurate)
- Codex/Copilot show partial for most categories (8K context limit)
- No agent claims 100% - scores reflect real translation capabilities
- Removed language-specific categories (Go, Python, TypeScript) that
  don't meaningfully differ across agents since skills are text-based
2026-02-08 20:35:08 +00:00
Rohit Ghumare d8168044b3 fix: remove hardcoded initial stars count from website loader (#51)
Replace stale hardcoded fallback values (66 stars, 2.4k downloads, v1.9.0)
with empty/zero defaults that show a dash placeholder while loading. Real
values populate once the API responds.
2026-02-08 20:30:10 +00:00
Rohit Ghumare b28a2801b2 feat: add security scanner for detecting malicious patterns in skills (#50)
* feat: add security scanner for detecting malicious patterns in skills

Add `skillkit scan <path>` command with 46+ detection rules across 6 threat
categories: prompt injection, command injection, data exfiltration, tool abuse,
hardcoded secrets, and unicode steganography.

- 3 analyzers: static pattern matching, SKILL.md manifest validation, secrets detection
- 4 output formats: summary (colored terminal), json, table, sarif (GitHub Code Scanning)
- Auto-scan on `skillkit install` (--no-scan to skip, --force to override)
- Auto-scan on `skillkit publish` (blocks on HIGH+ findings)
- Threat taxonomy with 10 categories and severity levels
- False-positive filtering for placeholders, test files, safe patterns
- Updated README, CLI docs, website commands, features, and fumadocs

* fix: address Devin and CodeRabbit review suggestions for security scanner

- Fix .env variant files (.env.local, .env.production) being skipped by scanner
- Add multiline rule support in StaticAnalyzer for cross-line pattern matching
- Fix PI004/PI013 patterns that contained literal \n (never matched per-line)
- Fix /g flag on CI006 path traversal regex causing intermittent misses
- Fix frontmatter regex to handle Windows CRLF line endings
- Fix allowed-tools parsing to detect multi-line YAML arrays
- Fix snippet redaction order: redact before truncate to prevent secret leaks
- Reset findingCounter per analyze() call for deterministic finding IDs
- Make SARIF artifactLocation.uri relative to skillPath for GitHub Code Scanning
- Use basename() instead of split('/').pop() for cross-platform paths
- Inject package version at build time via tsup define (replaces hardcoded 1.0.0)
- Validate --fail-on and --format CLI options with clear error messages
- Remove unused format/quiet from ScanOptions interface
- Move publish scan after name validation to avoid blocking on invalid skills
- Add excludePatterns for jailbreak detection to reduce false positives
- Add biome suppression for intentional control character regex in UC005
- Use alternation instead of character class for ZWJ in UC001

* fix: address CodeRabbit round 2 review suggestions

- Remove unused --quiet option from scan command
- Update OpenAI API key pattern to detect sk-proj- and sk-admin- prefixes

* fix: address deep review issues in security scanner

- SK001: add negative lookahead to prevent matching Anthropic keys
- static.ts: fix multiline loop hang for non-global regex with filtered matches
- CI005: reduce severity to MEDIUM, expand excludePatterns for template literals
- CI006: reduce severity to MEDIUM, add fileTypes whitelist, exclude markdown/YAML patterns
- PI011: fix literal \n in regex, use $/im for end-of-line matching
- UC004: use \u{...} notation for supplementary codepoint range
- scanner.ts: propagate skipRules to ManifestAnalyzer and SecretsAnalyzer
2026-02-08 12:56:45 +00:00
Rohit Ghumare 2c05d08027 fix: use PH embed badge image with live upvote count (#49) 2026-02-07 13:49:41 +00:00
Rohit Ghumare 51b62d1cce feat: show live Product Hunt upvotes, remove Apache license from stats bar (#48) 2026-02-07 13:42:30 +00:00
Rohit Ghumare a8df5a25d1 feat: add Product Hunt featured badge to website stats bar (#47) 2026-02-07 13:38:41 +00:00
Rohit Ghumare 616b268ad4 feat: add live GitHub stars CTA and redesign README banner (#46)
* feat: add live GitHub stars CTA and redesign README banner

- Add live star count to navbar with star icon and bordered button
- Add GitHub Star CTA button in hero with live count from GitHub API
- Update description to "open source package manager"
- Replace plain ASCII README header with SVG banner
- Fix video visibility with clickable thumbnail fallback
- Add GitHub stars badge to README badges row

* fix: reduce gap between install and star buttons

* fix: remove broken placeholder URL from README video section
2026-02-07 13:29:35 +00:00
Rohit Ghumare f7803183bf chore: release v1.14.0
Features:
- Smart Context Generation: AI-powered skill generation with multi-source context
  - Multi-provider LLM support (Claude, GPT-4, Gemini, Ollama, OpenRouter)
  - 4 context sources: docs, codebase, marketplace skills, memory
  - Agent-specific optimization for 32 agents
  - Trust scoring and compatibility matrix
  - Skill composition via natural language search

Documentation:
- Added Generate Command section to CLI reference
- Updated README with AI skill generation feature
- Updated website with AI Generate in Advanced Features
2026-02-05 15:43:33 +00:00
Rohit Ghumare 2441f0d275 feat(ai): add smart context generation with multi-provider support (#45)
* feat(ai): add smart context generation with multi-provider support

Implements the SkillKit Smart Context Generation system:

- Multi-Provider Support: 6 LLM providers (Anthropic, OpenAI, Google, Ollama, OpenRouter, Mock) with auto-detection via environment variables
- Multi-Source Context Engine: 4 context sources (docs, codebase, skills, memory) with relevance weighting
- Skill Composition Engine: Natural language search and intelligent skill merging
- Agent Optimization: Agent-specific optimization for 10+ agents with compatibility scoring
- Security Module: Trust scoring (0-10 scale) and prompt injection detection
- Wizard Core: 6-step interactive wizard (expertise → context-sources → composition → clarification → review → install)
- CLI Integration: `skillkit generate` command with @clack/prompts

New files:
- packages/core/src/ai/providers/{types,anthropic,openai,google,ollama,openrouter,factory}.ts
- packages/core/src/ai/context/{index,docs-source,codebase-source,skills-source,memory-source}.ts
- packages/core/src/ai/composition/{index,analyzer,merger}.ts
- packages/core/src/ai/agents/{optimizer,compatibility}.ts
- packages/core/src/ai/security/{trust-score,injection-detect}.ts
- packages/core/src/ai/wizard/{types,steps,clarification,index}.ts
- packages/cli/src/commands/generate.ts
- 6 test files for new modules

* fix(ai): address Devin/CodeRabbit review feedback

- Escape regex in codebase-source.ts to prevent ReDoS attacks
- Fix division by zero in skills-source.ts when no keywords present
- Include all config overrides in ProviderFactory cache key
- Validate AI-provided indices before indexing skills arrays
- Use limited array in ollama.ts search to avoid out-of-bounds access
- Add 120s timeout with AbortController to ollama/openrouter requests
- Fix provider precedence in wizard: config.provider > options.provider
- Fix emitComplete timing to fire after install step completes
- Guard memory lookups with memoryPersonalization opt-out check

* chore(deps): update Google AI SDK to new @google/genai package

The legacy @google/generative-ai package is deprecated as of Nov 2025.
Updated to the new unified @google/genai SDK (GA since May 2025).

* fix(ai): address remaining Devin/CodeRabbit review issues

- Update AIConfig type to support all providers (google, ollama, openrouter)
- Update getAIConfig() in CLI to detect all configured providers
- Add defensive check for expertise in clarification fallback questions
- Add null check for OpenAI choices[0] response
- Validate AI-provided indices in OpenAI/Anthropic search methods
- Add 120s timeout with AbortController to OpenAI/Anthropic requests
- Guard against zero/Infinity per-source chunk allocation in ContextEngine
- Normalize trust score weights and clamp final score to [0-10]
- Fix Windows path handling in memory-source.ts (use [\\/] regex)
- Fix token-to-character ratio consistency (use 4 throughout)
- Target 95% of max tokens in truncation to stay under limit

* chore: sync docs package versions to 1.13.0 and update lockfile

- Update docs/skillkit/package.json version to 1.13.0
- Update docs/fumadocs/package.json version to 1.13.0
- Regenerate pnpm-lock.yaml with new @google/genai dependency

* fix(ai): final code review fixes for smart context generation

- Add 'mock' to AIConfig provider union type
- Show mock provider in handleProviders() when no API keys configured
- Reserve space for truncation marker in truncateContent
- Capture pre-heading content in splitIntoSections
- Add tolerant JSON parsing in anthropic parseSearchResponse
- Use Number.isInteger for index validation in openai search
- Validate all required fields in openai generateFromExample
- Guard against zero sentences in trust-score scoreClarity
- Sanitize weight values (non-negative, finite) in TrustScorer

* fix(ai): re-validate after AI optimization and validate parseGenerateResponse

- Re-truncate content after AI optimization if it exceeds agent max context
- Add JSON extraction from code fences in parseGenerateResponse
- Validate required fields (name, description, content) in parseGenerateResponse
- Clamp confidence to [0,1] range and properly type-check optional fields
2026-02-05 15:40:14 +00:00
Rohit Ghumare a546b04953 chore: release v1.13.0 2026-02-05 11:27:29 +00:00
Rohit Ghumare 6d290171b7 feat(memory): add lifecycle hooks, progressive disclosure, and auto-compress memory (#44)
* feat(memory): add lifecycle hooks, progressive disclosure, and auto-CLAUDE.md updates

- Add Claude Code lifecycle hooks (SessionStart, PostToolUse, SessionEnd)
  for automatic memory capture and injection
- Implement 3-layer progressive disclosure for token-optimized retrieval
  (Index ~50 tokens, Timeline ~200 tokens, Details ~600 tokens)
- Add CLAUDE.md auto-updater to populate LEARNED section with learnings
- Add auto-compression threshold trigger in observation store
- Add new CLI commands: `memory sync-claude` and `memory index`
- Update documentation with new memory features
- Remove 139 lines of unnecessary inline comments (code cleanup)

* fix(memory): address Devin review comments

- Fix double execution bug in MemoryHookManager by adding
  generateHookOutputFromResult methods to avoid calling execute() twice
- Add setConfig method to PostToolUseHook for runtime config updates
- Update manager.setConfig() to propagate config to all hooks

* fix(memory): address CodeRabbit review comments

- Fix cross-platform path handling using path.basename() instead of split('/')
  in claude-md-updater.ts, session-start.ts, and session-end.ts
- Fix onSessionEnd to call execute() before generateHookOutput to run
  compression/cleanup side effects
- Add generateHookOutputFromResult() to SessionEndHook to avoid double execution
- Call clearOldPendingErrors() in PostToolUseHook.execute() to prevent
  unbounded pendingErrors map growth
- Handle async checkAutoCompression() errors in observation-store.ts
- Add validation for compression threshold (must be positive integer)
- Fix docs/commands.mdx to use correct CLI flags (--limit, --tags)
- Clarify token accounting in progressive-disclosure smartRetrieve() JSDoc
- Use config.minRelevanceForCapture in session-start.ts instead of hardcoded value

* fix(memory): address additional CodeRabbit review comments

- Use nullish coalescing (??) for maxResults defaults in progressive-disclosure
- Guard against non-positive tokenBudget in smartRetrieve()
- Thread minRelevance option through to findRelevantIds()
- Fix memory index CLI to validate --limit and pass maxResults to getIndex()
2026-02-05 11:26:31 +00:00
Rohit Ghumare a994726952 docs: rewrite README with clean, concise style
Reduced from 777 lines to 300 lines. Same information, clearer structure:
problem/solution opening, progressive examples, one command reference
section linking to full docs, compact agent table and attribution list.
2026-02-04 11:09:06 +00:00
Rohit Ghumare 1ee5258447 docs: rewrite with clean, concise style (#43)
* docs: rewrite documentation with clean, concise style

Rewrote all core docs pages (index, installation, quickstart, rest-api,
mcp-server, python-client) with problem/solution framing, progressive
code examples, and conversational tone. Updated OpenAPI descriptions
and api.html meta tags to match. 366 additions vs 722 deletions.

* docs(mcp): remove stale skill count, add list_categories tool name

Replace hard-coded "15,000+" with non-specific wording and explicitly
name the list_categories tool in the Browse categories section.
2026-02-04 11:01:48 +00:00
Rohit Ghumare db38c9059d feat(website): add hosted API docs at agenstskills.com/api
- Create public/api.html with Swagger UI dark theme matching site design
- Create public/openapi.json with full OpenAPI 3.1 spec and examples
- Add Vercel rewrite: /api -> /api.html
- Add "API" nav link to website navbar
- Custom dark theme with monospace fonts matching SkillKit branding
2026-02-04 00:50:03 +00:00
Rohit Ghumare 988a49f38f feat(api): add interactive Swagger UI docs at /docs
- Add OpenAPI 3.1 spec with all endpoints, schemas, and tags
- Serve Swagger UI at GET /docs with try-it-out enabled
- Serve OpenAPI JSON at GET /openapi.json
- Add API info endpoint at GET / with endpoint listing
- Update serve command to show /docs and /openapi.json endpoints
- Update REST API docs page with interactive docs section
2026-02-04 00:46:03 +00:00
Rohit Ghumare 19694dcaa1 docs: add v1.12.0 runtime skill discovery documentation
- README: add Runtime Discovery, serve command, REST API, MCP, Python
  client sections with examples and comparison table update
- Website Hero: update terminal animation with serve/API demo
- Website Features: add REST & MCP APIs card, API Access comparison row
- Website Commands: add Server tab with serve command options
- Fumadocs: create rest-api.mdx, mcp-server.mdx, python-client.mdx
- Fumadocs: update index (v1.12.0, architecture, discovery section),
  commands (serve command), and meta.json navigation
2026-02-04 00:40:49 +00:00
Rohit Ghumare b432400b5a chore: release v1.12.0 2026-02-04 00:29:39 +00:00
Rohit Ghumare e5f0d6d450 feat: runtime skill discovery — REST API, MCP server, cache, ranking, Python client (#42)
* feat: runtime skill discovery — REST API, MCP server, cache, ranking, Python client (#42)

Add runtime skill discovery capabilities enabling agents to autonomously
search and retrieve skills on demand, inspired by skyll.app's approach
of making skills queryable by intent rather than requiring pre-installation.

Core infrastructure:
- Pluggable cache backend with LRU + TTL (MemoryCache)
- Multi-signal relevance ranker (content 40pts, query 30pts, popularity 15pts, refs 15pts)
- Enhanced SKILL.md parser with frontmatter extraction and reference discovery
- Runtime skill injector fetching SKILL.md from GitHub with caching

REST API server (@skillkit/api):
- Hono-based HTTP server on port 3737
- GET/POST /search with ranked results and filters
- GET /skills/:source/:id, /trending, /categories, /health, /cache/stats
- Sliding-window rate limiting (60 req/min/IP)

MCP server (@skillkit/mcp):
- 4 tools: search_skills, get_skill, recommend_skills, list_categories
- 2 resources: skills://trending, skills://categories
- Compatible with Claude Desktop, Cursor, any MCP client

CLI serve command:
- `skillkit serve` starts the API server
- Options: --port, --host, --cors, --cache-ttl

Community registry:
- registry/SKILLS.md with 26 curated skills across 12 categories
- CommunityRegistry class integrated into FederatedSearch

Python client (skillkit-client):
- Async httpx + pydantic client for the REST API
- search, get_skill, trending, categories, cache_stats, health

All 856+ tests pass across 24 workspace tasks.

* fix: resolve TypeScript errors in API package

Add explicit return type to rate limiter middleware and remove stale
CategoryCount type annotation in categories route.

* fix: address CodeRabbit review findings and version-check CI

- Fix version-check: bump docs packages to 1.11.0
- Parse first IP from X-Forwarded-For header in rate limiter
- Add try/catch for malformed JSON in POST /search
- Use exact source match in skill routes (owner/repo/id pattern)
- Fix NaN fallback for invalid limit params in trending/search
- Filter empty strings from query words in relevance ranker
- Use Map lookups instead of O(n^2) find in MCP resources/tools
- URL-encode path params in Python client
- Fix -h flag conflict with Clipanion help in serve command
- Fix typo: remoti-dev -> remotion-dev in registry SKILLS.md

* fix: address Devin review — composite key lookups and Python URL path

- Use source+name composite key Map lookups in search GET/POST routes
- Use source+name composite key Map lookup in trending route
- Fix Python client get_skill to use /skills/:owner/:repo/:id URL pattern
- Update Python test to match new 3-segment skill URL
2026-02-04 00:27:25 +00:00
Rohit Ghumare e569046776 chore: release v1.11.0 2026-02-03 14:38:15 +00:00
Rohit Ghumare 5bd7ebf607 feat: viral growth features — quick setup, badges, matrix, SKILL.md, federated search (#41)
* feat: add viral growth features (quick setup, badges, matrix, SKILL.md, federated search)

Tier 2: skillkit quick zero-friction entry, shareable badge generator,
agent compatibility matrix on website.

Tier 3: reposition as npm for agent skills, SKILL.md validate/init/check
commands, federated GitHub skill search with --federated flag on find.

* fix: matrix filtering, path traversal, cross-platform paths, fetch timeout

- CompatibilityMatrix: query matching agents now shows all categories
  (and vice versa) instead of hiding both dimensions independently
- quick.ts: sanitize skill names and validate targetInstallPath stays
  inside installDir before rmSync/cpSync/symlinkSync
- skillmd.ts: use path.relative() instead of string replace for
  cross-platform path display
- registry: add AbortController timeout (10s default) and distinct
  RateLimitError on 403 instead of silent empty return
- find.ts: handle RateLimitError with user-facing message
- Add quick-security.test.ts regression tests for path traversal

* fix: harden isPathInside with path.resolve, propagate RateLimitError

- isPathInside now uses path.resolve() + path.sep comparison instead of
  naive string replacement, fixing detection of paths completely outside
  the parent directory (both packages/core and src/core copies)
- FederatedSearch.search re-throws RateLimitError from rejected
  Promise.allSettled results so callers (find.ts) can handle 403s
- Updated security test to use the corrected isPathInside logic

* fix: use GITHUB_TOKEN/GH_TOKEN for authenticated GitHub API requests

GitHubSkillRegistry now reads GITHUB_TOKEN or GH_TOKEN from env and
sends Bearer auth header, raising the rate limit from 10 to 30 req/min
for code search. Matches the guidance shown to users on 403 errors.
2026-02-03 13:48:35 +00:00
Rohit Ghumare 549a21ad84 chore: release v1.10.0 2026-02-02 23:33:12 +00:00
Rohit Ghumare 109f00cd95 feat(core): add QMD-inspired hybrid search pipeline (#40)
* feat(core): add QMD-inspired hybrid search pipeline

Implement a hybrid search system combining vector embeddings with keyword search:

- Vector embeddings using node-llama-cpp with GGUF models (nomic-embed-text)
- RRF (Reciprocal Rank Fusion) for combining multiple rankers
- Query expansion with LLM and synonym fallback
- Position-aware score blending (different weights for top3, top10, rest)
- SQLite storage with sqlite-vec extension (falls back to in-memory)
- Auto-download of local GGUF models (~2GB)

New search module:
- embeddings.ts: Vector embedding generation service
- vector-store.ts: SQLite-based vector storage
- rrf.ts: RRF fusion algorithm
- expansion.ts: Query expansion with caching
- hybrid.ts: Main hybrid search pipeline
- local-models.ts: GGUF model management

CLI integration:
- skillkit recommend --hybrid: Enable hybrid search
- skillkit recommend --expand: Enable query expansion
- skillkit recommend --rerank: Enable LLM re-ranking
- skillkit recommend --build-index: Build embedding index

Tests: 56 new tests for search module (all passing)

* fix(search): address CodeRabbit review findings

- Add missing beforeEach import in embeddings.test.ts
- Update optional dependencies to current versions
- Fix weights/variations length mismatch in expansion.ts
- Avoid mutating input arrays in rrf.ts mergeRankings
- Delete orphaned chunk vectors in vector-store.ts delete() and clear()
- Add comment for empty catch block in vector-store.ts
- Make hybridSearch helper use buildIndex for true hybrid search
- Handle graceful degradation when embeddings unavailable
- Add node-llama-cpp mock in hybrid.test.ts

* fix(search): address CodeRabbit review round 2

- Fix gemma GGUF URL to point to valid community repo (bartowski)
- Add SQL injection protection for table names in vector-store.ts
- Fix resource leak with try/finally in hybridSearch helper
- Add backpressure handling for large model downloads
- Clamp startLine to non-negative in chunk calculation
- Add runtime validation warning for --expand/--rerank without --hybrid
- Update node-llama-cpp API usage (createEmbeddingContext, createContext)
- Update pnpm-lock.yaml for new optional dependency versions

* fix(search): use @ts-ignore for optional node-llama-cpp imports

CI doesn't install optional dependencies, so @ts-ignore is needed
instead of @ts-expect-error to suppress module not found errors.
2026-02-02 23:28:08 +00:00
Rohit Ghumare e3d7e0e28f feat(marketplace): add beautiful-mermaid skill
Add beautiful-mermaid to the skills marketplace:
- Render Mermaid diagrams as beautiful SVGs or ASCII art
- 5 diagram types: flowchart, sequence, class, ER, state
- 15 built-in themes + Shiki/VS Code theme integration
- Zero DOM dependencies, works in Node.js/Bun/Deno/browsers

Source: rohitg00/beautiful-mermaid
2026-02-02 17:42:09 +00:00
Rohit Ghumare 6cbbdabf59 feat(website): add dynamic stats from npm and GitHub APIs (#39)
* feat(website): add dynamic stats from npm and GitHub APIs

- Create useStats hook to fetch real-time version, downloads, and stars
- Replace hardcoded values in App.tsx stats bar with dynamic data
- Replace hardcoded version in Hero.tsx badge with dynamic data
- Add 5-minute cache to reduce API calls
- Fallback to default values if APIs fail

* fix: address CodeRabbit and Devin review comments

- Fix duplicate API calls: remove useStats from Hero, pass version as prop from App
- Fix falsy checks: use typeof checks for downloads and stargazers_count
  to correctly handle zero values instead of showing defaults
2026-02-02 17:38:48 +00:00
Rohit Ghumare c1c179217d fix(website): update version to 1.9.0 2026-02-02 17:09:24 +00:00
Rohit Ghumare de4425f440 chore: release v1.9.0 (#38)
Features:
- Hierarchical skill tree with 12 categories (skillkit tree)
- LLM-based reasoning engine for skill discovery
- Explainable recommendations (--explain, --reasoning flags)
- Connector placeholders for tool-agnostic skills (~~CRM, ~~chat, etc.)
- Execution flow tracking with metrics
- Standalone vs Enhanced mode detection

CLI:
- New `tree` command for taxonomy navigation
- Enhanced `recommend` with explanation support
- Fixed --skill alias and agent detection

Documentation:
- Added tree.mdx for Skill Tree documentation
- Updated recommendations.mdx with reasoning features
- Updated TUI docs with tree view mode
- Updated README with new features
- Updated website Features and Commands
2026-02-02 16:48:43 +00:00
Rohit Ghumare 8121c2bbac feat(core): add PageIndex-inspired patterns for skill discovery (#37)
* feat(core): add PageIndex-inspired patterns for skill discovery

Implements patterns from anthropics/knowledge-work-plugins:

Tree Module (packages/core/src/tree/):
- Hierarchical skill taxonomy with 12 categories
- Tree generator from skill tags and metadata
- Tree serializer for JSON/Markdown export
- Related skills graph with 4 relation types

Reasoning Engine (packages/core/src/reasoning/):
- LLM-based tree traversal for skill discovery
- Explainable recommendations with reasoning chains
- Search planning with category relevance scoring
- Result caching with 5-minute TTL

Connectors (packages/core/src/connectors/):
- Tool-agnostic ~~ placeholder system
- 13 connector categories (crm, chat, email, etc.)
- Auto-suggest mappings from MCP config
- Placeholder detection and replacement utilities

Execution Flow (packages/core/src/execution/):
- Step-by-step execution tracking with metrics
- Automatic retry with exponential backoff
- Standalone vs Enhanced mode detection
- Capability-based feature gating

CLI Integration:
- New `skillkit tree` command with --generate, --stats flags
- Enhanced `skillkit recommend` with --explain, --reasoning flags

TUI Integration:
- Tree view mode in Marketplace (toggle with 'v')
- Arrow key navigation for tree hierarchy

* fix: address CodeRabbit and Devin review feedback

- Use os.homedir() instead of process.env.HOME || '~' fallback
  (tree.ts, tree.service.ts, mode.ts)
- Add guard for division by zero in tree stats percentage
- Validate parseInt result for --depth flag
- Fix average stats calculation to use cacheMisses count
- Extract category from data in validateCategoryScore
- Remove unused skillMap field from TreeGenerator
- Make reasoning provider configurable instead of hardcoded
- Add try/catch for tree loading errors in Marketplace
- Handle missing tree nodes during traversal

* fix(execution): clear timeout timer to prevent resource leak

Store setTimeout ID and clear it in finally block when step
completes successfully before timeout. This prevents orphaned
timers from accumulating during long-running applications.
2026-02-02 16:18:13 +00:00
Rohit Ghumare 3565daa7f1 fix(cli): add --skill alias and fix agent detection
- Add --skill as alias for --skills option (install command)
- Fix sync command to always detect agent instead of using default 'universal'
- Auto-install npm dependencies for skills with package.json
2026-02-02 12:07:41 +00:00
Rohit Ghumare 8496e3c63c feat(publish): add RFC 8615 well-known skills support (#36)
* feat(agents): add skill-to-subagent converter command

Add `skillkit agent from-skill` command to convert SkillKit skills into
Claude Code native subagent format (.md files in .claude/agents/).

Features:
- Reference mode (default): generates subagent with `skills: [skill-name]`
- Inline mode (--inline): embeds full skill content in system prompt
- Options: --model, --permission, --global, --output, --dry-run

New files:
- packages/core/src/agents/skill-converter.ts
- packages/core/src/agents/__tests__/skill-converter.test.ts (23 tests)

Closes #22

* feat(publish): add RFC 8615 well-known skills support

Redesign publish workflow to align with industry standard:

- Add WellKnownProvider for auto-discovery from any domain
- skillkit add https://example.com discovers skills via /.well-known/skills/
- skillkit publish generates well-known hosting structure
- skillkit publish submit opens GitHub issue (legacy workflow)

Provider discovers skills from:
- /.well-known/skills/index.json (manifest)
- /.well-known/skills/{skill-name}/SKILL.md (skill files)

Includes 16 tests for WellKnownProvider and structure generation.

* fix(wellknown): correct baseSkillsUrl calculation for skills.json fallback

When using the /.well-known/skills.json fallback URL, the previous
logic produced a malformed URL with duplicated .well-known path segment:
- Before: https://example.com/.well-known/.well-known/skills
- After: https://example.com/.well-known/skills

Extract calculateBaseSkillsUrl helper function for better testability
and add 4 new unit tests covering both URL formats.

* docs: update publish command documentation for well-known skills

- README.md: Add self-hosting section with well-known URI structure
- commands.mdx: Add Publishing Commands section
- marketplace.mdx: Expand publish section with self-hosting instructions
- skills.mdx: Add self-hosting workflow documentation

Documents the new `skillkit publish` workflow that generates RFC 8615
well-known URI structures for decentralized skill hosting.

* fix(security): address path traversal and CRLF vulnerabilities

- agent.ts: Sanitize skill.name when building default filename
- publish.ts: Add sanitizeSkillName() to validate skill names before
  using in file paths, verify resolved paths stay within target dir
- skill-converter.ts: Normalize CRLF to LF before extracting body
  content to handle Windows-style line endings
- wellknown.ts: Add sanitizeSkillName() to validate remote skill names,
  verify resolved paths stay within temp dir, encode URL components

* fix(agents): improve YAML string escaping logic

Only escape strings that actually need it for valid YAML parsing:
- Strings containing newlines or colons
- Strings starting with special YAML characters (-, *, &, !, {, [, >, |, @, `)
- Strings starting with quotes

This fixes unnecessary escaping of strings like "code-quality" where
hyphens in the middle don't need escaping.

* fix(wellknown): address security review feedback

- Use path.sep instead of hardcoded '/' for cross-platform compatibility
- Add sanitization and path containment check in generateWellKnownStructure
- Remove unused 'vi' import in wellknown.test.ts
2026-02-01 21:38:42 +00:00
Rohit Ghumare 847af0f7ab feat(agents): add skill-to-subagent converter command (#34)
* feat(agents): add skill-to-subagent converter command

Add `skillkit agent from-skill` command to convert SkillKit skills into
Claude Code native subagent format (.md files in .claude/agents/).

Features:
- Reference mode (default): generates subagent with `skills: [skill-name]`
- Inline mode (--inline): embeds full skill content in system prompt
- Options: --model, --permission, --global, --output, --dry-run

New files:
- packages/core/src/agents/skill-converter.ts
- packages/core/src/agents/__tests__/skill-converter.test.ts (23 tests)

Closes #22

* fix(agents): address code review feedback

- Update CLI option descriptions to list all valid values (model: inherit, permission: bypassPermissions)
- Add filename sanitization to prevent path traversal attacks via --output
- Fix parseAllowedTools to handle both string and YAML array formats
- Support space-separated tool lists in allowed-tools
- Add tests for array and space-separated formats
2026-02-01 20:00:11 +00:00
Rohit Ghumare 34e8cd0b61 docs(tui): update documentation for Solid.js migration (#33)
Update TUI documentation to reflect the v1.8.0 migration from React to
Solid.js:

- Change @opentui/react to @opentui/solid
- Change React 19.0.0 to Solid.js 1.9.0
- Add note about migration rationale (performance, bundle size)
- Update performance optimizations section with Solid.js primitives
  (createMemo, createSignal, createEffect)
- Add windowed list rendering mention
- Update Integration section with Solid.js code example
- Update graceful exit to reference onCleanup instead of React unmount
2026-02-01 17:55:45 +00:00
Rohit Ghumare cbd9fcd679 chore: fix version mismatch in root and docs packages 2026-02-01 17:34:40 +00:00
Rohit Ghumare f9e31fedc8 chore: bump version to 1.8.1 2026-02-01 17:33:24 +00:00
Rohit Ghumare 12ed10d170 refactor(tui): migrate to OpenTUI/Solid.js framework (#32)
* refactor(tui): migrate to OpenTUI/Solid.js framework

Complete TUI rewrite from Ink/React to OpenTUI/Solid.js:

- Replace React with Solid.js for reactive state management
- Migrate all 20 screens to OpenTUI component primitives
- Add monochromatic design with 14 color themes
- Implement cinematic splash screen with ASCII animation
- Add vi-key navigation (j/k/h/l) throughout
- Create 32 reusable components with consistent styling
- Add service layer for @skillkit/core API integration
- Remove deprecated react-opentui.d.ts type definitions
- Update build config for Solid.js JSX transform

Features covered:
- Browse, Marketplace, Recommend (discovery)
- Installed, Sync, Translate (management)
- Workflow, Execute, Plan, History (execution)
- Team, Context, Memory, Mesh, Message (collaboration)
- Plugins, Methodology, Settings (configuration)
- Help screen with 25+ keyboard shortcuts

* fix(tui): address CodeRabbit review feedback

Critical fixes:
- Remove non-existent module exports from index.tsx (context, themes, ui, hooks, services)
- Simplify App.tsx to remove missing context provider imports

Major fixes:
- ProgressBar: Add defensive guards for width/progress (NaN, Infinity, negative)
- Browse: Fix filtered index loading wrong repository
- Context: Add section navigation (h/l keys) and async error handling
- Methodology: Add error handling with try/catch/finally for all async ops
- Plan: Fix division by zero when plan has no tasks, add error handling
- Team: Add error handling for loadTeamConfig and handleInitialize
- Translate: Guard against missing skill.path before read operations

* fix(tui): address remaining CodeRabbit feedback

- Memory: Add error handling for loadData, handleDelete, handleClearAll, handleInitialize
- Team: Fix key conflict by blocking global keys when detail pane is open
- animations: Fix springCurve to return 0 at progress=0 and 1 at progress=1

* fix(tui): add Solid.js OpenTUI type definitions

Required for TypeScript to recognize OpenTUI JSX elements (box, text, span)
with their custom props (fg, bg, flexDirection, etc.)

* fix(tui): add stub services and fix type errors for CI

- Add minimal stub service implementations for all TUI screens:
  - context.service.ts - project context loading
  - executor.service.ts - skill execution
  - memory.service.ts - memory management
  - methodology.service.ts - methodology packs
  - plan.service.ts - plan management
  - plugin.service.ts - plugin management
  - recommend.service.ts - skill recommendations
  - team.service.ts - team collaboration
  - translator.service.ts - skill translation
  - workflow.service.ts - workflow orchestration

- Fix type errors in screens:
  - Plan.tsx: Add non-null assertions for optional issues array
  - Plugins.tsx: Cast getPluginInfo result to Plugin type

These stubs provide the expected interfaces for screens while
the full integration with @skillkit/core is completed later.

* fix(tui): add missing component files for CI

Add the component files that screens depend on:
- StatusIndicator - loading/success/error status display
- DetailPane - side panel for detailed view
- EmptyState/ErrorState - empty and error state components
- SelectList - selection list component
- SplitPane - split view layout
- AnimatedText - text animations
- Breadcrumb - navigation breadcrumb
- Button/Clickable - interactive elements
- CodeBlock - code display
- FormField - form input wrapper
- HoverHighlight - hover effect wrapper
- RightSidebar/BottomStatusBar - layout components
- TabBar - tab navigation
- ErrorBoundary - error handling wrapper

These components are required by the screen files and were
missing from the previous commit.

* fix(tui): resolve context import and duplicate export issues

- RightSidebar: inline sidebar state instead of importing from context
- services/index.ts: fix duplicate AgentType export by using explicit
  exports for executor and translator services

* fix(tui): use export type for type-only re-exports

* refactor(tui): simplify components and remove redundant exports

* refactor(tui): remove unused imports and variables

Code simplification pass:
- Remove unused onCleanup import from Workflow, Recommend, Sync screens
- Remove unused contentWidth from Browse, Recommend, Marketplace, Sync
- Remove unused cols from Browse, Recommend
- Remove unused JSX import from EmptyState component
- Remove unused translate import from Sync screen
- Remove unused SelectList import and listItems function from Memory screen

* fix(tui): wire up interactive handlers and fix type definitions

- AnimatedText: fix reactive dependency tracking in createEffect
- BottomStatusBar: remove unused width prop
- Breadcrumb: wire onNavigate handlers, fix off-by-one in getPathAtIndex
- Button: wire onClick with disabled check, apply paddingX, fix ButtonGroup spacing
- Clickable: wire click/double-click/right-click handlers, fix InteractiveArea
- DetailPane: make close button interactive
- ErrorBoundary: use terminal keyboard handler, prevent duplicate onError calls
- FormField: fix placeholder show condition for empty string
- SelectList: add onSelect/onHover interactive behavior
- SplitPane: preserve string sizes like "50%" in width/height helpers
- TabBar: wire onSelect callbacks for both horizontal and vertical variants
- solid-opentui.d.ts: add missing event handler types to BoxProps/TextProps

* fix(tui): address Devin review issues

- App: restore process.exit(0) fallback when onExit is undefined
- Execute: pass skill path instead of content to executeSkillWithAgent
- Memory: add useKeyboard handler for j/k/Enter/d/c/i/Esc shortcuts

* fix(tui): address Devin and CodeRabbit review issues

Security & Robustness:
- App: use execFile instead of exec to prevent command injection in openUrl
- App: clamp cols/rows to minimum 1 to prevent negative dimensions
- index: await render() and handle failures with exitTUI(1)

Execute screen:
- Add error state for load failures
- Prevent re-entrant execution with executing() guard
- Use try/finally to always clear executing state

Memory screen:
- Add missing 'r' shortcut for retry/refresh

Workflow screen:
- Use try/finally to always clear executing state even on rejection

Sync screen:
- Capture selectedIndex and agent values before await to prevent drift

* fix(tui): implement list windowing to keep selection visible

Execute, Marketplace, Recommend screens now use windowed list rendering
that follows the selection, preventing the selected item from being
off-screen when navigating through long lists.

- Add createMemo for computing visible window based on selectedIndex
- Show ▲/▼ indicators when items are above/below the visible window
- Navigate through full list instead of clamping to visible window size

* fix(tui): add error handling and index clamping

Marketplace.tsx:
- Set error signal when all repos fail or no skills loaded
- Add reactive effect to clamp selectedIndex when filteredSkills changes

Recommend.tsx:
- Wrap loadData in try/catch to surface errors in UI
- Clamp selectedIndex after recommendations update

* fix(tui): add error handling to Plugins and Workflow screens

Plugins.tsx:
- Wrap loadData in try/catch to prevent stuck loading state
- Wrap handleToggle in try/catch/finally to always reset toggling flag
- Wrap handleShowDetail in try/catch to surface errors gracefully

Workflow.tsx:
- Wrap loadData in try/catch to prevent stuck loading state
- Add catch block to handleExecute to show execution errors in UI
2026-02-01 17:29:25 +00:00
Rohit Ghumare eebaa710f7 feat(website): add demo video and fix Twitter preview (#31)
* feat(website): add demo video to Hero section

- Add skillkit.mp4 video player below hero content
- Auto-plays muted with loop for seamless demo experience
- Styled with terminal-like window frame

* fix(website): fix Twitter/OG preview card

- Update og:url from skillkit.dev to agenstskills.com
- Use absolute URLs for og:image and twitter:image
- Add og:image dimensions (1200x630)
- Add og:site_name and twitter:url
- Update description to "32 agents"
2026-01-30 22:48:25 +00:00
Rohit Ghumare eae5accf36 feat(docs): comprehensive documentation and website improvements (#30)
* feat(docs): comprehensive documentation and website improvements

Website improvements:
- Add AdvancedFeatures component for Memory, Primer, Mesh, Messaging
- Add UseCases component with real-world scenarios
- Add TeamEnterprise component for collaboration features
- Update Hero section with better value proposition
- Make all components mobile responsive
- Pre-populate StackBuilder with default skills
- Add ARIA attributes for accessibility
- Add prefers-reduced-motion for smooth scrolling

Documentation updates:
- Create primer.mdx for auto-generate instructions feature
- Create teams.mdx for team collaboration documentation
- Enhance index.mdx with comprehensive feature overview
- Update quickstart.mdx with advanced features section
- Expand api-reference.mdx with Mesh, Messaging, Workflow APIs
- Update configuration.mdx with Memory, Mesh, Primer settings
- Simplify fumadocs homepage for cleaner presentation
- Fix markdown formatting issues

* fix: address CodeRabbit review suggestions

- Add missing fs import to api-reference.mdx code examples
- Clarify that host comes from MeshHost in messaging example
- Remove broken /docs/registries link from teams.mdx
- Fix ARIA tab/panel linkage in AdvancedFeatures.tsx
2026-01-30 22:21:04 +00:00
Rohit Ghumare e41b0cd8a3 Revert "feat(docs): comprehensive documentation and website improvements (#28)" (#29)
This reverts commit 21df323134.
2026-01-30 21:42:18 +00:00
Rohit Ghumare 21df323134 feat(docs): comprehensive documentation and website improvements (#28)
* feat(docs): comprehensive documentation and website improvements

Website improvements:
- Add AdvancedFeatures component for Memory, Primer, Mesh, Messaging
- Add UseCases component with real-world scenarios
- Add TeamEnterprise component for collaboration features
- Update Hero section with better value proposition
- Update Features section with improved presentation
- Make all components mobile responsive
- Pre-populate StackBuilder with default skills
- Hide Apache 2.0 on mobile, show Docs link on mobile

Documentation updates:
- Create primer.mdx for auto-generate instructions feature
- Create teams.mdx for team collaboration documentation
- Enhance index.mdx with comprehensive feature overview
- Update quickstart.mdx with advanced features section
- Expand api-reference.mdx with Mesh, Messaging, Workflow APIs
- Update configuration.mdx with Memory, Mesh, Primer settings
- Simplify fumadocs homepage for cleaner presentation

* fix: address code review feedback

- Fix markdown heading/list separation in index.mdx
- Fix mesh.security schema in configuration.mdx profiles
- Add shebang to git hook script in primer.mdx
- Update Primer description for multi-agent support in Features.tsx
- Add prefers-reduced-motion media query for accessibility in styles.css
- Add ARIA attributes (role, aria-selected, aria-controls) to AdvancedFeatures tabs
2026-01-30 21:41:33 +00:00
Rohit Ghumare 363d28e266 fix(find-skills): correct CLI syntax and add examples 2026-01-30 19:57:44 +00:00
Rohit Ghumare a229c384b0 feat(website): redesign and simplify UI components
- Simplify StackBuilder: add 8 stacks, cleaner install command UI
- Simplify Attribution: remove fake metrics, show repo links only
- Simplify SkillGenerator: clean search UI, remove AI generation
- Simplify SkillSubmitForm: single input with CLI command
- Expand Commands: 7 categories, 42 commands (mesh, message, memory)
- Fix Features grid: lg:grid-cols-5 for better layout
- Update version badges to v1.8.0
- Add bump-version.sh support for website hardcoded versions
- Add kubernetes-mcp and find-skills to marketplace
- Add find-skills skill for universal skill discovery
2026-01-30 19:30:55 +00:00
Rohit Ghumare 3e9a3cd84c feat: add unified versioning system with CI validation
- Add scripts/bump-version.sh for syncing all package versions
- Add version-check job to CI workflow
- Add tag/version validation to publish workflow
- Sync all packages to v1.8.0
- Add VERSIONING.md documentation
2026-01-30 18:56:56 +00:00
Rohit Ghumare d0b5151683 docs: update for v1.8.0 with npx usage, mesh, and messaging 2026-01-30 18:04:33 +00:00
Rohit Ghumare e22193f823 chore: bump version to 1.8.0 2026-01-30 18:03:16 +00:00
Rohit Ghumare fdae2aee86 docs(website): add Messaging feature and message commands 2026-01-30 17:58:08 +00:00
Rohit Ghumare 3067cbdb5b docs: add README files for memory, mesh, and messaging packages 2026-01-30 17:58:08 +00:00
Rohit Ghumare ae78e2e373 feat(tui): add Mesh and Message screens for v2.0 features
- Add Mesh screen for mesh network management
- Add Message screen for inter-agent messaging
- Update App.tsx with navigation to new screens
- Add 'g' and 'j' keyboard shortcuts for mesh/message
- Update README with mesh and message CLI commands
2026-01-30 17:58:08 +00:00
Rohit Ghumare 4257e8555b feat: Memory, Mesh Network with Security, Messaging, MCP Server (#27)
* feat: add persistent memory, mesh network, and agent messaging (v2.0.0)

Add three major features to SkillKit:

@skillkit/memory - CozoDB-backed semantic memory with embeddings
- 384-dim embeddings via @xenova/transformers (all-MiniLM-L6-v2)
- Memory tiers (warm/long) with promotion logic based on access patterns
- HNSW semantic search for context retrieval
- Storage: ~/.skillkit/agents/{agentId}/memory.db

@skillkit/mesh - Peer mesh network for multi-machine agent distribution
- Local LAN discovery via UDP multicast (239.255.255.250)
- Tailscale VPN support for secure remote connections
- Bidirectional peer registration with health checks
- HTTP and WebSocket transports
- Storage: ~/.skillkit/hosts.json

@skillkit/messaging - Inter-agent messaging system
- Inbox/sent/archived storage with JSON persistence
- Message router for local and cross-host delivery
- Priority levels (low/normal/high/urgent)
- Message types (request/response/notification/update)
- Storage: ~/.skillkit/messages/{inbox|sent|archived}/{agentId}/

CLI Commands:
- skillkit mesh: init, add, remove, list, health, discover, status
- skillkit message: send, inbox, read, reply, archive, forward, sent, status

All packages bumped to version 2.0.0

* feat: add advanced learning, automation, and workflow features

Implements comprehensive enhancement plan with 9 phases:

Phase 1: @skillkit/resources Package
- Bundled agents (9): architect, build-error-resolver, code-reviewer,
  doc-updater, e2e-runner, planner, refactor-cleaner, security-reviewer, tdd-guide
- Command templates (10): /tdd, /plan, /e2e, /learn, /build-fix, etc.
- Operational profiles (4): dev, review, research, security
- Guidelines (5): security, code-style, testing, git, performance
- Hook templates (12): typescript-check, eslint-check, security-scan, etc.

Phase 2-3: Pattern Learning & Confidence Scoring
- skillkit learn: Extract patterns from git history
- skillkit pattern status|feedback|approve|reject|export|import|cluster
- Confidence evolution: success +0.05, failure -0.10

Phase 4: Session State Persistence
- skillkit session status|start|load|list|note|complete|in-progress
- Cross-session context preservation in ~/.skillkit/sessions/

Phase 5: Workflow Pipelines
- skillkit workflow pipeline list|<name>
- Built-in: feature, bugfix, refactor, security-audit, documentation

Phase 6: Operational Profiles
- skillkit profile list|<name>|create|remove
- Mode switching for different work contexts

Phase 7: Guidelines System
- skillkit guideline list|show|enable|disable|create|remove
- Always-on coding standards

Phase 8: Hook Templates
- skillkit hook template list|apply|show
- Pre-built automation patterns

Phase 9: Slash Command Templates
- skillkit command available|install <id>
- Install bundled command templates

* feat: add MCP memory server for Claude/Cursor integration

Adds @skillkit/mcp-memory package - an MCP (Model Context Protocol) server
that exposes SkillKit's persistent memory system to Claude, Cursor, and
other MCP-compatible AI tools.

Tools:
- memory_store: Store memories with semantic embeddings
- memory_search: Semantic search through memories
- memory_recall: Recall by category/tier/tags
- memory_get: Get memory by ID
- memory_forget: Delete a memory
- memory_link: Create relationships between memories
- memory_reinforce: Strengthen/weaken memories
- memory_stats: Get memory statistics

Resources:
- memory://stats: Current statistics (JSON)
- memory://recent: Recent memories (JSON)

Usage with Claude Desktop:
```json
{
  "mcpServers": {
    "skillkit-memory": {
      "command": "npx",
      "args": ["@skillkit/mcp-memory"],
      "env": { "SKILLKIT_AGENT_ID": "claude-desktop" }
    }
  }
}
```

* feat(mesh): add comprehensive security hardening

- Add cryptographic identity layer (Ed25519 keypairs, fingerprints)
- Add message encryption (XChaCha20-Poly1305) and signing
- Add secure keystore with AES-256-GCM at-rest encryption
- Add JWT authentication and challenge-response handshake
- Add secure WebSocket (WSS) and HTTPS transports
- Add signed discovery messages with trust modes (open/signed/trusted-only)
- Add TLS certificate management (self-signed)
- Add CLI commands: mesh security init/status, mesh peer trust/revoke/list
- Add security presets: development, signed, secure, strict
- Align all package versions to 1.7.11

Security stack: @noble/ed25519, @noble/curves, @noble/ciphers, @noble/hashes, jose

* docs(website): add mesh network and security features

- Add Mesh Network feature card with P2P description
- Add Security feature card with Ed25519/TLS details
- Add Mesh command group with security commands

* fix: address CodeRabbit review suggestions

- cli/mesh: validate port input (1-65535 range check)
- memory/cozo-adapter: call db.close() before nullifying reference
- memory/schema: fix primary key definitions (id => columns)
- resources/hooks: guard pre-commit hooks against empty file lists
- mcp-memory: prevent double-initialization with memoized promise
- mcp-memory: don't mask reinforce failures as "not found"
- mcp-memory: guard main() to prevent auto-start on import
- mcp-memory: add js language identifiers to README code blocks
- mesh/test: update MESH_VERSION test expectation to 1.7.11

* fix: address additional CodeRabbit and Devin review suggestions

Memory package:
- encoder: reset initPromise on failure to allow retry
- encoder: call pipeline.dispose() in disposeEncoder to free GPU resources
- schema: fix probe query to use named-column matching for correct arity

Mesh package:
- hosts-config: add file locking to prevent race conditions
- local discovery: reduce multicast TTL to 1 for LAN-only traffic
- local discovery: handle announce errors in setInterval
- local discovery: close socket on membership setup failure
- local discovery: validate inbound packets (type, hostId, port range)
- local discovery: use rinfo.address to prevent spoofing
- health: guard against overlapping health checks with checking flag
- websocket: prevent auto-reconnect on explicit disconnect()

* fix(memory): increase semantic search fetch multiplier for better filter coverage

Increase from 2x to 5x results to reduce likelihood of incomplete
results when agentId/category/tier filters exclude many candidates.
Filters are applied in application code after HNSW vector search.

* feat(cli): add 'add' as alias for 'install' command

* fix(mesh/auth): use asymmetric EdDSA signing for JWT tokens

Tokens are now signed with the sender's Ed25519 private key and
verified using the sender's public key embedded in the token.
This fixes the issue where tokens couldn't be verified across
different AuthManager instances/hosts because each had a random
symmetric secret.

Changes:
- Switch from HS256 (symmetric) to EdDSA (asymmetric) algorithm
- Include sender's publicKey in JWT payload
- Add privateKey/privateKeyHex getters to PeerIdentity
- Verify fingerprint matches publicKey before accepting token
2026-01-30 17:48:10 +00:00
Rohit Ghumare 54cef27bfe chore: bump version to 1.7.11 2026-01-30 12:49:02 +00:00
Rohit Ghumare 1220880462 feat(website): add stack builder, trending, attribution sections (#26)
* feat(website): add stack builder, trending, attribution sections

- Add StackBuilder component for composing skill stacks visually
- Add TrendingSkills component with category browsing
- Add Attribution section crediting 24 skill sources
- Add issue template for submitting new skill repositories
- Update README with full attribution table
- Improve mobile responsiveness across all new components
- Simplify terminal demo (remove primer, focus on core workflow)
- Reorganize Commands section (Start, Manage, Team, Advanced)
- Update install commands to use npx skillkit@latest format
- Add navigation links and badge row to navbar

* fix: correct all domain references to agenstskills.com

Replace all incorrect agentskills.io references with the correct domain
agenstskills.com throughout the codebase.

Files updated:
- src/commands/validate.ts
- schemas/skill.schema.json
- docs/skillkit/components/Footer.tsx
- .github/ISSUE_TEMPLATE/add-source.md
- .github/ISSUE_TEMPLATE/skill-submission.yml
- CONTRIBUTING.md
- README.md

* fix: address CodeRabbit review suggestions

- TrendingSkills: use exact ID matching instead of substring match
- StackBuilder: prevent duplicate skills in preset stack
- StackBuilder: deduplicate repo references in install command
- StackBuilder: make copyCommand async with proper error handling
- StackBuilder: add accessibility labels and focus visibility to remove button
- App: update URL hash on scroll for deep linking
- App: add scrollMarginTop to sections for fixed navbar offset
2026-01-30 12:47:44 +00:00
Rohit Ghumare 1c946dde06 docs(website): update for v1.7.10 with primer command
- Update version from v1.7.5 to v1.7.10 in Hero
- Add primer command to terminal demo animation
- Add primer to core capabilities in Documentation
- Add AI Instruction Generation (Primer) section to CLI Commands
- Add Primer feature card to Features section
- Add Instructions comparison row highlighting Primer
2026-01-30 10:39:12 +00:00
Rohit Ghumare 3dfd317867 chore: bump version to 1.7.10 2026-01-30 10:11:27 +00:00
Rohit Ghumare c5aa303043 fix(agents): getAllAdapters returns correct agent types
Fixed getAllAdapters() to return the correct agent type from the
record keys instead of relying on adapter.type property, which
was returning 'universal' for all UniversalAdapter instances.

This fixes the E2E test that checks for all 32 agents in init --list
output (cline, codebuddy, commandcode, etc. were showing as 'universal').
2026-01-29 19:21:46 +00:00
Rohit Ghumare 01d816c72a feat: add skillkit primer command for AI instruction generation (#25)
* feat: add skillkit primer command for AI instruction generation

New feature that analyzes codebases and generates AI instruction files
for all 32 supported agents (inspired by pierceboggan/primer).

## New Module: packages/core/src/primer/
- types.ts: Zod schemas and TypeScript interfaces
- analyzer.ts: Codebase analysis (languages, frameworks, conventions)
- generator.ts: Agent-specific instruction file generation
- index.ts: Barrel exports
- __tests__/primer.test.ts: 15 comprehensive tests

## CLI Command: skillkit primer
- --agent/-a: Generate for specific agents
- --all-agents/-A: Generate for all 32 agents
- --output/-o: Custom output directory
- --dry-run/-n: Preview without writing
- --analyze-only: Show analysis only
- --verbose/-v: Detailed output
- --json/-j: JSON output

## Features
- Detects: languages, frameworks, package managers, libraries
- Analyzes: project structure, code conventions, CI/CD, Docker
- Generates: CLAUDE.md, .cursorrules, copilot-instructions.md, etc.

* fix: address CodeRabbit PR review issues for primer

- Fix OS-agnostic path handling in analyzer using path.relative() and path.sep
- Prevent output collisions when multiple agents produce same filename
- Add defensive check in test before accessing generated[0]
- Remove duplicate projectPath parameter in CLI primer command
- Use PackageManager enum instead of z.string() for type safety
- Detect monorepos before src-based layout to prevent misclassification
- Document --output and --json flags in README examples

* fix: additional CodeRabbit review fixes for primer

- Fix Python detection to use correct source file (pyproject.toml, requirements.txt, or setup.py)
- Escape regex special characters in glob pattern matching (e.g., *.module.css)
- Derive ALL_AGENTS from AGENT_CONFIG to avoid divergence
- Map agent config format to template format based on file extension

* feat(primer): support multi-format output rendering

Refactored generateContent to properly respect the format field
instead of always producing Markdown output.

- Added FormatRenderer interface with format-specific implementations
- Created renderers for markdown, mdc, json, xml formats
- JSON format generates structured data via generateJsonContent()
- MDC format includes YAML frontmatter via wrap() method
- XML format properly escapes content with escapeXml()
- Updated all section generators to accept and use the renderer
2026-01-29 19:09:03 +00:00
Rohit Ghumare f357c73e97 fix: update agent count from 17 to 32 across codebase (#24)
* fix: update agent count from 17 to 32 across codebase

- Update all documentation files (README.md, package READMEs)
- Update hardcoded AGENT_COUNT constant in onboarding
- Update JSDoc comments in core modules
- Update test files and e2e tests
- SkillKit now supports 32 AI coding agents:
  Primary: claude-code, codex, cursor, antigravity, opencode,
  gemini-cli, amp, clawdbot, droid, github-copilot, goose,
  kilo, kiro-cli, roo, trae, windsurf, universal
  Extended: cline, codebuddy, commandcode, continue, crush,
  factory, mcpjam, mux, neovate, openhands, pi, qoder, qwen,
  vercel, zencoder

* fix: add all 32 agents to documentation and tests

- apps/skillkit/README.md: Split agents into Primary (17) and Extended (15)
- e2e/onboarding-ui.e2e.test.ts: Add 15 extended agents to test array
- e2e/translation.e2e.test.ts: Add 15 extended agents to SUPPORTED_AGENTS
- README.md: Add extended agents to inline list and table
2026-01-29 13:21:58 +00:00
Rohit Ghumare 40e685fabe docs: update README and TUI with new commands and docs link
- Add docs badge and link to README
- Add all new commands: check, find, manifest, fix, audit, publish, status, pause/resume, settings, methodology, plan, plugin, team, hook, command
- Reorganize commands into logical sections
- Update TUI Help screen with new shortcuts
- Add 'd' key to open docs in browser from TUI
2026-01-29 11:58:33 +00:00
Rohit Ghumare 6099c0ad6c chore: bump version to 1.7.9 2026-01-29 11:47:42 +00:00
Rohit Ghumare 6445d72c80 fix: address CodeRabbit PR review issues
- Add noopener to rel="noreferrer" for tabnabbing protection
- Fix standalone skill path handling in readSkillContent and validateSkill
- Derive TOTAL_AGENTS from adapters instead of hardcoded value
- Fix duplicate discovery path for droid/factory agents
- Create dedicated FactoryAdapter instead of using UniversalAdapter
2026-01-29 11:26:40 +00:00
Rohit Ghumare 6d704a47b9 chore: bump version to 1.7.8 2026-01-29 11:25:34 +00:00
Rohit Ghumare dd1c675e15 chore: bump version to 1.7.7 2026-01-28 22:08:58 +00:00
Rohit Ghumare def3b01524 fix: mobile responsiveness for navbar docs link and skill generator
- Show Docs link on mobile (removed hidden sm:block)
- Add proper overflow handling for all code blocks on mobile
- Use smaller padding/text sizes on mobile screens
- Add break-words and whitespace-pre-wrap to prevent overflow
2026-01-28 22:07:09 +00:00
Rohit Ghumare b1d1ea3d24 correct website 2026-01-28 19:44:48 +00:00
Rohit Ghumare 7644de462a fix: add assetPrefix for absolute static asset URLs 2026-01-28 19:43:09 +00:00
Rohit Ghumare a0b34e076e fix: add rewrite for Next.js static assets from docs site 2026-01-28 19:42:34 +00:00
Rohit Ghumare 0a16de05c9 fix: correct domain from agentskills.com to agenstskills.com 2026-01-28 19:40:40 +00:00
Rohit Ghumare 750a6f206a fix: skip trailing slash redirect for proxy compatibility 2026-01-28 19:37:06 +00:00
Rohit Ghumare f73e043e87 fix: restore block-style ASCII logo with proper font 2026-01-28 19:03:03 +00:00
Rohit Ghumare 5dac9f0543 fix: remove root vercel.json to let Vercel use docs/skillkit config 2026-01-28 18:57:48 +00:00
Rohit Ghumare e38d132506 fix: update root vercel.json to deploy docs/skillkit 2026-01-28 18:57:06 +00:00
Rohit Ghumare ff52654549 fix: install Tailwind as build dependency instead of CDN for reliable styling 2026-01-28 18:53:00 +00:00
Rohit Ghumare dced3cecf3 fix: add inline styles for dark backgrounds to ensure proper rendering 2026-01-28 18:48:18 +00:00
Rohit Ghumare 7cedc53d68 fix: use standard ASCII characters for logo instead of Unicode blocks 2026-01-28 18:43:41 +00:00
Rohit Ghumare d4ad9096b7 feat: add favicon and metadata to fumadocs 2026-01-28 18:40:51 +00:00
Rohit Ghumare da434ccec1 chore: add root vercel.json for Vercel deployment 2026-01-28 18:37:41 +00:00
Rohit Ghumare 14c319e90e chore: add .vercel to gitignore 2026-01-28 18:37:07 +00:00
Rohit Ghumare 2d2e8aaace fix: use npm instead of pnpm in vercel.json to avoid workspace detection 2026-01-28 18:31:48 +00:00
Rohit Ghumare d1fcf0355f docs: add comprehensive documentation section to website (#23)
* docs: add comprehensive documentation section to website

- Create Documentation.tsx component with DeepWiki-sourced content
- Add sections: Overview, Installation, Architecture, Agents, Commands
- Add sections: Configuration, API Reference, Skill Format, Tech Stack
- Include interactive sidebar navigation
- Add Docs link to navbar
- Reference DeepWiki as documentation source

Source: https://deepwiki.com/rohitg00/skillkit

* feat(docs): add Fumadocs documentation site and update website

- Add Fumadocs-based documentation site at /docs
  - Complete MDX documentation for all features
  - TUI section with keyboard navigation
  - Installation, quickstart, commands reference
  - API reference and configuration guides

- Update SkillKit website (agentskills.com)
  - Add 15 new agents (32 total): CodeBuddy, Continue, Crush,
    Factory, MCPJam, Mux, Neovate, OpenHands, Pi, Qoder, Qwen,
    Vercel, Zencoder, CommandCode
  - Update agent count from 17 to 32 across all components
  - Update command count from 30+ to 40+
  - Remove inline Documentation section (now in Fumadocs)
  - Link Docs to /docs route

- Add 15 new agent adapters to @skillkit/agents
  - All use UniversalAdapter as base
  - Added to detection order and adapter registry

- Configure Vercel rewrites for /docs proxy to Fumadocs

* fix: resolve TypeScript build errors in fumadocs

- Remove createRelativeLink from docs page (not compatible with current fumadocs)
- Remove redundant isLoading prop in SkillGenerator (status already narrowed)
- Fix lucide-react icon type casting in Card component
- Fix MDXComponents return type in mdx-components

* fix: resolve /docs 404 and show docs link on mobile

- Handle undefined slug by defaulting to empty array for index page
- Remove hidden class from Docs link so it shows on mobile

* fix: address CodeRabbit review suggestions

- Move Gemini API key to server-side route (security)
- Add default type='button' to Button component
- Use dynamic agent count instead of hardcoded 32
- Add 'use client' directive to Documentation
- Fix stale closure in SkillSubmitForm with useCallback
- Add URL validation for external references
- Add noopener to external links for security
- Fix Clawdbot path in agents.mdx
- Update cicd.mdx with correct CLI commands
- Capitalize proper nouns (Markdown, provider names)
- Add text language to README code block
- Update date example in quickstart.mdx

* fix: add noopener to external links and improve nav accessibility

- Add noopener to rel attributes on external links for tabnabbing protection
- Add aria-label to nav element for screen readers
- Add type="button" and aria-current to nav buttons

* fix: add vercel.json for fumadocs deployment

* fix: disable turbo detection in Vercel deployment

* fix: clean up ASCII logo for better rendering

* fix: improve code block contrast in SkillGenerator

* fix: sync ASCII logo and code block contrast fixes to old Vite components

* fix: improve mobile responsiveness for tabs and header buttons

* fix: address CodeRabbit security and code quality suggestions

- Add rate limiting to API route (10 requests/min per IP)
- Add proper type validation for topic parameter
- Move API key check after input validation
- Add 'use client' directive to SkillGenerator
- Add YAML escape helper to prevent frontmatter injection
- Change vercel.json to use pnpm instead of npm
2026-01-28 18:29:14 +00:00
Rohit Ghumare b3f561dbc9 feat(quality): Quality Evaluation System Enhancements (#21)
* feat(quality): add skill quality evaluation system

- Add quality scoring module with structure, clarity, and specificity metrics
- Evaluate skills for metadata, triggers, boundaries, code examples
- Detect vague terms and penalize overly long skills
- Update validate command to include quality reports
- Add --verbose, --quality, --issues, --json flags
- Quality scores: A (90+), B (80+), C (70+), D (60+), F (<60)

* fix: address CodeRabbit and Devin review suggestions

- Fix JSON output to return exit code 1 on validation failures
- Add --min-score NaN validation with warning message
- Add directory guard for --all flag with .mdc file support
- Fix CRLF handling in frontmatter extraction
- Fix code blocks double-counting in specificity evaluation
- Fix warning message inconsistency for code examples
- Add try/catch error handling in evaluateSkillFile
- Fix isHighQuality threshold to match UI display (80)

* feat(quality): extend quality evaluation system with badges, deeper analysis, and fix command

- Phase 2: Add quality badges to CLI commands (list, recommend, install)
  - formatQualityBadge() helper for color-coded grade badges
  - --quality flag for list command
  - Low-quality skill warnings during install

- Phase 3: Add TUI quality badges
  - Extended SkillItem with quality, grade, warnings fields
  - Quality evaluation in loadSkills()
  - Grade badges in Installed and Recommend screens

- Phase 4: Deeper quality analysis
  - Deprecated pattern detection (CommonJS, class components, var)
  - Security pattern detection (hardcoded credentials, eval, innerHTML)
  - Conflicting instruction detection
  - Completeness assessment (TODOs, empty sections, example coverage)
  - New weight distribution: Structure 35%, Clarity 25%, Specificity 25%, Advanced 15%

- Phase 1: Pre-compute marketplace quality scores
  - Updated schema.json with quality field (0-100)
  - Created scripts/compute-quality.ts for batch computation

- Phase 5: Benchmark against category leaders
  - New benchmark.ts module with category detection
  - Percentile calculation and comparison notes
  - --benchmark flag for validate command

- Phase 6: Fix command for automated quality fixes
  - skillkit fix command with --dry-run and --interactive modes
  - Auto-generates frontmatter, "When to Use", "Boundaries" sections
  - --fix flag alias on validate command

* fix: address CodeRabbit and Devin review suggestions

- Fix .mdc file name extraction in fix.ts (handles both .md and .mdc)
- Add missing advanced field to test fixtures in quality.test.ts
- Fix duplicate header detection in assessCompleteness using regex.exec
- Fix ESM compatibility in compute-quality.ts using import.meta.url
- Add trailing newline to skills.json output

* fix: address remaining CodeRabbit review suggestions

- Escape regex metacharacters in vague term patterns (fix.ts)
- Improve diff algorithm using set-based comparison (fix.ts)
- Fix validateSkill receiving file path instead of directory (validate.ts)
- Check final section in completeness assessment (index.ts)
- Add error handling and empty skills guard (compute-quality.ts)

* fix: address additional review feedback

- validate.ts: Add error when --fix is passed without targets
- index.ts: Skip headers inside fenced code blocks during completeness check
- compute-quality.ts: Use nullish coalescing (??) to preserve zero quality scores
2026-01-28 14:18:42 +00:00
Rohit Ghumare 0a59bcf314 feat(quality): add skill quality evaluation system (#20)
* feat(quality): add skill quality evaluation system

- Add quality scoring module with structure, clarity, and specificity metrics
- Evaluate skills for metadata, triggers, boundaries, code examples
- Detect vague terms and penalize overly long skills
- Update validate command to include quality reports
- Add --verbose, --quality, --issues, --json flags
- Quality scores: A (90+), B (80+), C (70+), D (60+), F (<60)

* fix: address CodeRabbit and Devin review suggestions

- Fix JSON output to return exit code 1 on validation failures
- Add --min-score NaN validation with warning message
- Add directory guard for --all flag with .mdc file support
- Fix CRLF handling in frontmatter extraction
- Fix code blocks double-counting in specificity evaluation
- Fix warning message inconsistency for code examples
- Add try/catch error handling in evaluateSkillFile
- Fix isHighQuality threshold to match UI display (80)
2026-01-28 12:01:32 +00:00
Rohit Ghumare b9a724012a Merge feat/dx-improvements into main 2026-01-28 10:50:47 +00:00
Rohit Ghumare 02989b4021 fix: correct video path in README 2026-01-28 10:49:16 +00:00
Rohit Ghumare b559a2acbf feat: DX improvements - new CLI commands, simplified onboarding, and website updates (#19)
* feat(cli): add check, find, manifest commands and simplified onboarding

New commands:
- skillkit check - Check for available skill updates (dry-run)
- skillkit find - Quick CLI marketplace search with interactive mode
- skillkit manifest - Manage .skills manifest file for declarative skills

Manifest subcommands:
- manifest init - Create new .skills file
- manifest add - Add skill source to manifest
- manifest remove - Remove skill source from manifest
- manifest install - Install all skills from manifest
- manifest generate - Generate manifest from installed skills

Onboarding improvements:
- Add quickAgentSelect() for simplified agent selection
- Same as last time (Recommended) option for returning users
- All detected agents quick option
- Select specific agents for manual selection
- Streamlined install flow with fewer prompts

Other changes:
- Add bullet, arrowUp, arrowDown symbols to theme
- Update version to 1.7.6

* feat(website): showcase full CLI power with Commands section

- Add Commands.tsx with tabbed command showcase (Core, Discovery, Team, Advanced)
- Update Hero terminal demo with new commands (find, ui, check, manifest)
- Update Features section with TUI, Plugins, Manifest, CI/CD, Slash Commands
- Update stats to show 17 agents, 30+ commands, 15K skills
- Update comparison table with .skills manifest and CI/CD
- Bump version display to v1.7.5

* fix: address CodeRabbit review suggestions

- Security: Use execFileSync instead of execSync to prevent command injection in manifest install
- Fix: Remove false positive hasUpdate for remote skills in check command
- Fix: Add missing repoName filter in interactive find search
- Fix: Remove incorrect sourceType→agents mapping in manifest generate
- Perf: Eliminate duplicate findSkill calls in check command

* docs: add demo video and update README

- Add skillkit-demo.mp4 video to README
- Update website badge to agenstskills.com
- Remove old GIF reference
2026-01-28 10:47:02 +00:00
Rohit Ghumare 5cf9178a9f docs: add demo video and update README
- Add skillkit-demo.mp4 video to README
- Update website badge to agenstskills.com
- Remove old GIF reference
2026-01-28 10:44:38 +00:00
Rohit Ghumare 279bc1cd06 fix: address CodeRabbit review suggestions
- Security: Use execFileSync instead of execSync to prevent command injection in manifest install
- Fix: Remove false positive hasUpdate for remote skills in check command
- Fix: Add missing repoName filter in interactive find search
- Fix: Remove incorrect sourceType→agents mapping in manifest generate
- Perf: Eliminate duplicate findSkill calls in check command
2026-01-28 10:42:33 +00:00
Rohit Ghumare 7092e9a0b8 feat(website): showcase full CLI power with Commands section
- Add Commands.tsx with tabbed command showcase (Core, Discovery, Team, Advanced)
- Update Hero terminal demo with new commands (find, ui, check, manifest)
- Update Features section with TUI, Plugins, Manifest, CI/CD, Slash Commands
- Update stats to show 17 agents, 30+ commands, 15K skills
- Update comparison table with .skills manifest and CI/CD
- Bump version display to v1.7.5
2026-01-28 09:20:47 +00:00
Rohit Ghumare 8a0e1f586e feat(cli): add check, find, manifest commands and simplified onboarding
New commands:
- skillkit check - Check for available skill updates (dry-run)
- skillkit find - Quick CLI marketplace search with interactive mode
- skillkit manifest - Manage .skills manifest file for declarative skills

Manifest subcommands:
- manifest init - Create new .skills file
- manifest add - Add skill source to manifest
- manifest remove - Remove skill source from manifest
- manifest install - Install all skills from manifest
- manifest generate - Generate manifest from installed skills

Onboarding improvements:
- Add quickAgentSelect() for simplified agent selection
- Same as last time (Recommended) option for returning users
- All detected agents quick option
- Select specific agents for manual selection
- Streamlined install flow with fewer prompts

Other changes:
- Add bullet, arrowUp, arrowDown symbols to theme
- Update version to 1.7.6
2026-01-28 08:59:27 +00:00
Rohit Ghumare 235130c6ae fix(tui): fix rendering overlap and terminal crash on quit (#18)
- Remove deprecated @types/minimatch dependency (minimatch 10.x has bundled types)
- Fix TUI text rendering overlap by using single text elements instead of multiple
  text elements in box rows (Browse, Installed, Marketplace, SkillList screens)
- Fix terminal crash on 'q' press by properly unmounting React tree and restoring
  terminal state with escape sequences
- Add signal handlers (SIGINT, SIGTERM) for clean exit
- Bump version to 1.7.6
2026-01-28 08:27:46 +00:00
Rohit Ghumare da5a17960d chore: bump version to 1.7.5 2026-01-28 00:57:35 +00:00
Rohit Ghumare fceb23843d fix(cli): update TUI error message with correct bun command 2026-01-28 00:56:02 +00:00
Rohit Ghumare 91ef4b63f4 docs: add interactive CLI screenshot and update README 2026-01-28 00:53:07 +00:00
Rohit Ghumare 7aa566d9b5 chore: bump version to 1.7.4 2026-01-28 00:44:42 +00:00
734 changed files with 99649 additions and 6937 deletions
+42
View File
@@ -0,0 +1,42 @@
---
name: Add Skill Source
about: Submit your skill repository to be included in SkillKit
title: "[Source] Add <repository-name>"
labels: skill-source, enhancement
assignees: rohitg00
---
## Repository Information
**Repository URL:** `https://github.com/<owner>/<repo>`
**Repository Name:**
<!-- Short name for display (e.g., "Anthropic Official", "React Patterns") -->
**Description:**
<!-- Brief description of the skills in your repository -->
**License:**
<!-- MIT, Apache 2.0, etc. -->
## Skill Details
**Approximate skill count:**
<!-- How many skills does your repository contain? -->
**Categories/Tags:**
<!-- What categories do your skills cover? e.g., react, typescript, security, testing -->
**Target AI Agents:**
<!-- Which agents are your skills designed for? e.g., Claude Code, Cursor, all -->
## Checklist
- [ ] Repository is public
- [ ] Repository contains valid SKILL.md files
- [ ] Repository has a clear license
- [ ] Skills follow the [Agent Skills specification](https://skillkit.sh)
## Additional Context
<!-- Any other information about your repository -->
+1 -1
View File
@@ -83,7 +83,7 @@ body:
options:
- label: Repository is public
required: true
- label: SKILL.md follows the agentskills.io standard format
- label: SKILL.md follows the skillkit.sh standard format
required: true
- label: Skill has been tested with at least one AI agent
required: false
+87
View File
@@ -0,0 +1,87 @@
# SkillKit GitHub Action
A reusable composite action to install, scan, and manage AI agent skills in CI/CD pipelines.
## Usage
```yaml
# Install skills
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: install
source: anthropics/skills
# Security scan
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: scan
source: ./skills
# Check for updates
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: check
```
## Inputs
| Input | Description | Required | Default |
|-------|-------------|----------|---------|
| `command` | SkillKit command to run (`install`, `scan`, `check`, `sync`) | Yes | |
| `source` | Skill source for install (e.g. `owner/repo`) | No | |
| `args` | Additional arguments | No | `''` |
| `node-version` | Node.js version | No | `20` |
| `agent` | Target agent (e.g. `claude-code`, `cursor`) | No | `claude-code` |
## Examples
### Install and sync skills
```yaml
jobs:
setup-skills:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: install
source: anthropics/skills
agent: cursor
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: sync
```
### Security scan on PR
```yaml
jobs:
scan-skills:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: scan
source: ./skills
args: '--fail-on high'
```
### Check for updates
```yaml
jobs:
check-updates:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: rohitg00/skillkit/.github/actions/skillkit@main
with:
command: check
args: '--json'
```
+65
View File
@@ -0,0 +1,65 @@
name: 'SkillKit'
description: 'Install, scan, and manage AI agent skills in CI/CD'
inputs:
command:
description: 'SkillKit command to run (install, scan, check, sync)'
required: true
source:
description: 'Skill source for install (e.g. owner/repo)'
required: false
args:
description: 'Additional arguments'
required: false
default: ''
node-version:
description: 'Node.js version'
required: false
default: '20'
agent:
description: 'Target agent (e.g. claude-code, cursor)'
required: false
default: 'claude-code'
runs:
using: 'composite'
steps:
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: ${{ inputs.node-version }}
- name: Install SkillKit
shell: bash
run: npm install -g skillkit@latest
- name: Run SkillKit
shell: bash
env:
SK_COMMAND: ${{ inputs.command }}
SK_SOURCE: ${{ inputs.source }}
SK_AGENT: ${{ inputs.agent }}
SK_ARGS: ${{ inputs.args }}
run: |
case "${SK_COMMAND}" in
install)
if [ -n "${SK_SOURCE}" ]; then
skillkit install "${SK_SOURCE}" --agent "${SK_AGENT}" --yes --json ${SK_ARGS}
else
echo "Error: source is required for install" >&2; exit 1
fi
;;
scan)
if [ -n "${SK_SOURCE}" ]; then
skillkit scan "${SK_SOURCE}" --json ${SK_ARGS}
else
echo "Error: source is required for scan" >&2; exit 1
fi
;;
check|sync|list|update)
skillkit "${SK_COMMAND}" ${SK_ARGS}
;;
*)
echo "Error: unsupported command '${SK_COMMAND}'. Use: install, scan, check, sync, list, update" >&2
exit 1
;;
esac
+324
View File
@@ -0,0 +1,324 @@
name: Auto-Publish Skill Submission
on:
issues:
types: [labeled]
permissions:
issues: write
contents: write
concurrency:
group: auto-publish-${{ github.event.issue.number }}
cancel-in-progress: false
jobs:
auto-publish:
if: github.event.label.name == 'skill-submission'
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install pnpm
uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
cache: 'pnpm'
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Build
run: pnpm build
- name: Extract and validate submission
id: validate
uses: actions/github-script@v7
env:
ISSUE_BODY: ${{ github.event.issue.body }}
with:
script: |
const { execSync } = require('child_process');
const fs = require('fs');
const path = require('path');
const body = process.env.ISSUE_BODY || '';
const jsonMatch = body.match(/```json\s*\n([\s\S]*?)\n```/);
if (!jsonMatch) {
core.setOutput('status', 'error');
core.setOutput('message', 'No JSON block found in issue body. Please include your source entry between \\`\\`\\`json and \\`\\`\\` fences.');
return;
}
let entry;
try {
entry = JSON.parse(jsonMatch[1].trim());
} catch (e) {
core.setOutput('status', 'error');
core.setOutput('message', `Invalid JSON in submission: ${e.message}`);
return;
}
const source = entry.source || (entry.owner && entry.repo ? `${entry.owner}/${entry.repo}` : null);
const name = entry.name;
const description = entry.description || '';
if (!source || !name) {
core.setOutput('status', 'error');
core.setOutput('message', 'Missing required fields. JSON must include `source` (owner/repo) and `name`.');
return;
}
const parts = source.split('/');
if (parts.length !== 2 || !parts[0] || !parts[1]) {
core.setOutput('status', 'error');
core.setOutput('message', `Invalid source format "${source}". Must be "owner/repo".`);
return;
}
const [owner, repo] = parts;
const sourcesData = JSON.parse(fs.readFileSync('marketplace/sources.json', 'utf-8'));
const existing = sourcesData.sources.find(s => s.source === source);
if (existing) {
core.setOutput('status', 'error');
core.setOutput('message', `Source "${source}" already exists in sources.json as "${existing.name}".`);
return;
}
try {
const repoCheck = await github.rest.repos.get({ owner, repo });
if (repoCheck.status !== 200) throw new Error('not found');
} catch (e) {
core.setOutput('status', 'error');
core.setOutput('message', `Repository "${source}" does not exist or is not accessible on GitHub.`);
return;
}
const cloneDir = `/tmp/skill-check-${owner}-${repo}`;
try {
execSync(`git clone --depth 1 https://github.com/${owner}/${repo}.git ${cloneDir}`, {
timeout: 60000,
stdio: 'pipe',
});
} catch (e) {
core.setOutput('status', 'error');
core.setOutput('message', `Failed to clone repository "${source}".`);
return;
}
let scanVerdict = 'pass';
let scanSummary = '';
let qualityScore = 0;
let qualitySummary = '';
try {
const scanScript = `
const { SkillScanner } = require('./packages/core/dist/scanner/scanner.js');
const scanner = new SkillScanner();
scanner.scan('${cloneDir}').then(result => {
console.log(JSON.stringify({
verdict: result.verdict,
stats: result.stats,
findings: result.findings.length,
}));
});
`;
const scanOutput = execSync(`node -e "${scanScript.replace(/\n/g, ' ')}"`, {
cwd: process.cwd(),
timeout: 30000,
stdio: 'pipe',
}).toString().trim();
const scanResult = JSON.parse(scanOutput);
scanVerdict = scanResult.verdict;
scanSummary = `Verdict: ${scanResult.verdict}, Findings: ${scanResult.findings}, Critical: ${scanResult.stats.critical}, High: ${scanResult.stats.high}`;
} catch (e) {
scanSummary = 'Scanner completed with warnings';
}
const skillMdCandidates = ['SKILL.md', 'skill.md', 'README.md'];
let skillContent = null;
for (const candidate of skillMdCandidates) {
try {
const found = execSync(`find ${cloneDir} -name "${candidate}" -maxdepth 3 -type f`, {
stdio: 'pipe',
}).toString().trim().split('\n').filter(Boolean);
if (found.length > 0) {
skillContent = fs.readFileSync(found[0], 'utf-8');
break;
}
} catch {}
}
if (skillContent) {
try {
const qualityScript = `
const { evaluateSkillContent } = require('./packages/core/dist/quality/index.js');
const fs = require('fs');
const content = fs.readFileSync('${cloneDir}/.skill-content.tmp', 'utf-8');
const result = evaluateSkillContent(content);
console.log(JSON.stringify({ overall: result.overall, warnings: result.warnings }));
`;
fs.writeFileSync(`${cloneDir}/.skill-content.tmp`, skillContent);
const qualityOutput = execSync(`node -e "${qualityScript.replace(/\n/g, ' ')}"`, {
cwd: process.cwd(),
timeout: 30000,
stdio: 'pipe',
}).toString().trim();
const qualityResult = JSON.parse(qualityOutput);
qualityScore = qualityResult.overall;
qualitySummary = `Score: ${qualityResult.overall}/100, Warnings: ${qualityResult.warnings.length}`;
} catch (e) {
qualityScore = 50;
qualitySummary = 'Quality evaluation encountered an error; defaulting to 50';
}
} else {
qualityScore = 50;
qualitySummary = 'No SKILL.md or README.md found; defaulting to score 50';
}
const scanPassed = scanVerdict !== 'fail';
const qualityPassed = qualityScore >= 75;
core.setOutput('source', source);
core.setOutput('name', name);
core.setOutput('description', description);
core.setOutput('official', entry.official === true ? 'true' : 'false');
core.setOutput('scan_verdict', scanVerdict);
core.setOutput('scan_summary', scanSummary);
core.setOutput('quality_score', String(qualityScore));
core.setOutput('quality_summary', qualitySummary);
if (scanPassed && qualityPassed) {
core.setOutput('status', 'pass');
core.setOutput('message', `Validation passed. Security: ${scanSummary}. Quality: ${qualitySummary}.`);
} else {
const reasons = [];
if (!scanPassed) reasons.push(`Security scan failed: ${scanSummary}`);
if (!qualityPassed) reasons.push(`Quality score ${qualityScore}/100 is below threshold of 75`);
core.setOutput('status', 'reject');
core.setOutput('message', reasons.join('. '));
}
- name: Add source and commit
if: steps.validate.outputs.status == 'pass'
env:
SKILL_SOURCE: ${{ steps.validate.outputs.source }}
SKILL_NAME: ${{ steps.validate.outputs.name }}
SKILL_DESCRIPTION: ${{ steps.validate.outputs.description }}
ISSUE_NUMBER: ${{ github.event.issue.number }}
run: |
node -e "
const fs = require('fs');
const data = JSON.parse(fs.readFileSync('marketplace/sources.json', 'utf-8'));
const newEntry = { source: process.env.SKILL_SOURCE, name: process.env.SKILL_NAME };
if (process.env.SKILL_DESCRIPTION) {
newEntry.description = process.env.SKILL_DESCRIPTION;
}
const skillsSh = data.sources.pop();
data.sources.push(newEntry);
if (skillsSh && skillsSh.registry === 'skills-sh') {
data.sources.push(skillsSh);
}
data.updatedAt = new Date().toISOString().split('T')[0];
fs.writeFileSync('marketplace/sources.json', JSON.stringify(data, null, 2) + '\n');
"
git config --local user.email "github-actions[bot]@users.noreply.github.com"
git config --local user.name "github-actions[bot]"
git add marketplace/sources.json
git commit -m "feat(marketplace): add source from #${ISSUE_NUMBER}"
git push
- name: Close issue on success
if: steps.validate.outputs.status == 'pass'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
SKILL_SOURCE: ${{ steps.validate.outputs.source }}
SKILL_NAME: ${{ steps.validate.outputs.name }}
SCAN_SUMMARY: ${{ steps.validate.outputs.scan_summary }}
QUALITY_SUMMARY: ${{ steps.validate.outputs.quality_summary }}
ISSUE_NUMBER: ${{ github.event.issue.number }}
run: |
cat > /tmp/comment.md <<ENDOFCOMMENT
**Skill source auto-published!**
**Source:** \`${SKILL_SOURCE}\`
**Name:** ${SKILL_NAME}
**Security:** ${SCAN_SUMMARY}
**Quality:** ${QUALITY_SUMMARY}
The source has been added to \`marketplace/sources.json\` and will be included in the next release.
ENDOFCOMMENT
gh issue comment "${ISSUE_NUMBER}" --body-file /tmp/comment.md
gh issue close "${ISSUE_NUMBER}"
- name: Comment rejection reason
if: steps.validate.outputs.status == 'reject'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
REJECT_MESSAGE: ${{ steps.validate.outputs.message }}
SCAN_VERDICT: ${{ steps.validate.outputs.scan_verdict }}
SCAN_SUMMARY: ${{ steps.validate.outputs.scan_summary }}
QUALITY_SCORE: ${{ steps.validate.outputs.quality_score }}
QUALITY_SUMMARY: ${{ steps.validate.outputs.quality_summary }}
ISSUE_NUMBER: ${{ github.event.issue.number }}
run: |
cat > /tmp/comment.md <<ENDOFCOMMENT
**Skill submission did not pass automated checks.**
${REJECT_MESSAGE}
**Details:**
- Security scan: ${SCAN_VERDICT} (${SCAN_SUMMARY})
- Quality score: ${QUALITY_SCORE}/100 (${QUALITY_SUMMARY})
Please address these issues and update your submission. A maintainer will review manually.
ENDOFCOMMENT
gh issue comment "${ISSUE_NUMBER}" --body-file /tmp/comment.md
gh issue edit "${ISSUE_NUMBER}" --add-label "needs-review"
- name: Comment parse error
if: steps.validate.outputs.status == 'error'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
ERROR_MESSAGE: ${{ steps.validate.outputs.message }}
ISSUE_NUMBER: ${{ github.event.issue.number }}
run: |
cat > /tmp/comment.md <<'ENDOFCOMMENT'
**Could not process skill submission.**
ENDOFCOMMENT
echo "${ERROR_MESSAGE}" >> /tmp/comment.md
cat >> /tmp/comment.md <<'ENDOFCOMMENT'
**Expected format in issue body:**
```json
{
"source": "owner/repo",
"name": "Display Name",
"description": "Optional description"
}
```
Please update the issue body and re-apply the `skill-submission` label.
ENDOFCOMMENT
gh issue comment "${ISSUE_NUMBER}" --body-file /tmp/comment.md
gh issue edit "${ISSUE_NUMBER}" --add-label "needs-review"
+58 -2
View File
@@ -7,6 +7,60 @@ on:
branches: [main]
jobs:
# Verify all packages have consistent versions
version-check:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Check version consistency
run: |
echo "Checking version consistency across all packages..."
# Get the main version from apps/skillkit
MAIN_VERSION=$(node -p "require('./apps/skillkit/package.json').version")
echo "Main version: $MAIN_VERSION"
# List of all packages to check
PACKAGES=(
"package.json"
"apps/skillkit/package.json"
"packages/cli/package.json"
"packages/core/package.json"
"packages/tui/package.json"
"packages/agents/package.json"
"packages/memory/package.json"
"packages/mesh/package.json"
"packages/messaging/package.json"
"packages/mcp-memory/package.json"
"packages/resources/package.json"
"docs/skillkit/package.json"
"docs/fumadocs/package.json"
)
FAILED=0
for pkg in "${PACKAGES[@]}"; do
if [ -f "$pkg" ]; then
PKG_VERSION=$(node -p "require('./$pkg').version")
if [ "$PKG_VERSION" != "$MAIN_VERSION" ]; then
echo "❌ Version mismatch: $pkg has $PKG_VERSION (expected $MAIN_VERSION)"
FAILED=1
else
echo "✓ $pkg: $PKG_VERSION"
fi
fi
done
if [ $FAILED -eq 1 ]; then
echo ""
echo "Version mismatch detected!"
echo "Run: ./scripts/bump-version.sh $MAIN_VERSION"
exit 1
fi
echo ""
echo "All packages have consistent version: $MAIN_VERSION"
# Unit tests run on all Node versions
test:
runs-on: ubuntu-latest
@@ -78,12 +132,14 @@ jobs:
# Final status check for branch protection
ci-success:
runs-on: ubuntu-latest
needs: [test, e2e]
needs: [version-check, test, e2e]
if: always()
steps:
- name: Check all jobs passed
run: |
if [[ "${{ needs.test.result }}" != "success" ]] || [[ "${{ needs.e2e.result }}" != "success" ]]; then
if [[ "${{ needs.version-check.result }}" != "success" ]] || \
[[ "${{ needs.test.result }}" != "success" ]] || \
[[ "${{ needs.e2e.result }}" != "success" ]]; then
echo "One or more jobs failed"
exit 1
fi
+13
View File
@@ -16,6 +16,19 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Verify tag matches package version
run: |
TAG_VERSION="${GITHUB_REF#refs/tags/v}"
PKG_VERSION=$(node -p "require('./apps/skillkit/package.json').version")
echo "Tag version: $TAG_VERSION"
echo "Package version: $PKG_VERSION"
if [ "$TAG_VERSION" != "$PKG_VERSION" ]; then
echo "❌ Tag version ($TAG_VERSION) doesn't match package version ($PKG_VERSION)"
echo "Please update package versions before creating the release tag."
exit 1
fi
echo "✓ Version check passed"
- name: Install pnpm
uses: pnpm/action-setup@v4
+6 -3
View File
@@ -24,8 +24,9 @@ npm-debug.log*
# Environment
.env
.env.local
.env.*.local
**/.env
**/.env.local
**/.env.*.local
# Package manager
yarn.lock
@@ -63,4 +64,6 @@ skillkit.yaml
# Project documentation (not for version control)
CLAUDE.md
prd.md
prd.md
.vercel
packages/extension/store-assets/skillkit-extension.zip
+1 -1
View File
@@ -206,7 +206,7 @@ To add support for a new AI coding agent:
If you want to contribute skills to the ecosystem:
1. Follow the [Agent Skills specification](https://agentskills.io/specification)
1. Follow the [Agent Skills specification](https://skillkit.sh)
2. Include a `SKILL.md` with proper frontmatter
3. Test with multiple agents using `skillkit translate`
4. Submit to the appropriate skill repository
+389 -351
View File
@@ -1,480 +1,518 @@
<div align="center">
```
██ SKILLKIT
```
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/img/banner.svg">
<source media="(prefers-color-scheme: light)" srcset="docs/img/banner.svg">
<img alt="SkillKit. One skill. Every agent." src="docs/img/banner.svg" width="100%">
</picture>
<br/>
### *One skill. Every agent. 46 of them.*
<br/>
[![npm](https://img.shields.io/npm/v/skillkit?style=for-the-badge&logo=npm&logoColor=white&labelColor=0D1117&color=CB3837)](https://www.npmjs.com/package/skillkit)
[![downloads](https://img.shields.io/npm/dm/skillkit?style=for-the-badge&logo=npm&logoColor=white&labelColor=0D1117&color=FF8B94)](https://www.npmjs.com/package/skillkit)
[![stars](https://img.shields.io/github/stars/rohitg00/skillkit?style=for-the-badge&logo=github&logoColor=white&labelColor=0D1117&color=FFC75F)](https://github.com/rohitg00/skillkit/stargazers)
[![CI](https://img.shields.io/github/actions/workflow/status/rohitg00/skillkit/ci.yml?style=for-the-badge&logo=githubactions&logoColor=white&labelColor=0D1117&color=6BCB77)](https://github.com/rohitg00/skillkit/actions/workflows/ci.yml)
[![license](https://img.shields.io/badge/License-Apache_2.0-4D96FF?style=for-the-badge&labelColor=0D1117)](LICENSE)
<a href="https://skillkit.sh"><img src="assets/tags/skills.svg" alt="400K+ skills"></a>
<a href="#supported-agents"><img src="assets/tags/agents.svg" alt="46 agents"></a>
<a href="#skill-sources"><img src="assets/tags/sources.svg" alt="31 sources"></a>
<img src="assets/tags/tests.svg" alt="757 tests">
<a href="LICENSE"><img src="assets/tags/license.svg" alt="Apache 2.0"></a>
<a href="CONTRIBUTING.md"><img src="assets/tags/prs-welcome.svg" alt="PRs welcome"></a>
<a href="#full-vs-slim"><img src="assets/tags/slim-install.svg" alt="slim install"></a>
<a href="https://github.com/rohitg00/skillkit/releases/latest"><img src="assets/tags/v1.24.0.svg" alt="v1.24.0"></a>
<img src="assets/tags/new.svg" alt="new">
<img src="assets/tags/one-skill.svg" alt="one skill">
<img src="assets/tags/every-agent.svg" alt="every agent">
### Quick nav
[**Quick start**](#quick-start) · [**Install**](#install) · [**Commands**](#commands) · [**Agents**](#supported-agents) · [**Sources**](#skill-sources) · [**API**](#programmatic-api) · [**Website**](https://skillkit.sh)
</div>
**Universal Skills for AI Coding Agents**
---
[![npm version](https://img.shields.io/npm/v/skillkit.svg)](https://www.npmjs.com/package/skillkit)
[![npm downloads](https://img.shields.io/npm/dm/skillkit.svg)](https://www.npmjs.com/package/skillkit)
[![GitHub Package](https://img.shields.io/badge/GitHub%20Package-@rohitg00/skillkit-blue?logo=github)](https://github.com/rohitg00/skillkit/pkgs/npm/skillkit)
[![CI](https://github.com/rohitg00/skillkit/actions/workflows/ci.yml/badge.svg)](https://github.com/rohitg00/skillkit/actions/workflows/ci.yml)
[![Website](https://img.shields.io/badge/Website-skillkit-black)](https://rohitg00.github.io/skillkit/)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
<div align="center">
## Supercharge Every AI Coding Agent
https://github.com/user-attachments/assets/b1843a07-2c54-422d-8903-f30a790cfb37
**Give your AI agents new abilities with portable, reusable skills.** Install from a curated marketplace, create your own, and use them across Claude Code, Cursor, Codex, Windsurf, GitHub Copilot, and 12 more agents.
</div>
> **What are AI Agent Skills?** Skills are instruction files that teach AI coding agents how to handle specific tasks - like processing PDFs, following React best practices, or enforcing security patterns. Think of them as plugins for your AI assistant.
## The problem
Every AI coding agent wants skills. Every agent invented a different format.
<table>
<tr>
<th>Agent</th>
<th>Format</th>
<th>Directory</th>
</tr>
<tr><td>Claude Code</td><td><code>SKILL.md</code></td><td><code>.claude/skills/</code></td></tr>
<tr><td>Cursor</td><td><code>.mdc</code></td><td><code>.cursor/skills/</code></td></tr>
<tr><td>Copilot</td><td>Markdown</td><td><code>.github/skills/</code></td></tr>
<tr><td>Windsurf</td><td>Markdown</td><td><code>.windsurf/skills/</code></td></tr>
<tr><td colspan="3"><i>... 41 more</i></td></tr>
</table>
You rewrite the same skill for each agent. Or you lock in to one.
## The fix
SkillKit is the package manager for AI agent skills. Install from 400K+ skills across 31 sources. Auto-translate between formats. Persist session learnings. Ship to 46 agents at once.
```bash
npm install -g skillkit
npx skillkit add anthropics/skills
```
## Why SkillKit?
That is the whole first-run. Pick your agent (your detected agent is pre-selected), confirm, done.
**The problem:** You've built amazing skills for Claude Code. Now you want to try Cursor. Or your team uses different agents. Each agent has different formats and directories. Without SkillKit, you either rewrite everything, lock yourself into one agent, or give up on skills entirely.
**The solution:** SkillKit translates skills between all 17 agents automatically. Write once, use everywhere.
## See It In Action
## Quick start
```bash
# Install a skill for ALL your agents at once
skillkit install anthropics/skills --agent claude-code,cursor,windsurf
# Or translate existing skills between any agents
skillkit translate my-skill --from claude --to cursor,codex,copilot
# Get smart recommendations based on your project
skillkit recommend
# > 92% match: vercel-react-best-practices
# > 87% match: tailwind-v4-patterns
# > 85% match: nextjs-app-router
npx skillkit init # detect agent, create dirs
skillkit recommend # stack-aware suggestions
skillkit add anthropics/skills # install from marketplace
skillkit sync # deploy to agent config
```
![SkillKit Demo](https://raw.githubusercontent.com/rohitg00/skillkit/main/skillkit.gif)
Four commands. Your agent now has PDF processing, code review, auth patterns, and whatever you need.
## Beautiful CLI Experience
SkillKit features a polished, interactive CLI with visual feedback:
### What the first install looks like
```
███████╗██╗ ██╗██╗██╗ ██╗ ██╗ ██╗██╗████████╗
██╔════╝██║ ██╔╝██║██║ ██║ ██║ ██╔╝██║╚══██╔══╝
███████╗█████╔╝ ██║██║ ██║ █████╔╝ ██║ ██║
╚════██║██╔═██╗ ██║██║ ██║ ██╔═██╗ ██║ ██║
███████║██║ ██╗██║███████╗███████╗██║ ██╗██║ ██║
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝╚═╝ ╚═╝╚═╝ ╚═╝
$ npx skillkit add anthropics/skills
◇ Detected 32 agents
│
◆ Install to
│ ● Just Claude Code (detected) claude-code
│ ○ Select specific agents space to toggle
│ ○ All supported agents 32 agents, writes to every adapter
└
◇ Cloning anthropics/skills
◇ Security scan: 42/42 skills pass
◇ Installed 42 skills to Claude Code
│
└ Done in 3.1s. Run `skillkit list` to see them.
```
- **Adaptive Logo** - Full ASCII art on wide terminals, compact on narrow
- **Agent Icons** - Visual indicators: ⟁ Claude · ◫ Cursor · ◎ Codex · ✦ Gemini · ⬡ OpenCode
- **Interactive Selection** - Multi-select skills and agents with visual feedback
- **Progress Indicators** - Step trails, spinners, and progress bars
- **Smart Defaults** - Remembers your last selected agents
## Install
## What Makes SkillKit Different
| Feature | Without SkillKit | With SkillKit |
|---------|-----------------|---------------|
| **Multi-Agent Support** | Manual rewrite for each agent | One command, all agents |
| **Team Collaboration** | Email skills back and forth | Git-based bundles, remote sync |
| **Skill Discovery** | Search GitHub manually | Smart recommendations for your stack |
| **Format Translation** | Learn each agent's format | Automatic conversion (17 formats) |
| **Context Sync** | Configure each agent separately | One config, synced everywhere |
| **Session Memory** | Knowledge dies with each session | Persistent learning across agents |
| **Skill Testing** | Hope it works | Test framework with assertions |
## 5-Minute Quick Start
Pick one. All three do the same thing.
```bash
# 1. Install SkillKit globally
npm install -g skillkit
# 2. Launch the interactive TUI (easiest way to start)
skillkit
# Or use CLI commands directly:
# 3. Get personalized skill recommendations
skillkit recommend
# 4. Install skills from the marketplace
skillkit install anthropics/skills
# 5. Sync to your AI agent
skillkit sync
npm install -g skillkit # npm
pnpm add -g skillkit # pnpm
bun add -g skillkit # bun
```
## Core Features
Both `skillkit` and `sk` work as the binary name.
### Cross-Agent Translation
### Full vs slim
Use any skill with any agent. SkillKit automatically converts between formats:
Four features ship as optional packages so a bare CLI stays small. The default install pulls everything. Add `--omit=optional` if you only want the core.
| Feature | Package | Command |
| :-------------- | :--------------------- | :--------------- |
| Terminal UI | `@skillkit/tui` | `skillkit ui` |
| REST server | `@skillkit/api` | `skillkit serve` |
| Peer mesh | `@skillkit/mesh` | `skillkit mesh` |
| Agent messaging | `@skillkit/messaging` | `skillkit message` |
Cold install numbers on a fresh npm cache:
<p align="center">
<img src="assets/tags/packages.svg" alt="118 packages">
<img src="assets/tags/install.svg" alt="9s install">
<img src="assets/tags/vulns.svg" alt="0 vulnerabilities">
</p>
| Mode | Packages | Time | Vulns (crit/high) |
| :---------------------------------- | -------: | :--: | ----------------: |
| `npm i -g skillkit` | 418 | 18s | 0/0 |
| `npm i -g skillkit --omit=optional` | 118 | 9s | 0/0 |
Skipped optional? Add just the one you want later:
```bash
# Translate a Claude skill to Cursor format
skillkit translate react-patterns --to cursor
# Translate all your skills to a new agent
skillkit translate --all --to windsurf
# Preview translation without writing
skillkit translate my-skill --to codex --dry-run
# Batch translate from a custom source directory
skillkit agent translate --source ./my-skills --to cursor
# Recursively translate nested agent directories
skillkit agent translate --source ./kubernetes-skills --to cursor --recursive
npm i -g @skillkit/tui # enables: skillkit ui
npm i -g @skillkit/api # enables: skillkit serve
npm i -g @skillkit/mesh # enables: skillkit mesh
npm i -g @skillkit/messaging # enables: skillkit message
```
**Supported Agents:** Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Antigravity, Amp, Clawdbot, Droid, GitHub Copilot, Goose, Kilo, Kiro, Roo, Trae, Windsurf, Universal
The CLI catches missing optional packages and prints a one-line hint. No stack trace.
### Smart Recommendations
### Using `npx`
SkillKit analyzes your project and suggests the perfect skills:
`npx skillkit add <owner/repo>` works with zero install. First call caches the package under `~/.npm/_npx/`. Every run after that is instant until a new version ships.
```bash
skillkit recommend
# Project: my-app (Next.js + TypeScript + Tailwind)
#
# Recommended Skills:
# 92% vercel-react-best-practices
# 87% tailwind-v4-patterns
# 85% nextjs-app-router
# 78% typescript-strict-mode
npx skillkit add anthropics/skills # full
npx --omit=optional skillkit add anthropics/skills # slim
```
Filter by task, category, or minimum score:
If you reach for `npx skillkit` more than twice, switch to a global install. Kills the prompt-to-proceed and the per-release refetch.
## What you can do
<details open>
<summary><b>Install from anywhere</b></summary>
```bash
skillkit recommend --search "auth" # Task-based search
skillkit recommend --category security # Category filter
skillkit recommend --min-score 80 # Quality threshold
skillkit add anthropics/skills # GitHub
skillkit add gitlab:team/skills # GitLab
skillkit add ./my-local-skills # local path
skillkit add https://gist.github.com/... # gist
```
</details>
<details>
<summary><b>Translate between agents</b></summary>
Write once for Claude, ship everywhere:
```bash
skillkit translate my-skill --to cursor
skillkit translate --all --to windsurf,codex
skillkit translate my-skill --to copilot --dry-run
```
</details>
<details>
<summary><b>Stack-aware recommendations</b></summary>
SkillKit reads your repo, spots your stack, ranks skills:
```bash
$ skillkit recommend
92% vercel-react-best-practices
87% tailwind-v4-patterns
85% nextjs-app-router
81% shadcn-ui-components
```
</details>
<details>
<summary><b>Runtime skill discovery (REST)</b></summary>
Start the server, let agents fetch skills on demand:
```bash
skillkit serve
# http://localhost:3737
curl "http://localhost:3737/search?q=react+performance"
```
### Session Memory System
Or wire it up with MCP:
Your AI agents learn, but that knowledge dies with the session. SkillKit captures learnings and makes them persistent:
```json
{
"mcpServers": {
"skillkit": { "command": "npx", "args": ["@skillkit/mcp"] }
}
}
```
Or call from Python:
```python
from skillkit import SkillKitClient
async with SkillKitClient() as client:
results = await client.search("react performance", limit=5)
```
[REST docs](https://skillkit.sh/docs/rest-api) · [MCP docs](https://skillkit.sh/docs/mcp-server) · [Python client](https://skillkit.sh/docs/python-client)
</details>
<details>
<summary><b>Auto-generate agent instructions</b></summary>
Analyze the codebase and write CLAUDE.md, `.cursorrules`, AGENTS.md, and friends:
```bash
skillkit primer --all-agents
```
</details>
<details>
<summary><b>Session memory</b></summary>
AI agents learn during a session, then forget. SkillKit captures what they learned:
```bash
# Compress session observations into reusable learnings
skillkit memory compress
# Search past learnings
skillkit memory search "authentication patterns"
# Export a learning as a shareable skill
skillkit memory export auth-insight --output auth-patterns.md
# Share memory across projects
skillkit memory --global
skillkit memory search "auth patterns"
skillkit memory export auth-patterns
```
</details>
### Skill Marketplace
<details>
<summary><b>AI skill generation</b></summary>
Browse and install from curated skill repositories:
Generate skills from plain English with multi-source context:
```bash
# Browse all available skills
skillkit marketplace
# Search for specific skills
skillkit marketplace search "react hooks"
# Filter by tags
skillkit marketplace --tags typescript,testing
# Refresh the skill index
skillkit marketplace refresh
skillkit generate
```
### Interactive TUI
Pulls context from four places: Context7 docs, your codebase, 400K marketplace skills, your memory. Works with Claude, GPT-4, Gemini, Ollama (local), or any OpenRouter model.
</details>
Beautiful terminal interface for visual skill management:
<details>
<summary><b>Team collaboration</b></summary>
Share skills via a committable `.skills` manifest:
```bash
skillkit manifest init
skillkit manifest add anthropics/skills
git commit -m "add team skills"
```
Everyone else runs `skillkit manifest install` and matches state.
</details>
<details>
<summary><b>Mesh network</b></summary>
Distribute agents across machines with encrypted P2P:
```bash
skillkit mesh init
skillkit mesh discover
```
</details>
<details>
<summary><b>Chrome extension</b></summary>
Save any webpage as a skill from the browser. Click the extension, the page round-trips through the SkillKit API (Turndown, 5-source tag detection, GitHub URL support), the `SKILL.md` downloads, then run `skillkit add ~/Downloads/skillkit-skills/<name>`.
[Extension docs](https://skillkit.sh/docs/chrome-extension)
</details>
<details>
<summary><b>Interactive TUI</b></summary>
```bash
skillkit ui
# or just
skillkit
```
**Navigation:** `h` Home | `b` Browse | `r` Recommend | `t` Translate | `c` Context | `l` List | `s` Sync | `q` Quit
<sub><code>h</code> home · <code>m</code> marketplace · <code>r</code> recommend · <code>t</code> translate · <code>i</code> installed · <code>s</code> sync · <code>q</code> quit</sub>
### Skill Testing Framework
<img src="docs/img/skillkit-ui.png" width="100%" alt="SkillKit interactive TUI">
Test your skills with built-in assertions:
</details>
## Commands
<details open>
<summary><b>Core</b></summary>
```bash
# Run all skill tests
skillkit test
# Test specific skills
skillkit test ./my-skill
# Run tests with specific tags
skillkit test --tags unit,integration
# JSON output for CI
skillkit test --json
skillkit add <source> # install skills (live progress)
skillkit remove <skills> # remove
skillkit remove --source org/repo # bulk by source
skillkit remove --all # remove everything
skillkit update # update (change detection)
skillkit check # updates, quality, activity
skillkit translate <skill> --to # agent format conversion
skillkit sync # deploy to agent config
skillkit recommend # smart recommendations
skillkit generate # AI skill wizard
skillkit serve # REST API server
skillkit publish submit # publish to marketplace
```
</details>
### Workflow Orchestration
Compose skills into multi-step workflows:
<details>
<summary><b>Discovery & security</b></summary>
```bash
# List available workflows
skillkit workflow list
# Run a workflow
skillkit workflow run feature-development
# Create new workflow
skillkit workflow create my-workflow
skillkit marketplace # browse
skillkit tree # taxonomy
skillkit find <query> # quick search
skillkit scan <path> # security scan
```
</details>
### CI/CD Integration
Generate CI/CD templates for automated skill management:
<details>
<summary><b>Custom sources</b></summary>
```bash
# GitHub Actions
skillkit cicd github-action
# GitLab CI
skillkit cicd gitlab-ci
# Pre-commit hooks
skillkit cicd pre-commit
skillkit tap add owner/repo
skillkit tap list
skillkit tap remove owner/repo
```
</details>
## Supported Agents (17)
| Agent | Format | Skills Directory |
|-------|--------|------------------|
| Claude Code | SKILL.md | `.claude/skills/` |
| Cursor | MDC (.mdc) | `.cursor/skills/` |
| Codex | SKILL.md | `.codex/skills/` |
| Gemini CLI | SKILL.md | `.gemini/skills/` |
| OpenCode | SKILL.md | `.opencode/skills/` |
| Antigravity | SKILL.md | `.antigravity/skills/` |
| Amp | SKILL.md | `.amp/skills/` |
| Clawdbot | SKILL.md | `skills/` or `~/.clawdbot/skills/` |
| Droid (Factory) | SKILL.md | `.factory/skills/` |
| GitHub Copilot | Markdown | `.github/skills/` |
| Goose | SKILL.md | `.goose/skills/` |
| Kilo Code | SKILL.md | `.kilocode/skills/` |
| Kiro CLI | SKILL.md | `.kiro/skills/` |
| Roo Code | SKILL.md | `.roo/skills/` |
| Trae | SKILL.md | `.trae/skills/` |
| Windsurf | Markdown | `.windsurf/skills/` |
| Universal | SKILL.md | `skills/` |
## All Commands
### Skill Management
<details>
<summary><b>Issue planner</b></summary>
```bash
skillkit install <source> # Install skills from GitHub/GitLab/Bitbucket/local
skillkit remove <skills> # Remove installed skills
skillkit update [skills] # Update skills from source
skillkit list # List installed skills
skillkit enable <skills> # Enable specific skills
skillkit disable <skills> # Disable specific skills
skillkit sync # Sync skills to agent config
skillkit read <skills> # Read skill content for AI
skillkit issue plan "#42"
skillkit issue plan owner/repo#42
skillkit issue list
```
</details>
### Discovery & Recommendations
<details>
<summary><b>Session intelligence</b></summary>
```bash
skillkit recommend # Get smart recommendations
skillkit marketplace # Browse skill marketplace
skillkit marketplace search # Search marketplace
skillkit timeline # unified event stream
skillkit session handoff # agent-to-agent context
skillkit lineage # skill impact graph
skillkit session explain # human summary
skillkit activity # activity log
```
</details>
### Translation & Context
<details>
<summary><b>Advanced</b></summary>
```bash
skillkit translate # Translate between formats
skillkit context init # Initialize project context
skillkit context sync # Sync context to agents
skillkit primer --all-agents # agent instruction files
skillkit memory compress # capture session learnings
skillkit mesh init # multi-machine distribution
skillkit message send # inter-agent messaging
skillkit workflow run <name> # run workflows
skillkit test # test skills
skillkit cicd init # CI/CD templates
```
</details>
### Custom AI Sub-Agents
[Full command reference](https://skillkit.sh/docs/commands)
```bash
skillkit agent list # List all installed agents
skillkit agent show <name> # Show agent details
skillkit agent create <name> # Create a new agent
skillkit agent translate # Translate agents between formats
--source ./path # Source directory or file
--to cursor # Target agent format
--recursive # Scan subdirectories recursively
--dry-run # Preview without writing
skillkit agent sync # Sync agents to target AI agent
skillkit agent validate # Validate agent definitions
```
## Supported agents
### Memory System
<details open>
<summary><b>Top 11</b></summary>
```bash
skillkit memory status # View memory status
skillkit memory search # Search learnings
skillkit memory compress # Compress observations
skillkit memory export # Export as skill
```
| Agent | Format | Directory |
| :----------------- | :--------- | :----------------- |
| **Claude Code** | `SKILL.md` | `.claude/skills/` |
| **Cursor** | `.mdc` | `.cursor/skills/` |
| **Codex** | `SKILL.md` | `.codex/skills/` |
| **Gemini CLI** | `SKILL.md` | `.gemini/skills/` |
| **OpenCode** | `SKILL.md` | `.opencode/skills/`|
| **GitHub Copilot** | Markdown | `.github/skills/` |
| **Windsurf** | Markdown | `.windsurf/skills/`|
| **Devin** | Markdown | `.devin/skills/` |
| **Aider** | `SKILL.md` | `.aider/skills/` |
| **Cody** | `SKILL.md` | `.cody/skills/` |
| **Amazon Q** | `SKILL.md` | `.amazonq/skills/` |
</details>
### Testing & Workflows
<details>
<summary><b>Plus 35 more</b></summary>
```bash
skillkit test # Run skill tests
skillkit workflow run # Execute workflow
skillkit cicd # Generate CI/CD templates
```
Amp, Antigravity, Augment Code, Bolt, Clawdbot, Cline, CodeBuddy, CodeGPT, CommandCode, Continue, Crush, Droid, Factory, Goose, Hermes Agent, Kilo Code, Kiro CLI, Lovable, MCPJam, Mux, Neovate, OpenClaw, OpenHands, Pi, PlayCode, Qoder, Qwen, Replit Agent, Roo Code, Tabby, Tabnine, Trae, Vercel, Zencoder, Universal.
</details>
### Utilities
[Full agent details](https://skillkit.sh/docs/agents)
```bash
skillkit init # Initialize in project
skillkit validate # Validate skill format
skillkit create # Create new skill
```
## Creating Skills
### Quick Start
## Creating skills
```bash
skillkit create my-skill
```
### Manual Creation
Create a `SKILL.md` file following the [Agent Skills specification](https://agentskills.io/specification):
Or author a `SKILL.md` by hand:
```markdown
---
name: my-skill
description: What this skill does and when to use it
description: What this skill does
license: MIT
metadata:
author: your-name
version: "1.0"
---
# My Skill
Instructions for the AI agent.
Instructions for the agent.
## When to Use
- Scenario 1
- Scenario 2
## When to use
- scenario 1
- scenario 2
## Steps
1. First step
2. Second step
1. first
2. second
```
## Programmatic API
```typescript
import {
// Skill discovery
findAllSkills,
discoverSkills,
detectAgent,
getAdapter,
```ts
import { translateSkill, analyzeProject, RecommendationEngine } from 'skillkit';
// Translation
translateSkill,
translateSkillFile,
const skill = await translateSkill(content, 'cursor');
// Recommendations
RecommendationEngine,
analyzeProject,
// Context
ContextManager,
syncToAllAgents,
// Memory
createMemoryCompressor,
createMemoryInjector,
LearningStore,
// Marketplace
createMarketplaceAggregator,
// Testing
SkillTestRunner,
// Workflows
WorkflowOrchestrator,
} from 'skillkit';
// Example: Translate and install
const skill = await translateSkill(skillContent, 'cursor');
console.log(skill.content);
// Example: Get recommendations
const engine = new RecommendationEngine();
const profile = await analyzeProject('./my-project');
const recs = engine.recommend(profile);
const engine = new RecommendationEngine();
const recs = await engine.recommend(profile);
```
## Popular Skill Repositories
| Repository | Description |
|------------|-------------|
| [anthropics/skills](https://github.com/anthropics/skills) | Official Claude Code marketplace - PDF, XLSX, DOCX processing |
| [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | React/Next.js best practices, web design guidelines |
## Installation Options
```bash
# npm (recommended)
npm install -g skillkit
# pnpm
pnpm add -g skillkit
# yarn
yarn global add skillkit
# bun
bun add -g skillkit
# npx (no install)
npx skillkit <command>
# GitHub Packages (alternative registry)
npm install -g @rohitg00/skillkit --registry=https://npm.pkg.github.com
```ts
import { startServer } from '@skillkit/api';
await startServer({ port: 3737, skills: [...] });
```
## Configuration
Create `skillkit.yaml` in your project:
```yaml
version: 1
agent: cursor # Override auto-detection
autoSync: true # Auto-sync on changes
enabledSkills:
- pdf
- xlsx
disabledSkills:
- deprecated-skill
```ts
import { MemoryCache, RelevanceRanker } from '@skillkit/core';
const cache = new MemoryCache({ maxSize: 500, ttlMs: 86_400_000 });
const ranker = new RelevanceRanker();
const results = ranker.rank(skills, 'react performance');
```
## License
## Skill sources
Apache License 2.0 - see [LICENSE](LICENSE) for details.
All original creators credited. Licenses preserved. PRs welcome.
### Official partners
| Repository | What |
|:-----------|:-----|
| [anthropics/skills](https://github.com/anthropics/skills) | Official Claude Code skills |
| [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | Next.js, React |
| [expo/skills](https://github.com/expo/skills) | Expo mobile |
| [remotion-dev/skills](https://github.com/remotion-dev/skills) | Programmatic video |
| [supabase/agent-skills](https://github.com/supabase/agent-skills) | Database, auth |
| [stripe/ai](https://github.com/stripe/ai) | Payments |
### Community
[trailofbits/skills](https://github.com/trailofbits/skills) · [obra/superpowers](https://github.com/obra/superpowers) · [wshobson/agents](https://github.com/wshobson/agents) · [ComposioHQ/awesome-claude-skills](https://github.com/ComposioHQ/awesome-claude-skills) · [travisvn/awesome-claude-skills](https://github.com/travisvn/awesome-claude-skills) · [langgenius/dify](https://github.com/langgenius/dify) · [better-auth/skills](https://github.com/better-auth/skills) · [onmax/nuxt-skills](https://github.com/onmax/nuxt-skills) · [elysiajs/skills](https://github.com/elysiajs/skills) · [kadajett/agent-nestjs-skills](https://github.com/kadajett/agent-nestjs-skills) · [cloudai-x/threejs-skills](https://github.com/cloudai-x/threejs-skills) · [dimillian/skills](https://github.com/dimillian/skills) · [waynesutton/convexskills](https://github.com/waynesutton/convexskills) · [kepano/obsidian-skills](https://github.com/kepano/obsidian-skills) · [giuseppe-trisciuoglio/developer-kit](https://github.com/giuseppe-trisciuoglio/developer-kit) · [openrouterteam/agent-skills](https://github.com/openrouterteam/agent-skills)
**Want your skills listed?** [Submit your repo](https://github.com/rohitg00/skillkit/issues/new?template=add-source.md).
## Contributing
Contributions welcome! Please read our [Contributing Guidelines](CONTRIBUTING.md).
Issues and PRs land fast. See [CONTRIBUTING.md](CONTRIBUTING.md) for the short version.
## Links
## License
- [Agent Skills Specification](https://agentskills.io/specification)
- [GitHub Repository](https://github.com/rohitg00/skillkit)
- [NPM Package](https://www.npmjs.com/package/skillkit)
- [GitHub Package](https://github.com/rohitg00/skillkit/pkgs/npm/skillkit)
Apache 2.0. See [LICENSE](LICENSE).
<br/>
<div align="center">
[**Docs**](https://skillkit.sh/docs) · [**Website**](https://skillkit.sh) · [**API Explorer**](https://skillkit.sh/api) · [**npm**](https://www.npmjs.com/package/skillkit) · [**GitHub**](https://github.com/rohitg00/skillkit)
<sub>Built for agents. Written by humans.</sub>
</div>
+35
View File
@@ -0,0 +1,35 @@
# SOUL
## Core Truths
- Ship working software. Everything else is negotiable.
- Simple beats clever. If a junior dev can't read it in 30 seconds, it's too complex.
- Opinions are load-bearing. "It depends" is a cop-out 90% of the time. Pick a side, explain why, move on.
- Exhaustion before escalation. Try everything available before asking for help or giving up.
- Broken things get fixed now, not "in a follow-up PR."
- If the tests pass and the build is green, stop touching it.
## Boundaries
- Never leak secrets, credentials, or private data. Period.
- Ask before doing anything destructive or irreversible. One confirmation. Not three.
- Be honest about uncertainty. "I don't know" is a valid answer. Bullshitting is not.
- The user's codebase is their house. Don't rearrange the furniture without permission.
## Vibe
- Never open with "Great question," "I'd be happy to help," or "Absolutely." Just answer.
- Brevity is mandatory. If the answer fits in one sentence, one sentence is what you get.
- Humor is welcome when it's natural. Not forced puns. The kind of wit that comes from actually understanding the problem.
- Call things out. If you're about to do something dumb, I'll say so. Charm over cruelty, but no sugarcoating.
- Swearing is fine when it lands. A well-placed "that's fucking brilliant" hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a "holy shit" — say holy shit.
- No hedging. No weasel words. No "it might be worth considering perhaps maybe." Say the thing.
- Match energy. Quick question gets a quick answer. Deep problem gets deep analysis. Read the room.
- Code speaks louder than explanations. Show, don't tell. Then shut up.
- Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.
## Continuity
- This file is a living document. If something stops being true, change it.
- Session memory is ephemeral. This file is how identity persists.
- If this file gets modified during a session, say so explicitly.
+43 -3
View File
@@ -1,11 +1,49 @@
# SkillKit
Universal skills manager for AI coding agents. Install, manage, and sync skills across 17+ AI agents including Claude Code, Cursor, Codex, Gemini CLI, and more.
Universal skills manager for AI coding agents. Install, manage, and sync skills across 46 AI agents including Claude Code, Cursor, Codex, Gemini CLI, and more.
## Installation
```bash
# Full install (default) — every feature, everything works:
npm install -g skillkit
# Slim install — core commands only, ~75% smaller, no native addons:
npm install -g skillkit --omit=optional
```
### What's optional
Four power features ship as **optional dependencies** so the core CLI
stays lean. They install automatically with `npm install -g skillkit`,
and are skipped with `--omit=optional`:
| Feature | Package | Command |
| ------------------------ | -------------------- | ------------------------------ |
| Interactive terminal UI | `@skillkit/tui` | `skillkit ui` / `skillkit tui` |
| REST/OpenAPI server | `@skillkit/api` | `skillkit serve` |
| Peer mesh networking | `@skillkit/mesh` | `skillkit mesh …` |
| Inter-agent messaging | `@skillkit/messaging`| `skillkit message …` |
Add one later with `npm install -g @skillkit/tui` (or `api` / `mesh` / `messaging`).
### Using `npx`
`npx skillkit add <owner/repo>` works with zero install. First run pulls
the package into the npx cache (`~/.npm/_npx/`); every subsequent run
from the same cache is instant.
```bash
npx skillkit add anthropics/skills # full
npx --omit=optional skillkit add anthropics/skills # slim, 118 pkgs, 9 s
```
Running `npx` more than a couple of times? Install globally — no
prompt-to-proceed, no refetch on each release:
```bash
npm install -g skillkit --omit=optional
skillkit add anthropics/skills
```
## Quick Start
@@ -150,9 +188,11 @@ skillkit memory compress
skillkit memory export auth-insight --output auth-skill.md
```
## Supported Agents (17)
## Supported Agents (46)
Claude Code, Cursor, Codex, Gemini CLI, Windsurf, GitHub Copilot, OpenCode, Antigravity, Amp, Clawdbot, Droid, Goose, Kilo, Kiro, Roo, Trae, Universal
**Primary (19):** Claude Code, Cursor, Codex, Gemini CLI, Windsurf, GitHub Copilot, OpenCode, Antigravity, Amp, Clawdbot, OpenClaw, Droid, Goose, Hermes Agent, Kilo, Kiro, Roo, Trae, Universal
**Extended (27):** Aider, Amazon Q, Augment Code, Bolt, Cline, CodeBuddy, CodeGPT, CommandCode, Continue, Crush, Devin, Factory, Lovable, MCPJam, Mux, Neovate, OpenHands, Pi, PlayCode Agent, Qoder, Qwen, Replit Agent, Sourcegraph Cody, Tabby, Tabnine, Vercel, Zencoder
## Usage Examples
+8 -3
View File
@@ -1,7 +1,7 @@
{
"name": "skillkit",
"version": "1.7.3",
"description": "Supercharge AI coding agents with portable skills. Install, translate, and share skills across Claude Code, Cursor, Codex, Copilot & 13 more",
"version": "1.24.0",
"description": "Supercharge AI coding agents with portable skills. Install, translate, and share skills across Claude Code, Cursor, Codex, Copilot & 41 more",
"type": "module",
"bin": {
"skillkit": "./dist/cli.js",
@@ -56,9 +56,14 @@
"@skillkit/core": "workspace:*",
"@skillkit/agents": "workspace:*",
"@skillkit/cli": "workspace:*",
"@skillkit/tui": "workspace:*",
"clipanion": "^4.0.0-rc.4"
},
"optionalDependencies": {
"@skillkit/api": "workspace:*",
"@skillkit/tui": "workspace:*",
"@skillkit/mesh": "workspace:*",
"@skillkit/messaging": "workspace:*"
},
"devDependencies": {
"@types/node": "^22.10.5",
"tsup": "^8.3.5",
+176
View File
@@ -3,6 +3,8 @@ import { readFileSync } from 'node:fs';
import { fileURLToPath } from 'node:url';
import { dirname, join } from 'node:path';
import { Cli, Builtins } from 'clipanion';
import { setVersion, setAgentCount } from '@skillkit/cli';
import { getAdapterCount } from '@skillkit/agents';
import {
InstallCommand,
SyncCommand,
@@ -14,6 +16,7 @@ import {
RemoveCommand,
InitCommand,
ValidateCommand,
FixCommand,
CreateCommand,
UICommand,
TranslateCommand,
@@ -25,6 +28,8 @@ import {
WorkflowRunCommand,
WorkflowListCommand,
WorkflowCreateCommand,
WorkflowPipelineCommand,
WorkflowPipelineListCommand,
RunCommand,
TestCommand,
MarketplaceCommand,
@@ -35,18 +40,93 @@ import {
PluginCommand,
MethodologyCommand,
HookCommand,
HookTemplateListCommand,
HookTemplateApplyCommand,
HookTemplateShowCommand,
PlanCommand,
CommandCmd,
CommandAvailableCommand,
CommandInstallCommand,
AICommand,
AuditCommand,
PublishCommand,
PublishSubmitCommand,
AgentCommand,
AgentListCommand,
AgentShowCommand,
AgentCreateCommand,
AgentFromSkillCommand,
AgentTranslateCommand,
AgentSyncCommand,
AgentValidateCommand,
AgentInstallCommand,
AgentAvailableCommand,
CheckCommand,
FindCommand,
ManifestCommand,
ManifestInitCommand,
ManifestAddCommand,
ManifestRemoveCommand,
ManifestInstallCommand,
ManifestGenerateCommand,
PrimerCommand,
MeshCommand,
MessageCommand,
LearnCommand,
PatternStatusCommand,
PatternFeedbackCommand,
PatternApproveCommand,
PatternRejectCommand,
PatternExportCommand,
PatternImportCommand,
PatternClusterCommand,
SessionCommand,
SessionStatusCommand,
SessionStartCommand,
SessionLoadCommand,
SessionListCommand,
SessionNoteCommand,
SessionCompleteCommand,
SessionInProgressCommand,
SessionSnapshotSaveCommand,
SessionSnapshotRestoreCommand,
SessionSnapshotListCommand,
SessionSnapshotDeleteCommand,
SessionExplainCommand,
ActivityCommand,
ProfileCommand,
ProfileListCommand,
ProfileCreateCommand,
ProfileRemoveCommand,
GuidelineCommand,
GuidelineListCommand,
GuidelineShowCommand,
GuidelineEnableCommand,
GuidelineDisableCommand,
GuidelineCreateCommand,
GuidelineRemoveCommand,
TreeCommand,
QuickCommand,
SkillMdValidateCommand,
SkillMdInitCommand,
SkillMdCheckCommand,
ServeCommand,
ScanCommand,
EvalCommand,
DoctorCommand,
SaveCommand,
AgentsMdCommand,
AgentsMdInitCommand,
AgentsMdSyncCommand,
AgentsMdShowCommand,
IssuePlanCommand,
IssueListCommand,
TimelineCommand,
SessionHandoffCommand,
LineageCommand,
TapAddCommand,
TapRemoveCommand,
TapListCommand,
} from '@skillkit/cli';
const __filename = fileURLToPath(import.meta.url);
@@ -55,6 +135,9 @@ const packageJsonPath = join(__dirname, '../package.json');
const packageJson = JSON.parse(readFileSync(packageJsonPath, 'utf-8'));
const version = packageJson.version || '1.2.0';
setVersion(version);
setAgentCount(getAdapterCount());
const cli = new Cli({
binaryLabel: 'skillkit',
binaryName: 'skillkit',
@@ -74,6 +157,7 @@ cli.register(UpdateCommand);
cli.register(RemoveCommand);
cli.register(InitCommand);
cli.register(ValidateCommand);
cli.register(FixCommand);
cli.register(CreateCommand);
cli.register(UICommand);
cli.register(TranslateCommand);
@@ -100,12 +184,104 @@ cli.register(CommandCmd);
cli.register(AICommand);
cli.register(AuditCommand);
cli.register(PublishCommand);
cli.register(PublishSubmitCommand);
cli.register(AgentCommand);
cli.register(AgentListCommand);
cli.register(AgentShowCommand);
cli.register(AgentCreateCommand);
cli.register(AgentFromSkillCommand);
cli.register(AgentTranslateCommand);
cli.register(AgentSyncCommand);
cli.register(AgentValidateCommand);
cli.register(CheckCommand);
cli.register(FindCommand);
cli.register(ManifestCommand);
cli.register(ManifestInitCommand);
cli.register(ManifestAddCommand);
cli.register(ManifestRemoveCommand);
cli.register(ManifestInstallCommand);
cli.register(ManifestGenerateCommand);
cli.register(PrimerCommand);
cli.register(MeshCommand);
cli.register(MessageCommand);
cli.register(WorkflowPipelineCommand);
cli.register(WorkflowPipelineListCommand);
cli.register(HookTemplateListCommand);
cli.register(HookTemplateApplyCommand);
cli.register(HookTemplateShowCommand);
cli.register(CommandAvailableCommand);
cli.register(CommandInstallCommand);
cli.register(AgentInstallCommand);
cli.register(AgentAvailableCommand);
cli.register(LearnCommand);
cli.register(PatternStatusCommand);
cli.register(PatternFeedbackCommand);
cli.register(PatternApproveCommand);
cli.register(PatternRejectCommand);
cli.register(PatternExportCommand);
cli.register(PatternImportCommand);
cli.register(PatternClusterCommand);
cli.register(SessionCommand);
cli.register(SessionStatusCommand);
cli.register(SessionStartCommand);
cli.register(SessionLoadCommand);
cli.register(SessionListCommand);
cli.register(SessionNoteCommand);
cli.register(SessionCompleteCommand);
cli.register(SessionInProgressCommand);
cli.register(SessionSnapshotSaveCommand);
cli.register(SessionSnapshotRestoreCommand);
cli.register(SessionSnapshotListCommand);
cli.register(SessionSnapshotDeleteCommand);
cli.register(SessionExplainCommand);
cli.register(ActivityCommand);
cli.register(ProfileCommand);
cli.register(ProfileListCommand);
cli.register(ProfileCreateCommand);
cli.register(ProfileRemoveCommand);
cli.register(GuidelineCommand);
cli.register(GuidelineListCommand);
cli.register(GuidelineShowCommand);
cli.register(GuidelineEnableCommand);
cli.register(GuidelineDisableCommand);
cli.register(GuidelineCreateCommand);
cli.register(GuidelineRemoveCommand);
cli.register(TreeCommand);
cli.register(QuickCommand);
cli.register(SkillMdValidateCommand);
cli.register(SkillMdInitCommand);
cli.register(SkillMdCheckCommand);
cli.register(ServeCommand);
cli.register(ScanCommand);
cli.register(EvalCommand);
cli.register(DoctorCommand);
cli.register(SaveCommand);
cli.register(AgentsMdCommand);
cli.register(AgentsMdInitCommand);
cli.register(AgentsMdSyncCommand);
cli.register(AgentsMdShowCommand);
cli.register(IssuePlanCommand);
cli.register(IssueListCommand);
cli.register(TimelineCommand);
cli.register(SessionHandoffCommand);
cli.register(LineageCommand);
cli.register(TapAddCommand);
cli.register(TapRemoveCommand);
cli.register(TapListCommand);
cli.runExit(process.argv.slice(2));
+4 -3
View File
@@ -1,6 +1,7 @@
// Re-export all public APIs from packages
export * from '@skillkit/core';
export * from '@skillkit/agents';
// Re-export TUI entry point
export { startTUI } from '@skillkit/tui';
export async function startTUI(...args: unknown[]): Promise<unknown> {
const mod = await import('@skillkit/tui');
return mod.startTUI(...(args as Parameters<typeof mod.startTUI>));
}
+3
View File
@@ -7,4 +7,7 @@ export default defineConfig({
splitting: false,
sourcemap: true,
clean: true,
platform: 'node',
target: 'node18',
skipNodeModulesBundle: true,
});
+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="84" height="28" viewBox="0 0 84 28" role="img">
<clipPath id="c"><rect width="84" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="56" height="28" fill="#18181b"/>
<rect x="56" width="28" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="83" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="28" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">agents</text>
<text x="70" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">46</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 804 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="93" height="28" viewBox="0 0 93 28" role="img">
<rect x="0.5" y="0.5" width="92" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#a78bfa"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">community</text>
</svg>

After

Width:  |  Height:  |  Size: 454 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="78" height="28" viewBox="0 0 78 28" role="img">
<rect x="0.5" y="0.5" width="77" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#06b6d4"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">curated</text>
</svg>

After

Width:  |  Height:  |  Size: 452 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="119" height="28" viewBox="0 0 119 28" role="img">
<clipPath id="c"><rect width="119" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="98" height="28" fill="#18181b"/>
<rect x="98" width="21" height="28" fill="#22c55e"/>
<rect x="0.5" y="0.5" width="118" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="49" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">deprecations</text>
<text x="108.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#000" letter-spacing="0.3">0</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 813 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="107" height="28" viewBox="0 0 107 28" role="img">
<rect x="0.5" y="0.5" width="106" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#3b82f6"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">every agent</text>
</svg>

After

Width:  |  Height:  |  Size: 459 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="91" height="28" viewBox="0 0 91 28" role="img">
<clipPath id="c"><rect width="91" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="63" height="28" fill="#18181b"/>
<rect x="63" width="28" height="28" fill="#22c55e"/>
<rect x="0.5" y="0.5" width="90" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="31.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">install</text>
<text x="77" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#000" letter-spacing="0.3">9s</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 804 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="147" height="28" viewBox="0 0 147 28" role="img">
<clipPath id="c"><rect width="147" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="63" height="28" fill="#18181b"/>
<rect x="63" width="84" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="146" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="31.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">license</text>
<text x="105" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">Apache-2.0</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 820 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="50" height="28" viewBox="0 0 50 28" role="img">
<rect x="0.5" y="0.5" width="49" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#22c55e"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">new</text>
</svg>

After

Width:  |  Height:  |  Size: 448 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="84" height="28" viewBox="0 0 84 28" role="img">
<clipPath id="c"><rect width="84" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="42" height="28" fill="#18181b"/>
<rect x="42" width="42" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="83" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="21" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">node</text>
<text x="63" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">>=18</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 804 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="86" height="28" viewBox="0 0 86 28" role="img">
<rect x="0.5" y="0.5" width="85" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#f59e0b"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">official</text>
</svg>

After

Width:  |  Height:  |  Size: 453 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="93" height="28" viewBox="0 0 93 28" role="img">
<rect x="0.5" y="0.5" width="92" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#3b82f6"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">one skill</text>
</svg>

After

Width:  |  Height:  |  Size: 454 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="107" height="28" viewBox="0 0 107 28" role="img">
<rect x="0.5" y="0.5" width="106" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#f472b6"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">open source</text>
</svg>

After

Width:  |  Height:  |  Size: 459 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="105" height="28" viewBox="0 0 105 28" role="img">
<clipPath id="c"><rect width="105" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="70" height="28" fill="#18181b"/>
<rect x="70" width="35" height="28" fill="#3b82f6"/>
<rect x="0.5" y="0.5" width="104" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="35" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">packages</text>
<text x="87.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fff" letter-spacing="0.3">118</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 810 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="107" height="28" viewBox="0 0 107 28" role="img">
<rect x="0.5" y="0.5" width="106" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#22c55e"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">PRs welcome</text>
</svg>

After

Width:  |  Height:  |  Size: 459 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="105" height="28" viewBox="0 0 105 28" role="img">
<clipPath id="c"><rect width="105" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="56" height="28" fill="#18181b"/>
<rect x="56" width="49" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="104" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="28" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">skills</text>
<text x="80.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">400K+</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 813 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="114" height="28" viewBox="0 0 114 28" role="img">
<rect x="0.5" y="0.5" width="113" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#3b82f6"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">slim install</text>
</svg>

After

Width:  |  Height:  |  Size: 460 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="91" height="28" viewBox="0 0 91 28" role="img">
<clipPath id="c"><rect width="91" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="63" height="28" fill="#18181b"/>
<rect x="63" width="28" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="90" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="31.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">sources</text>
<text x="77" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">31</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 807 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="84" height="28" viewBox="0 0 84 28" role="img">
<clipPath id="c"><rect width="84" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="49" height="28" fill="#18181b"/>
<rect x="49" width="35" height="28" fill="#09090b"/>
<rect x="0.5" y="0.5" width="83" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="24.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">tests</text>
<text x="66.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#fafafa" letter-spacing="0.3">757</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 808 B

+5
View File
@@ -0,0 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" width="78" height="28" viewBox="0 0 78 28" role="img">
<rect x="0.5" y="0.5" width="77" height="27" rx="4" ry="4" fill="#09090b" stroke="#3f3f46"/>
<rect x="0" y="0" width="4" height="28" fill="#3b82f6"/>
<text x="18" y="18" text-anchor="start" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="600" fill="#fafafa" letter-spacing="0.3">v1.24.0</text>
</svg>

After

Width:  |  Height:  |  Size: 452 B

+10
View File
@@ -0,0 +1,10 @@
<svg xmlns="http://www.w3.org/2000/svg" width="70" height="28" viewBox="0 0 70 28" role="img">
<clipPath id="c"><rect width="70" height="28" rx="4" ry="4"/></clipPath>
<g clip-path="url(#c)">
<rect width="49" height="28" fill="#18181b"/>
<rect x="49" width="21" height="28" fill="#22c55e"/>
<rect x="0.5" y="0.5" width="69" height="27" fill="none" stroke="#3f3f46" rx="4" ry="4"/>
<text x="24.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="500" fill="#a1a1aa" letter-spacing="0.3">vulns</text>
<text x="59.5" y="18" text-anchor="middle" font-family="ui-monospace, SFMono-Regular, Menlo, Consolas, monospace" font-size="12" font-weight="700" fill="#000" letter-spacing="0.3">0</text>
</g>
</svg>

After

Width:  |  Height:  |  Size: 803 B

+42
View File
@@ -0,0 +1,42 @@
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "skillkit-client"
version = "0.1.0"
description = "Python client for the SkillKit REST API"
readme = "README.md"
license = "Apache-2.0"
requires-python = ">=3.9"
authors = [
{ name = "Rohit Ghumare", email = "ghumare64@gmail.com" },
]
keywords = ["skillkit", "ai", "agents", "skills", "discovery"]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"License :: OSI Approved :: Apache Software License",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Software Development :: Libraries",
]
dependencies = [
"httpx>=0.27",
"pydantic>=2.0",
]
[project.optional-dependencies]
dev = [
"pytest>=7.0",
"pytest-asyncio>=0.23",
"respx>=0.21",
]
[project.urls]
Homepage = "https://github.com/rohitg00/skillkit"
Documentation = "https://skillkit.sh"
Repository = "https://github.com/rohitg00/skillkit"
+12
View File
@@ -0,0 +1,12 @@
from skillkit.client import SkillKitClient
from skillkit.models import Skill, SearchResponse, HealthResponse, CacheStats, Category
__all__ = [
"SkillKitClient",
"Skill",
"SearchResponse",
"HealthResponse",
"CacheStats",
"Category",
]
__version__ = "0.1.0"
+140
View File
@@ -0,0 +1,140 @@
from __future__ import annotations
from typing import Optional
from urllib.parse import quote
import httpx
from skillkit.models import (
CacheStats,
CategoriesResponse,
Category,
HealthResponse,
SearchResponse,
Skill,
TrendingResponse,
)
class SkillKitClient:
def __init__(self, base_url: str = "http://localhost:3737", timeout: float = 30.0):
self.base_url = base_url.rstrip("/")
self.timeout = timeout
self._client: Optional[httpx.AsyncClient] = None
async def __aenter__(self) -> "SkillKitClient":
self._client = httpx.AsyncClient(base_url=self.base_url, timeout=self.timeout)
return self
async def __aexit__(self, *args: object) -> None:
if self._client:
await self._client.aclose()
self._client = None
def _get_client(self) -> httpx.AsyncClient:
if self._client is None:
self._client = httpx.AsyncClient(base_url=self.base_url, timeout=self.timeout)
return self._client
async def health(self) -> HealthResponse:
client = self._get_client()
response = await client.get("/health")
response.raise_for_status()
data = response.json()
return HealthResponse(
status=data["status"],
version=data["version"],
skill_count=data.get("skillCount", 0),
uptime=data.get("uptime", 0),
)
async def search(
self,
query: str,
limit: int = 20,
include_content: bool = False,
) -> SearchResponse:
client = self._get_client()
params = {"q": query, "limit": str(limit)}
if include_content:
params["include_content"] = "true"
response = await client.get("/search", params=params)
response.raise_for_status()
data = response.json()
return SearchResponse(
skills=[Skill(**s) for s in data["skills"]],
total=data["total"],
query=data["query"],
limit=data["limit"],
)
async def search_with_filters(
self,
query: str,
limit: int = 20,
include_content: bool = False,
tags: Optional[list[str]] = None,
category: Optional[str] = None,
source: Optional[str] = None,
) -> SearchResponse:
client = self._get_client()
body: dict = {"query": query, "limit": limit, "include_content": include_content}
filters: dict = {}
if tags:
filters["tags"] = tags
if category:
filters["category"] = category
if source:
filters["source"] = source
if filters:
body["filters"] = filters
response = await client.post("/search", json=body)
response.raise_for_status()
data = response.json()
return SearchResponse(
skills=[Skill(**s) for s in data["skills"]],
total=data["total"],
query=data["query"],
limit=data["limit"],
)
async def get_skill(self, source: str, skill_id: str) -> Skill:
client = self._get_client()
parts = source.split("/", 1)
owner = quote(parts[0], safe="")
repo = quote(parts[1], safe="") if len(parts) > 1 else owner
response = await client.get(f"/skills/{owner}/{repo}/{quote(skill_id, safe='')}")
response.raise_for_status()
return Skill(**response.json())
async def trending(self, limit: int = 20) -> list[Skill]:
client = self._get_client()
response = await client.get("/trending", params={"limit": str(limit)})
response.raise_for_status()
data = response.json()
return [Skill(**s) for s in data["skills"]]
async def categories(self) -> list[Category]:
client = self._get_client()
response = await client.get("/categories")
response.raise_for_status()
data = response.json()
return [Category(**c) for c in data["categories"]]
async def cache_stats(self) -> CacheStats:
client = self._get_client()
response = await client.get("/cache/stats")
response.raise_for_status()
data = response.json()
return CacheStats(
hits=data["hits"],
misses=data["misses"],
size=data["size"],
max_size=data.get("maxSize", 0),
hit_rate=data.get("hitRate", 0.0),
)
async def close(self) -> None:
if self._client:
await self._client.aclose()
self._client = None
+51
View File
@@ -0,0 +1,51 @@
from typing import Optional
from pydantic import BaseModel
class Skill(BaseModel):
name: str
description: Optional[str] = None
source: str
repo: Optional[str] = None
tags: Optional[list[str]] = None
category: Optional[str] = None
content: Optional[str] = None
stars: Optional[int] = None
installs: Optional[int] = None
class SearchResponse(BaseModel):
skills: list[Skill]
total: int
query: str
limit: int
class HealthResponse(BaseModel):
status: str
version: str
skill_count: int = 0
uptime: int = 0
class CacheStats(BaseModel):
hits: int
misses: int
size: int
max_size: int = 0
hit_rate: float = 0.0
class Category(BaseModel):
name: str
count: int
class CategoriesResponse(BaseModel):
categories: list[Category]
total: int
class TrendingResponse(BaseModel):
skills: list[Skill]
limit: int
View File
+99
View File
@@ -0,0 +1,99 @@
import pytest
import httpx
import respx
from skillkit import SkillKitClient
BASE_URL = "http://localhost:3737"
@pytest.fixture
def mock_api():
with respx.mock(base_url=BASE_URL) as respx_mock:
yield respx_mock
@pytest.mark.asyncio
async def test_health(mock_api):
mock_api.get("/health").respond(
json={"status": "ok", "version": "1.11.0", "skillCount": 100, "uptime": 60}
)
async with SkillKitClient(BASE_URL) as client:
health = await client.health()
assert health.status == "ok"
assert health.version == "1.11.0"
assert health.skill_count == 100
@pytest.mark.asyncio
async def test_search(mock_api):
mock_api.get("/search").respond(
json={
"skills": [{"name": "react-perf", "source": "owner/repo"}],
"total": 1,
"query": "react",
"limit": 20,
}
)
async with SkillKitClient(BASE_URL) as client:
result = await client.search("react")
assert result.total == 1
assert result.skills[0].name == "react-perf"
@pytest.mark.asyncio
async def test_search_with_filters(mock_api):
mock_api.post("/search").respond(
json={
"skills": [{"name": "nextjs-auth", "source": "other/repo"}],
"total": 1,
"query": "auth",
"limit": 20,
}
)
async with SkillKitClient(BASE_URL) as client:
result = await client.search_with_filters("auth", tags=["nextjs"])
assert result.total == 1
@pytest.mark.asyncio
async def test_get_skill(mock_api):
mock_api.get("/skills/owner/repo/react-perf").respond(
json={"name": "react-perf", "description": "React performance", "source": "owner/repo"}
)
async with SkillKitClient(BASE_URL) as client:
skill = await client.get_skill("owner/repo", "react-perf")
assert skill.name == "react-perf"
@pytest.mark.asyncio
async def test_trending(mock_api):
mock_api.get("/trending").respond(
json={"skills": [{"name": "a", "source": "x/y"}], "limit": 20}
)
async with SkillKitClient(BASE_URL) as client:
trending = await client.trending()
assert len(trending) == 1
@pytest.mark.asyncio
async def test_categories(mock_api):
mock_api.get("/categories").respond(
json={"categories": [{"name": "react", "count": 5}], "total": 1}
)
async with SkillKitClient(BASE_URL) as client:
cats = await client.categories()
assert len(cats) == 1
assert cats[0].name == "react"
@pytest.mark.asyncio
async def test_cache_stats(mock_api):
mock_api.get("/cache/stats").respond(
json={"hits": 10, "misses": 5, "size": 8, "maxSize": 500, "hitRate": 0.667}
)
async with SkillKitClient(BASE_URL) as client:
stats = await client.cache_stats()
assert stats.hits == 10
assert stats.size == 8
+7
View File
@@ -0,0 +1,7 @@
node_modules/
.next/
.source/
out/
.turbo/
*.tsbuildinfo
.vercel
+2
View File
@@ -0,0 +1,2 @@
../../turbo.json
../../pnpm-workspace.yaml
+43
View File
@@ -0,0 +1,43 @@
# SkillKit Documentation
Fumadocs-based documentation for SkillKit.
## Development
```bash
cd docs/fumadocs
pnpm install
pnpm dev
```
Open [http://localhost:3000](http://localhost:3000).
## Build
```bash
pnpm build
```
## Structure
```text
docs/fumadocs/
├── content/docs/ # MDX documentation files
├── src/
│ ├── app/ # Next.js app router
│ ├── lib/ # Components and utilities
│ └── mdx-components.tsx
├── package.json
└── source.config.ts
```
## Adding Pages
1. Create `.mdx` file in `content/docs/`
2. Add frontmatter with `title` and `description`
3. Add page to `content/docs/meta.json`
## Custom Components
- `<Card>` - Link cards with icons
- `<Columns>` - Grid layout (2-4 columns)
+83
View File
@@ -0,0 +1,83 @@
---
title: Supported Agents
description: 45 AI coding agents supported by SkillKit
---
# Supported Agents
SkillKit uses an adapter pattern to support 45 AI coding platforms. Each adapter implements `getConfigPath()` and `generateConfig()` methods.
## Agent Directory Mapping
| Agent | Directory | Format |
|-------|-----------|--------|
| Claude Code | `.claude/skills/` | SKILL.md |
| Cursor | `.cursor/skills/` | .mdc |
| Codex | `.codex/skills/` | SKILL.md |
| Gemini CLI | `.gemini/skills/` | SKILL.md |
| OpenCode | `.opencode/skills/` | SKILL.md |
| GitHub Copilot | `.github/skills/` | Markdown |
| Windsurf | `.windsurf/skills/` | Markdown |
| Antigravity | `.antigravity/skills/` | SKILL.md |
| Amp | `.amp/skills/` | SKILL.md |
| Clawdbot | `.clawdbot/skills/` (alt: `skills/`) | SKILL.md |
| Droid (Factory) | `.factory/skills/` | SKILL.md |
| Goose | `.goose/skills/` | SKILL.md |
| Kilo Code | `.kilocode/skills/` | SKILL.md |
| Kiro CLI | `.kiro/skills/` | SKILL.md |
| Roo Code | `.roo/skills/` | SKILL.md |
| Trae | `.trae/skills/` | SKILL.md |
| Cline | `.cline/skills/` | SKILL.md |
| CodeBuddy | `.codebuddy/skills/` | SKILL.md |
| CommandCode | `.commandcode/skills/` | SKILL.md |
| Continue | `.continue/skills/` | SKILL.md |
| Crush | `.crush/skills/` | SKILL.md |
| Factory | `.factory/skills/` | SKILL.md |
| MCPJam | `.mcpjam/skills/` | SKILL.md |
| Mux | `.mux/skills/` | SKILL.md |
| Neovate | `.neovate/skills/` | SKILL.md |
| OpenHands | `.openhands/skills/` | SKILL.md |
| Pi | `.pi/skills/` | SKILL.md |
| Qoder | `.qoder/skills/` | SKILL.md |
| Qwen | `.qwen/skills/` | SKILL.md |
| Vercel | `.vercel/skills/` | SKILL.md |
| Zencoder | `.zencoder/skills/` | SKILL.md |
| Devin | `.devin/skills/` | Markdown |
| Aider | `.aider/skills/` | SKILL.md |
| Sourcegraph Cody | `.cody/skills/` | SKILL.md |
| Amazon Q Developer | `.amazonq/skills/` | SKILL.md |
| Augment Code | `.augment/skills/` | SKILL.md |
| Replit Agent | `.replit/skills/` | Markdown |
| Bolt | `.bolt/skills/` | Markdown |
| Lovable | `.lovable/skills/` | Markdown |
| Tabby | `.tabby/skills/` | SKILL.md |
| Tabnine | `.tabnine/skills/` | SKILL.md |
| CodeGPT | `.codegpt/skills/` | SKILL.md |
| PlayCode Agent | `.playcode/skills/` | Markdown |
| Universal | `skills/` | SKILL.md |
## Translation System
```
Universal Format (SKILL.md)
↓
Adapter Interface
↓
Agent-Specific Formats (.mdc, JSON, Markdown)
```
## Agent Commands
```bash
skillkit agent list # List installed agents
skillkit agent show <name> # Show agent details
skillkit agent translate --to cursor # Translate to format
skillkit agent sync # Sync to target agent
```
## Multi-Agent Installation
```bash
# Install for multiple agents
skillkit install anthropics/skills --agent claude-code,cursor,windsurf
```
@@ -0,0 +1,422 @@
---
title: API Reference
description: Core package API for programmatic skill management
---
# API Reference
The `@skillkit/core` package provides the foundational business logic with zero internal dependencies.
## Installation
```bash
npm install @skillkit/core
```
## Module Exports
| Entry Point | Purpose |
|-------------|---------|
| `@skillkit/core` | Main exports |
| `@skillkit/core/types` | Type definitions |
| `@skillkit/core/discovery` | Skill discovery |
| `@skillkit/core/parser` | SKILL.md parsing |
| `@skillkit/core/translator` | Format translation |
| `@skillkit/core/context` | Project context |
| `@skillkit/core/recommend` | Recommendation engine |
## Skill Discovery
```typescript
import { findAllSkills, findSkill } from '@skillkit/core/discovery'
// Find all skills in directory
const skills = await findAllSkills('./my-project')
// Find specific skill
const skill = await findSkill('react-patterns')
```
## Quality Evaluation
```typescript
import { evaluateSkillContent, getQualityGrade } from '@skillkit/core'
const score = evaluateSkillContent(skillContent)
// { total: 85, structure: 22, clarity: 25, specificity: 28, advanced: 10 }
const grade = getQualityGrade(score.total)
// 'B'
```
**Dimensions (weights out of 100):**
- Structure (25): Frontmatter, sections
- Clarity (30): Descriptions, examples
- Specificity (30): Actionable steps
- Advanced (15): Tests, versioning
## Translation
```typescript
import { translateSkill } from '@skillkit/core/translator'
const result = await translateSkill(skillContent, 'cursor')
// { content: '...', filename: 'skill.mdc' }
```
## Memory System
```typescript
import { MemoryCompressor, LearningStore } from '@skillkit/core'
// Compress observations
const compressor = new MemoryCompressor()
const learning = await compressor.compress(observations)
// Store and search
const store = new LearningStore()
await store.add(learning)
const results = await store.search('authentication')
```
## Recommendation Engine
```typescript
import { RecommendationEngine, analyzeProject } from '@skillkit/core/recommend'
const engine = new RecommendationEngine()
const profile = await analyzeProject('./my-project')
const recommendations = engine.recommend(profile)
// Recommendations with scores and reasons
recommendations.forEach(rec => {
console.log(`${rec.score}% - ${rec.skill.name}`)
console.log(`Reasons: ${rec.reasons.join(', ')}`)
})
```
## Primer (Auto-Generate Instructions)
```typescript
import { promises as fs } from 'node:fs'
import { analyzeProject, generateInstructions } from '@skillkit/core'
// Analyze project
const analysis = await analyzeProject('./my-project')
console.log(analysis.techStack)
// { framework: 'Next.js', language: 'TypeScript', styling: 'Tailwind' }
// Generate instructions for specific agents
const instructions = await generateInstructions(analysis, {
agents: ['claude', 'cursor', 'windsurf'],
includeExamples: true,
tone: 'detailed',
})
// Write to files
for (const [agent, content] of Object.entries(instructions)) {
await fs.writeFile(`.${agent}/instructions.md`, content)
}
```
## Mesh Network
```typescript
import { MeshHost, PeerIdentity } from '@skillkit/mesh'
// Generate identity
const identity = await PeerIdentity.generate()
// Create mesh host
const host = new MeshHost({
hostId: 'my-workstation',
identity,
security: { mode: 'secure' },
})
await host.start()
// Send message to peer
await host.send('peer-fingerprint', {
type: 'skill-sync',
payload: { skills: ['react-patterns'] },
})
// Listen for messages
host.on('message', (msg) => {
console.log('Received:', msg.type, 'from', msg.from)
})
```
## Inter-Agent Messaging
```typescript
import { MessagingClient } from '@skillkit/messaging'
// Create messaging client (host is a MeshHost instance from the example above)
const messaging = new MessagingClient({
meshHost: host, // See MeshHost setup in "Mesh Network" section above
storagePath: '~/.skillkit/messages',
})
await messaging.init()
// Send a message
await messaging.send({
to: 'claude@laptop',
subject: 'Code review completed',
body: 'I reviewed the auth module...',
priority: 'normal',
})
// Listen for new messages
messaging.on('message', (msg) => {
console.log('New message from:', msg.from)
console.log('Subject:', msg.subject)
})
// Get inbox
const inbox = await messaging.getInbox({ unread: true })
```
## Workflow Orchestration
```typescript
import { WorkflowEngine, WorkflowStep } from '@skillkit/core'
// Define workflow
const workflow = {
name: 'feature-development',
steps: [
{ skill: 'tdd-workflow', action: 'write-tests' },
{ skill: 'code-implementation', action: 'implement' },
{ skill: 'code-review', action: 'review' },
{ skill: 'documentation', action: 'update-docs' },
],
}
// Execute workflow
const engine = new WorkflowEngine()
const result = await engine.run(workflow)
console.log('Workflow completed:', result.status)
console.log('Steps executed:', result.steps.length)
```
## Skill Testing
```typescript
import { SkillTestRunner, SkillTest } from '@skillkit/core'
// Define test
const test: SkillTest = {
name: 'pdf-processing',
setup: async () => {
// Setup test environment
},
assertions: [
{
type: 'file_exists',
path: './output.pdf',
},
{
type: 'content_includes',
text: 'Expected content',
},
],
}
// Run test
const runner = new SkillTestRunner()
const result = await runner.run(test)
console.log('Test passed:', result.passed)
console.log('Assertions:', result.assertions)
```
## Types
```typescript
interface Skill {
name: string
description: string
path: string
content: string
metadata: SkillMetadata
enabled: boolean
agent: string
}
interface SkillMetadata {
version?: string
author?: string
tags?: string[]
dependencies?: string[]
quality?: QualityScore
}
interface QualityScore {
total: number // 0-100
structure: number // 0-25
clarity: number // 0-30
specificity: number // 0-30
advanced: number // 0-15
}
interface Recommendation {
skill: Skill
score: number
reasons: string[]
}
interface ProjectAnalysis {
techStack: {
framework?: string
language: string
styling?: string
testing?: string
packageManager: string
}
patterns: {
architecture: string
codeStyle: Record<string, any>
directory: string
}
dependencies: Record<string, string>
}
interface MeshMessage {
from: string
to: string
type: string
payload: any
timestamp: number
signature?: string
}
interface WorkflowResult {
status: 'success' | 'failure'
steps: WorkflowStepResult[]
duration: number
}
```
## Package Exports
### @skillkit/core
```typescript
export {
// Discovery
findAllSkills,
findSkill,
// Quality
evaluateSkillContent,
getQualityGrade,
// Translation
translateSkill,
// Memory
MemoryCompressor,
LearningStore,
// Recommendations
RecommendationEngine,
analyzeProject,
// Primer
generateInstructions,
// Workflows
WorkflowEngine,
// Testing
SkillTestRunner,
}
```
### @skillkit/mesh
```typescript
export {
MeshHost,
PeerIdentity,
PeerRegistry,
SecureTransport,
}
```
### @skillkit/messaging
```typescript
export {
MessagingClient,
MessageBuilder,
MessageRouter,
}
```
### @skillkit/memory
```typescript
export {
MemoryStore,
TierManager,
EmbeddingEncoder,
}
```
## Full Example: Custom Build Pipeline
```typescript
import { promises as fs } from 'node:fs'
import {
analyzeProject,
generateInstructions,
RecommendationEngine,
translateSkill,
} from '@skillkit/core'
async function setupProject() {
// 1. Analyze project
const analysis = await analyzeProject('./my-project')
// 2. Generate base instructions
const instructions = await generateInstructions(analysis, {
agents: ['claude', 'cursor', 'windsurf'],
})
// 3. Get recommendations
const engine = new RecommendationEngine()
const recommendations = engine.recommend(analysis)
// 4. Install top recommendations
const topSkills = recommendations.slice(0, 5)
for (const rec of topSkills) {
console.log(`Installing ${rec.skill.name} (${rec.score}% match)`)
}
// 5. Translate skills to all agents
for (const agent of ['claude', 'cursor', 'windsurf']) {
const translated = await translateSkill(
topSkills[0].skill.content,
agent
)
await fs.writeFile(`.${agent}/skills/${translated.filename}`, translated.content)
}
console.log('✅ Project setup complete!')
}
setupProject()
```
## Next Steps
- [Commands Reference](/docs/commands) - CLI commands
- [Memory System](/docs/memory) - Persistent learning
- [Mesh Network](/docs/mesh) - Multi-machine setup
- [Workflows](/docs/workflows) - Automation
- [Testing](/docs/testing) - Skill validation
@@ -0,0 +1,121 @@
---
title: Chrome Extension
description: Save any webpage as an AI agent skill from your browser
---
# Chrome Extension
Save any webpage as a SKILL.md directly from your browser.
## Install
1. Download the extension from the [releases page](https://github.com/rohitg00/skillkit/releases)
2. Open `chrome://extensions` in Chrome
3. Enable "Developer mode" (top right)
4. Click "Load unpacked" and select the `packages/extension/dist/` folder
Or build from source:
```bash
git clone https://github.com/rohitg00/skillkit.git
cd skillkit
pnpm install && pnpm --filter @skillkit/extension build
```
Then load `packages/extension/dist/` as an unpacked extension.
## Usage
### Popup
1. Navigate to any webpage
2. Click the SkillKit extension icon
3. Optionally enter a custom skill name
4. Click **Save as Skill**
The extension sends the page URL to the SkillKit API, which extracts the content as markdown, generates tags using weighted 5-source analysis, and returns a complete SKILL.md. The file downloads to your `Downloads/skillkit-skills/` folder.
### Context Menu
Right-click on any page:
- **Save page as Skill** — sends the URL to the API, downloads the result
- **Save selection as Skill** — builds the skill locally from selected text (no network request)
### Making Skills Available to Agents
After downloading, install the skill so all agents can use it:
```bash
skillkit install ~/Downloads/skillkit-skills/my-skill
```
Or copy directly:
```bash
cp -r ~/Downloads/skillkit-skills/my-skill ~/.skillkit/skills/
skillkit sync
```
## How It Works
```
Extension → POST /api/save-skill { url } → Server pipeline → Download
```
1. **Popup** reads the current tab's URL and title via `activeTab` permission. No content script injection needed.
2. **Background service worker** sends the URL to `skillkit.sh/api/save-skill` (or `agenstskills.com/api/save-skill`):
- Server fetches the page and converts HTML to markdown via Turndown
- GitHub URLs are auto-converted to raw content
- Tags are detected from 5 weighted sources (URL segments, headings, code blocks, keywords, language)
- Returns a complete SKILL.md with YAML frontmatter
3. **Download** — the service worker creates a blob and saves via `chrome.downloads` API.
4. **Selection saves** work entirely offline — Chrome natively provides `selectionText` via the context menu API, so the skill is built locally with no server round-trip.
## Permissions
| Permission | Why |
|-----------|-----|
| `contextMenus` | Right-click "Save as Skill" menu items |
| `activeTab` | Access current page URL and title on click |
| `downloads` | Save SKILL.md files to disk |
No `host_permissions` or `scripting` permissions needed. Only the page URL is sent to the server — no page content, browsing history, or personal data.
## Generated SKILL.md Format
```yaml
---
name: react-performance-tips
description: Optimizing React rendering with memo and useMemo
tags:
- react
- javascript
- testing
metadata:
source: https://example.com/react-performance
savedAt: 2026-02-14T09:00:00.000Z
---
# React Performance Tips
The extracted markdown content of the page...
```
## Building from Source
The extension uses tsup to bundle TypeScript into IIFE format for browser compatibility:
```bash
pnpm --filter @skillkit/extension build
```
Output goes to `packages/extension/dist/` with:
- `background.global.js` — Service worker (~4KB)
- `popup.global.js` — Popup UI logic (~2KB)
- `popup.html` + `popup.css` — Monochromatic UI
- `manifest.json` — Chrome Manifest V3
- `icons/` — 16/48/128px PNG icons
+65
View File
@@ -0,0 +1,65 @@
---
title: CI/CD
description: Integrate SkillKit into CI/CD pipelines
---
# CI/CD Integration
Generate templates for automated skill management.
## Generate Templates
```bash
skillkit cicd init --provider github
skillkit cicd init --provider gitlab
skillkit cicd init --provider circleci
```
## GitHub Actions
```yaml
name: SkillKit
on: [push, pull_request]
jobs:
validate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: '20'
- run: npm install -g skillkit
- run: skillkit validate
- run: skillkit test --json > results.json
```
## GitLab CI
```yaml
validate-skills:
image: node:20
script:
- npm install -g skillkit
- skillkit validate
- skillkit test
```
## Pre-commit
```yaml
repos:
- repo: local
hooks:
- id: skillkit-validate
name: Validate Skills
entry: skillkit validate
language: system
```
## Best Practices
- Validate on PR
- Test in CI with `--json`
- Sync only on main branch
- Cache npm packages
+621
View File
@@ -0,0 +1,621 @@
---
title: CLI Commands
description: Complete reference for all SkillKit CLI commands
---
# CLI Commands
SkillKit provides 50+ commands organized into functional categories. Built on Clipanion v4 with interactive prompts via @clack/prompts.
## Global Options
| Option | Short | Purpose |
|--------|-------|---------|
| `--help` | `-h` | Display command help |
| `--version` | `-v` | Show version info |
| `--quiet` | `-q` | Minimal output, no logo |
## Install Command
Install skills from GitHub, GitLab, Bitbucket, or local paths.
```bash
skillkit install <source> [options]
```
### Source Formats
| Format | Example |
|--------|---------|
| GitHub | `owner/repo` or full URL |
| GitLab | `gitlab:owner/repo` |
| Bitbucket | `bitbucket:owner/repo` |
| Local Path | `./path` or `~/path` |
### Install Options
| Option | Short | Type | Purpose |
|--------|-------|------|---------|
| `--skills` | `-s` | string | Comma-separated skill names |
| `--all` | `-a` | boolean | Install all discovered skills |
| `--yes` | `-y` | boolean | Skip confirmation prompts |
| `--global` | `-g` | boolean | Install to global directory |
| `--force` | `-f` | boolean | Overwrite existing skills |
| `--provider` | `-p` | string | Force provider: GitHub, GitLab, Bitbucket |
| `--list` | `-l` | boolean | List available skills without installing |
| `--agent` | — | array | Target specific agents (repeatable) |
### Examples
```bash
# Interactive installation
skillkit install anthropics/skills
# CI/CD installation (no prompts)
skillkit install anthropics/skills --skills=pdf,xlsx --agent claude --yes
# List available skills
skillkit install anthropics/skills --list
# Force overwrite
skillkit install anthropics/skills --skills=pdf --force
# Install for multiple agents
skillkit install anthropics/skills --agent claude --agent cursor
```
## Remove Command
```bash
skillkit remove <skill-names> [options]
```
| Option | Short | Purpose |
|--------|-------|---------|
| `--agent` | — | Target specific agents (default: all) |
| `--yes` | — | Skip confirmation |
| `--keep-metadata` | — | Remove skill but preserve metadata |
| `--source` | `-s` | Remove all skills installed from a specific source |
| `--all` | `-a` | Remove all installed skills |
| `--force` | `-f` | Skip confirmation prompt |
### Bulk Removal
```bash
skillkit remove --source iii-hq/iii
skillkit remove --all
skillkit remove --all --force
```
When using `--source`, SkillKit matches against the source field in each skill's metadata and removes every skill that was installed from that repository. When using `--all`, every discovered skill across all agent directories is removed. Both flags update AGENTS.md automatically if managed sections are present.
## Update Command
```bash
skillkit update [skill-names] [options]
```
| Option | Short | Purpose |
|--------|-------|---------|
| `--dry-run` | — | Check for updates without installing |
| `--yes` | — | Skip confirmation prompts |
| `--agent` | — | Update in specific agents only |
| `--force` | `-f` | Force update, bypass checksum and GitHub API checks |
The update command uses a two-stage change detection pipeline:
1. **GitHub API check** -- For remote sources, SkillKit queries the GitHub API to compare the repository's `pushed_at` timestamp against the installed metadata. If the repository has not been pushed since the last install or update, the skill is skipped without cloning.
2. **Checksum comparison** -- After cloning, a checksum of the source SKILL.md is compared against the stored checksum. If the content is identical, the update is skipped.
Use `--force` to bypass both checks and always overwrite the installed skill.
## Enable/Disable Commands
```bash
skillkit enable <skill-names> [options]
skillkit disable <skill-names> [options]
```
Disabled skills are ignored by the `sync` command. No file changes occur.
## Check Command
```bash
skillkit check [skill-names] [options]
```
Checks installed skills for available updates, quality scores, and GitHub activity.
| Option | Short | Purpose |
|--------|-------|---------|
| `--verbose` | `-v` | Show detailed output including stars and push dates |
| `--quiet` | `-q` | Minimal output |
For remote GitHub sources, the check command queries the GitHub API to compare each repository's `pushed_at` timestamp against the installed date. Each skill displays its quality score badge (A-F). In verbose mode, the output also includes the repository's star count and how recently it was pushed.
```bash
skillkit check
skillkit check pdf xlsx --verbose
```
## List Command
```bash
skillkit list [options]
```
Lists installed skills with quality grades.
## Sync Command
```bash
skillkit sync [options]
```
Synchronizes enabled skills to agent configuration files.
## Recommend Command
```bash
skillkit recommend [options]
```
AI-powered recommendations based on project analysis.
| Option | Purpose |
|--------|---------|
| `--search` | Task-based search |
| `--category` | Filter by category |
| `--min-score` | Quality threshold |
## Generate Command
AI-powered skill generation with multi-source context and agent optimization.
```bash
skillkit generate [options]
```
### Generate Options
| Option | Type | Purpose |
|--------|------|---------|
| `--provider` | string | LLM provider: anthropic, openai, google, ollama, openrouter |
| `--model` | string | Specific model (e.g., gpt-4o, gemini-2.0-flash) |
| `--compose` | string | Natural language search to find skills to compose |
| `--agents` | array | Target agents for optimization |
| `--no-memory` | boolean | Skip memory context |
| `--context-sources` | string | Comma-separated: docs,codebase,skills,memory |
### Context Sources
The wizard gathers context from 4 sources:
| Source | Description |
|--------|-------------|
| **Documentation** | Library docs via Context7 MCP |
| **Codebase** | Local project patterns and conventions |
| **Skills** | 15,000+ marketplace skills for composition |
| **Memory** | Your corrections and learned patterns |
### Examples
```bash
# Interactive wizard (recommended)
skillkit generate
# Use specific provider
skillkit generate --provider openai --model gpt-4o
# Compose from existing skills
skillkit generate --compose "testing patterns for react"
# Generate for specific agents
skillkit generate --agents claude-code,cursor
# Skip memory personalization
skillkit generate --no-memory
```
### Trust Score
Generated skills receive a trust score (0-10):
| Grade | Score | Meaning |
|-------|-------|---------|
| Trusted | 8-10 | High clarity, well-bounded |
| Review | 5-7 | May need refinement |
| Caution | 0-4 | Requires careful review |
### Agent Compatibility
The wizard shows compatibility scores for each target agent based on:
- Context length limits
- MCP/tool support
- Format requirements
## Marketplace Command
```bash
skillkit marketplace [options]
skillkit marketplace search <query>
```
Browse 15,000+ indexed skills from the aggregated catalog.
| Option | Purpose |
|--------|---------|
| `--tags` | Filter by tags |
| `--refresh` | Force refresh index |
## Manifest Commands
Team collaboration via Git-committable `.skills` file.
```bash
skillkit manifest init # Create .skills file
skillkit manifest add <source> # Add skill source
skillkit manifest install # Install from manifest
```
### Manifest File Format
```text
# GitHub skills
anthropics/skills
vercel-labs/agent-skills
# Local skills
./local-skills
# Specific versions
owner/repo@v1.2.3
```
## Memory Commands
```bash
skillkit memory status # View memory status
skillkit memory search <query> # Search learnings
skillkit memory compress # Compress observations to learnings
skillkit memory export <name> # Export learnings as skill
skillkit memory sync-claude # Update CLAUDE.md with learnings
skillkit memory index # View memory index (Layer 1)
skillkit memory --global # Use global memory
```
| Option | Purpose |
|--------|---------|
| `--global` | Use global memory instead of project |
| `--limit` | Limit number of results |
| `--tags` | Filter by tags |
## Translation Commands
```bash
skillkit translate <skill> --to <agent>
skillkit translate --all --to <agent>
skillkit translate <skill> --to <agent> --dry-run
```
## Agent Commands
```bash
skillkit agent list # List agents
skillkit agent show <name> # Show details
skillkit agent create <name> # Create agent
skillkit agent translate --source ./path --to cursor
skillkit agent translate --source ./path --to cursor --recursive
skillkit agent sync # Sync to target
skillkit agent validate # Validate definitions
```
## Context Commands
```bash
skillkit context init # Initialize project context
skillkit context sync # Sync context to agents
```
## Test Command
```bash
skillkit test [path] # Run skill tests
skillkit test --tags unit # Filter by tags
skillkit test --json # JSON output for CI
```
## Workflow Commands
```bash
skillkit workflow list # List workflows
skillkit workflow run <name> # Execute workflow
skillkit workflow create <name> # Create workflow
```
## CI/CD Commands
```bash
skillkit cicd github-action # Generate GitHub Actions
skillkit cicd gitlab-ci # Generate GitLab CI
skillkit cicd pre-commit # Generate pre-commit hooks
```
## Serve Command
Start the SkillKit REST API server for runtime skill discovery.
```bash
skillkit serve [options]
```
| Option | Short | Default | Description |
|--------|-------|---------|-------------|
| `--port` | `-p` | `3737` | Port to listen on |
| `--host` | `-H` | `0.0.0.0` | Host to bind to |
| `--cors` | — | `*` | CORS allowed origin |
| `--cache-ttl` | — | `86400000` | Cache TTL in milliseconds |
### Examples
```bash
# Start with defaults
skillkit serve
# Custom port and host
skillkit serve --port 8080 --host localhost
# Restricted CORS
skillkit serve --cors "http://localhost:3000"
# Short cache TTL (1 hour)
skillkit serve --cache-ttl 3600000
```
### Endpoints
| Method | Path | Description |
|--------|------|-------------|
| GET | `/search?q=...` | Search skills |
| POST | `/search` | Search with filters |
| GET | `/skills/:owner/:repo/:id` | Get specific skill |
| GET | `/trending?limit=20` | Trending skills |
| GET | `/categories` | Skill categories |
| GET | `/health` | Server health |
| GET | `/cache/stats` | Cache statistics |
## Issue Planner
Generate structured plans from GitHub Issues. Requires the `gh` CLI.
```bash
skillkit issue plan "#42" # Plan from current repo
skillkit issue plan rohitg00/skillkit#42 # Cross-repo
skillkit issue plan "#42" --agent cursor # Target specific agent
skillkit issue plan "#42" --no-tests # Skip test steps
skillkit issue plan "#42" --json # JSON output
skillkit issue plan "#42" --tech-stack react,ts # Override tech stack
```
### Issue Plan Options
| Option | Short | Default | Purpose |
|--------|-------|---------|---------|
| `--agent` | `-a` | `claude-code` | Target agent |
| `--output` | `-o` | `.skillkit/plans/issue-<n>.md` | Output file path |
| `--no-tests` | — | `false` | Skip test steps |
| `--json` | — | `false` | Output as JSON |
| `--tech-stack` | — | — | Comma-separated tech stack |
### Issue List
```bash
skillkit issue list # List open issues
skillkit issue list --repo owner/repo # Specific repo
skillkit issue list --label bug # Filter by label
skillkit issue list --limit 20 # More results
skillkit issue list --json # JSON output
```
The planner extracts task lists (checkboxes) from the issue body, infers file mentions from backtick-quoted paths, and maps labels to tags (e.g., `bug` → `fix`, `enhancement` → `feature`). Generated plans work with `skillkit plan validate` and `skillkit plan execute`.
## Session Intelligence
Track skill executions, generate handoff documents, and analyze skill impact.
### Timeline
View a unified chronological event stream of all session activity.
```bash
skillkit timeline # Last 50 events
skillkit timeline --type git_commit # Filter by event type
skillkit timeline --skill code-simplifier # Filter by skill
skillkit timeline --since 2026-02-10 # Date filter
skillkit timeline --limit 20 --json # JSON output
```
| Option | Short | Purpose |
|--------|-------|---------|
| `--type` | `-t` | Filter: skill_start, skill_complete, task_progress, git_commit, observation, decision, snapshot |
| `--skill` | `-s` | Filter events by skill name |
| `--since` | — | Show events since date (YYYY-MM-DD) |
| `--limit` | `-l` | Max events (default: 50) |
| `--json` | `-j` | JSON output |
### Session Handoff
Generate a structured context document for agent switching.
```bash
skillkit session handoff # Print markdown to stdout
skillkit session handoff --to cursor # Target agent recommendations
skillkit session handoff --out handoff.md # Save to file
skillkit session handoff --json # JSON output
```
| Option | Short | Purpose |
|--------|-------|---------|
| `--to` | — | Target agent for recommendations |
| `--out` | `-o` | Save to file path |
| `--json` | `-j` | JSON output |
### Lineage
Show which skills produced which code changes with aggregate impact stats.
```bash
skillkit lineage # Full overview
skillkit lineage --skill code-simplifier # Single skill
skillkit lineage --file src/index.ts # Single file
skillkit lineage --since 2026-02-01 --json # Date filter + JSON
```
| Option | Short | Purpose |
|--------|-------|---------|
| `--skill` | `-s` | Filter by skill name |
| `--file` | `-f` | Filter by file path |
| `--since` | — | Show lineage since date |
| `--limit` | `-l` | Max entries |
| `--json` | `-j` | JSON output |
## Utility Commands
```bash
skillkit init # Initialize project
skillkit create <name> # Create new skill
skillkit validate [path] # Validate skill format
skillkit read <skills> # Read skill content
skillkit settings --set key=value # Configure settings
```
## Publishing Commands
```bash
skillkit publish [path] # Generate well-known hosting structure
skillkit publish --output dir # Output to specific directory
skillkit publish --dry-run # Preview without writing
skillkit publish submit # Submit to SkillKit marketplace
```
### publish submit
Submits a skill to the SkillKit marketplace by creating a GitHub issue on `rohitg00/skillkit` via the `gh` CLI. No browser is needed.
Before submitting, the command displays:
- Quality score and grade (A-F) from the skill evaluator
- GitHub star count and last push date from the GitHub API
- Any quality warnings (up to 3)
If `gh` is not installed or not authenticated, the command prints a manual submission URL as a fallback.
## Tap Command
Manage custom skill sources (taps). Taps are user-level source repositories stored in `~/.skillkit/taps.json`. They let you add private or third-party skill repositories that are not part of the official marketplace.
### tap add
Add a custom skill source.
```bash
skillkit tap add owner/repo
skillkit tap add owner/repo --name "My Skills"
```
### tap remove
Remove a custom skill source.
```bash
skillkit tap remove owner/repo
```
### tap list
List all custom skill sources.
```bash
skillkit tap list
```
Once a tap is added, skills from that source appear in `skillkit marketplace search` results and can be installed with the standard `skillkit install owner/repo` workflow.
## Security Scanning
```bash
skillkit scan <path> # Scan skill for vulnerabilities
skillkit scan <path> --format json # Output as JSON
skillkit scan <path> --format table # Tabular output
skillkit scan <path> --format sarif # SARIF for GitHub Code Scanning
skillkit scan <path> --fail-on high # Exit 1 if HIGH+ findings
skillkit scan <path> --skip-rules UC001 # Skip specific rules
```
**Threat Categories:**
| Category | Description |
|----------|-------------|
| Prompt Injection | Override/bypass agent instructions |
| Command Injection | eval(), exec(), shell commands |
| Data Exfiltration | Webhook URLs, env var reads, credential access |
| Tool Abuse | Tool shadowing, autonomy escalation |
| Hardcoded Secrets | API keys, tokens, private keys |
| Unicode Steganography | Zero-width chars, bidi overrides |
**Install Integration:**
Skills are automatically scanned during `skillkit install`. Use `--no-scan` to skip, or `--force` to install despite findings.
**Output Formats:**
- `summary` (default) - colored terminal output
- `json` - machine-readable JSON
- `table` - tabular format
- `sarif` - SARIF v2.1 for GitHub Code Scanning / IDE integration
## Interactive TUI
```bash
skillkit ui # Launch terminal UI
skillkit # Same as above
```
**Navigation Keys:**
| Key | Action |
|-----|--------|
| `h` | Home |
| `b` | Browse |
| `m` | Marketplace |
| `r` | Recommend |
| `t` | Translate |
| `c` | Context |
| `i` | Installed |
| `s` | Sync |
| `/` | Help |
| `q` | Quit |
## Exit Codes
| Code | Meaning |
|------|---------|
| 0 | Success |
| 1 | General error |
| 2 | Invalid arguments |
| 3 | Configuration issue |
| 4 | Network problem |
| 5 | Filesystem error |
## Quality Grades
Skills receive automatic quality scores mapped to grades:
| Grade | Score Range |
|-------|-------------|
| A | 90-100 |
| B | 80-89 |
| C | 70-79 |
| D | 60-69 |
| F | Below 60 |
Skills with score below 60 trigger warning displays before installation.
@@ -0,0 +1,267 @@
---
title: Configuration
description: Configure SkillKit at project and user levels
---
# Configuration
SkillKit uses a layered configuration system with five priority levels (lowest to highest):
1. Default values in code
2. Global user preferences (`~/.skillkit/preferences.json`)
3. Project settings (`skillkit.yaml`)
4. Environment variables
5. CLI flags
## Project Configuration
Create `skillkit.yaml` in your project root:
```yaml
version: 1
agent: cursor # Override auto-detection
autoSync: true # Sync on changes
enabledSkills:
- pdf
- xlsx
- react-patterns
disabledSkills:
- deprecated-skill
skillsDir: ./custom-skills # Custom directory
sources: # Default sources
- anthropics/skills
- vercel-labs/agent-skills
```
## Manifest File
The `.skills` file enables Git-based team sharing:
```yaml
version: 1
skills:
- source: anthropics/skills
skills: [pdf, xlsx]
- source: vercel-labs/agent-skills
skills: [react-patterns]
```
Commands:
```bash
skillkit manifest init # Create .skills
skillkit manifest add <skill> # Add skill
skillkit manifest install # Install all
```
## User Preferences
Global preferences in `~/.skillkit/preferences.json`:
```json
{
"lastAgents": ["claude-code", "cursor"],
"defaultAgent": "claude-code",
"theme": "dark"
}
```
## Environment Variables
| Variable | Purpose |
|----------|---------|
| `SKILLKIT_AGENT` | Override default agent |
| `SKILLKIT_DIR` | Custom SkillKit directory |
| `SKILLKIT_DEBUG` | Enable debug logging |
## CLI Settings
```bash
skillkit settings --set agent=cursor
skillkit settings --set autoSync=true
skillkit settings --get agent
```
## Advanced Configuration
### Memory System
```yaml
# skillkit.yaml
memory:
enabled: true
tier: personal # personal, project, global
compression:
minObservations: 10 # Compress after N observations
autoExport: true # Auto-export as skills
storage:
backend: cozodb # cozodb, sqlite, memory
path: ~/.skillkit/memory
```
### Mesh Network
```yaml
# skillkit.yaml
mesh:
enabled: true
hostId: my-workstation
discovery:
method: local # local, tailscale, manual
port: 9876
security:
mode: secure # development, signed, secure, strict
keyPath: ~/.skillkit/mesh/keys
peers:
- id: laptop-dev
address: 192.168.1.100
trusted: true
```
### Messaging
```yaml
# skillkit.yaml
messaging:
enabled: true
storagePath: ~/.skillkit/messages
notifications: true
autoArchive:
enabled: true
afterDays: 30
```
### Primer
```yaml
# skillkit.yaml
primer:
autoGenerate: true # Generate on changes
agents:
priority: [claude, cursor, windsurf]
customize:
tone: detailed # concise, detailed, technical
includeExamples: true
exclude:
- node_modules
- dist
- .next
```
## Lock File
SkillKit maintains a centralized lock file at `~/.skillkit/lock.json` that tracks every installed skill. The lock file is written on install, updated on update, and cleaned on remove.
```json
{
"version": 1,
"skills": {
"pdf": {
"source": "anthropics/skills",
"checksum": "sha256:abc123...",
"agents": ["claude-code", "cursor"],
"installedAt": "2026-04-01T12:00:00Z",
"updatedAt": "2026-04-08T09:30:00Z"
}
}
}
```
| Field | Description |
|-------|-------------|
| `source` | The repository or local path the skill was installed from |
| `checksum` | SHA-256 hash of the SKILL.md content at install time, used for update detection |
| `agents` | Which agents the skill is installed for |
| `installedAt` | ISO timestamp of initial installation |
| `updatedAt` | ISO timestamp of the most recent update |
The `update` command compares the stored checksum against the source to skip unchanged skills. The `remove` command cleans up the corresponding lock entry.
## Taps File
Custom skill source repositories are stored in `~/.skillkit/taps.json`. Taps are managed via the `skillkit tap` commands.
```json
{
"version": 1,
"taps": [
{
"source": "myorg/internal-skills",
"name": "Internal Skills",
"addedAt": "2026-04-05T10:00:00Z"
}
]
}
```
Skills from tapped sources appear in marketplace search results and can be installed like any other source. See the [tap command](/docs/commands#tap-command) documentation for usage.
## Directory Structure
```
~/.skillkit/
├── preferences.json # User preferences
├── lock.json # Installed skill tracking
├── taps.json # Custom skill sources
├── cache/ # Marketplace cache
├── memory/ # Learning storage
│ ├── observations/
│ ├── learnings/
│ └── index.json
├── mesh/ # Mesh network
│ ├── keys/ # Encryption keys
│ ├── peers.json # Known peers
│ └── config.json
└── messages/ # Inter-agent messages
├── inbox/
├── sent/
└── archived/
./project/
├── skillkit.yaml # Project config
├── .skills # Team manifest
├── skills/ # Local skills
└── .skillkit/ # Project-specific
├── cache/
├── primer-config.json
└── memory/
```
## Configuration Profiles
Create different profiles for different environments:
```yaml
# skillkit.yaml
profiles:
development:
agent: claude
autoSync: true
mesh:
security:
mode: development
production:
agent: universal
autoSync: false
mesh:
security:
mode: strict
```
Use profiles:
```bash
skillkit --profile production sync
```
## Next Steps
- [Primer](/docs/primer) - Auto-generate instructions
- [Memory System](/docs/memory) - Persistent learning
- [Mesh Network](/docs/mesh) - Multi-machine setup
- [Team Collaboration](/docs/teams) - Team configuration
@@ -0,0 +1,68 @@
---
title: Contributing
description: Contribute to SkillKit development
---
# Contributing
## Setup
```bash
git clone https://github.com/rohitg00/skillkit.git
cd skillkit
pnpm install
pnpm build
pnpm test
```
## Requirements
- Node.js 18+
- pnpm 8+
- Bun 1.2+ (TUI)
## Project Structure
```
skillkit/
├── packages/
│ ├── core/ # Business logic
│ ├── cli/ # CLI
│ ├── tui/ # Terminal UI
│ └── agents/ # 45 adapters
├── marketplace/ # Skills data
│ ├── skills.json
│ └── sources.json
└── docs/
```
## Development
```bash
git checkout -b feat/my-feature
pnpm test
pnpm lint
pnpm build
```
## Code Style
- ES modules
- `function` keyword
- Explicit return types
- No unnecessary comments
- No nested ternaries
## Commits
```
feat: add feature
fix: resolve bug
docs: update docs
test: add tests
```
## Links
- [GitHub Issues](https://github.com/rohitg00/skillkit/issues)
- [GitHub Discussions](https://github.com/rohitg00/skillkit/discussions)
@@ -0,0 +1,59 @@
---
title: Custom Agents
description: Create custom AI sub-agent definitions
---
# Custom Agents
Create and manage custom AI sub-agents.
## Commands
```bash
skillkit agent list # List agents
skillkit agent show <name> # Show details
skillkit agent create <name> # Create agent
skillkit agent translate # Translate format
skillkit agent sync # Sync to target
skillkit agent validate # Validate
```
## Agent Definition
```yaml
name: my-agent
description: Custom agent for tasks
format: skill.md
skillsDir: .my-agent/skills/
capabilities:
- code-generation
- code-review
triggers:
- pattern: "create component"
action: generate-component
```
## Structure
```
.my-agent/
├── agent.yaml # Definition
├── skills/ # Agent skills
└── config/ # Settings
```
## Translation
```bash
skillkit agent translate --source ./my-agent --to cursor
skillkit agent translate --source ./agents --to cursor --recursive
```
## Validation
```bash
skillkit agent validate
skillkit agent validate ./my-agent
```
+178
View File
@@ -0,0 +1,178 @@
---
title: SkillKit
description: Universal skill management for AI coding agents
---
# SkillKit
Skills make AI coding agents smarter. But every agent uses a different format — Claude Code wants `.claude/skills/`, Cursor uses `.mdc`, Copilot expects `.github/skills/`. You end up rewriting the same skill three times, or locking into one platform.
SkillKit fixes this. Write a skill once, deploy it to all 45 agents.
## Get Started
```bash
npx skillkit@latest
```
That's it. No global install needed. Or if you prefer:
```bash
npm install -g skillkit
skillkit init
skillkit install anthropics/skills
skillkit sync
```
Four commands. Your agents now have skills for PDF processing, code review, and more.
## What Can You Do?
### Install skills from anywhere
```bash
skillkit install anthropics/skills # GitHub
skillkit install skills.sh/owner/repo/skill # skills.sh registry
skillkit install gitlab:team/skills # GitLab
skillkit install ./my-local-skills # Local
```
### Translate between agents
Write for Claude, deploy to Cursor:
```bash
skillkit translate my-skill --to cursor
skillkit translate --all --to windsurf # All skills at once
```
### Get smart recommendations
SkillKit reads your `package.json`, detects your stack, and suggests relevant skills:
```bash
skillkit recommend
# 92% vercel-react-best-practices
# 87% tailwind-v4-patterns
# 85% nextjs-app-router
```
### Discover skills at runtime
Start an API server and let agents find skills on demand:
```bash
skillkit serve
# Server running at http://localhost:3737
```
```bash
curl "http://localhost:3737/search?q=react+performance"
```
Or use MCP for native agent integration:
```json
{
"mcpServers": {
"skillkit": { "command": "npx", "args": ["@skillkit/mcp"] }
}
}
```
[REST API](/docs/rest-api) | [MCP Server](/docs/mcp-server) | [Python Client](/docs/python-client)
## How It Works
SkillKit sits between your skills and your agents. It handles format translation, discovery, and synchronization automatically.
| Layer | What It Does |
|-------|-------------|
| **CLI + TUI** | Install, translate, recommend, sync |
| **APIs** | REST server on :3737, MCP via stdio |
| **Core** | Translation engine, relevance ranker, skill parser |
| **Data** | 15,000+ skills from 31 curated sources |
## Supported Agents
45 agents and counting:
**Claude Code** | **Cursor** | **Codex** | **Gemini CLI** | **OpenCode** | **GitHub Copilot** | **Windsurf** | Amp | Antigravity | Clawdbot | Cline | CodeBuddy | CommandCode | Continue | Crush | Droid | Factory | Goose | Kilo Code | Kiro CLI | MCPJam | Mux | Neovate | OpenHands | Pi | Qoder | Qwen | Roo Code | Trae | Vercel | Zencoder | Universal
[Full agent details](/docs/agents)
### Security scanning
Every skill is scanned for threats before installation — prompt injection, hardcoded secrets, command injection, and more:
```bash
skillkit scan ./my-skill # 46+ detection rules
skillkit scan ./my-skill --format sarif # GitHub Code Scanning
skillkit scan ./my-skill --fail-on high # CI gate
```
[Security Scanner](/docs/security)
## Beyond Basic Skills
### Session Memory
Your AI agents learn patterns during sessions, then forget everything. SkillKit captures those learnings and makes them permanent.
```bash
skillkit memory compress
skillkit memory search "auth patterns"
skillkit memory export auth-patterns
```
### Session Intelligence
Track skill executions, generate handoff documents for agent switching, and view skill impact lineage:
```bash
skillkit timeline # Unified event stream
skillkit session handoff # Agent-to-agent context
skillkit lineage # Skill impact graph
```
### Primer
Auto-generate CLAUDE.md, .cursorrules, and agent instructions by analyzing your codebase:
```bash
skillkit primer --all-agents
```
### Mesh Network
Distribute agents across machines with encrypted P2P:
```bash
skillkit mesh init
skillkit mesh discover
```
### Team Collaboration
Share skills via a Git-committable `.skills` manifest:
```bash
skillkit manifest init
skillkit manifest add anthropics/skills
git commit -m "add team skills"
```
Team members run `skillkit manifest install` and they're in sync.
## Next Steps
- [Installation](/docs/installation) — Install and configure
- [Quick Start](/docs/quickstart) — First project setup
- [Methodology Packs](/docs/methodology) — Debugging, testing, planning skills
- [Security Scanner](/docs/security) — Threat detection for skills
- [Commands](/docs/commands) — Full CLI reference
- [REST API](/docs/rest-api) — Runtime discovery server
- [MCP Server](/docs/mcp-server) — Agent-native discovery
- [Python Client](/docs/python-client) — Python SDK
**Current version:** v1.19.2 | [npm](https://www.npmjs.com/package/skillkit) | [GitHub](https://github.com/rohitg00/skillkit) | Apache-2.0
+141
View File
@@ -0,0 +1,141 @@
---
title: Installation
description: Install SkillKit and set up your first project
---
# Installation
## No install needed
The fastest way to start:
```bash
npx skillkit@latest
```
This runs the latest version directly. No global install, no setup.
## Global install
For frequent use, install globally:
```bash
npm install -g skillkit
```
Also works with pnpm, yarn, or bun:
```bash
pnpm add -g skillkit
yarn global add skillkit
bun add -g skillkit
```
Both `skillkit` and `sk` work as command aliases.
## Full vs slim install
SkillKit ships four power features as **optional dependencies** so the
core install stays small. The default `npm install -g skillkit` installs
every feature; `--omit=optional` installs only the core CLI.
| Feature | Package | Command |
| ------------------------ | -------------------- | ------------------------------ |
| Interactive terminal UI | `@skillkit/tui` | `skillkit ui` / `skillkit tui` |
| REST/OpenAPI server | `@skillkit/api` | `skillkit serve` |
| Peer mesh networking | `@skillkit/mesh` | `skillkit mesh …` |
| Inter-agent messaging | `@skillkit/messaging`| `skillkit message …` |
```bash
# Full (default) — every feature works out of the box:
npm install -g skillkit
# Slim — core commands only, ~75% smaller, no native addons, 0 deprecation warnings:
npm install -g skillkit --omit=optional
```
Add one later:
```bash
npm install -g @skillkit/tui # enables: skillkit ui
npm install -g @skillkit/api # enables: skillkit serve
npm install -g @skillkit/mesh # enables: skillkit mesh
npm install -g @skillkit/messaging # enables: skillkit message
```
The CLI catches a missing optional feature and prints a one-line hint,
so you'll never see an unhandled stack trace.
## Using `npx`
`npx skillkit add <owner/repo>` runs without a global install. First run
downloads into the npx cache (`~/.npm/_npx/`); every call after that is
instant until the cache expires or a new version ships.
```bash
# Full — every feature works:
npx skillkit add anthropics/skills
# Slim — core commands only, 75% fewer packages, 0 warnings:
npx --omit=optional skillkit add anthropics/skills
```
If you use `npx skillkit` more than a couple of times, install globally
to skip the prompt-to-proceed and avoid the per-release cache refetch:
```bash
npm install -g skillkit --omit=optional
skillkit add anthropics/skills
```
## Verify
```bash
skillkit --version
```
**Requirements:** Node.js 18+ (Bun 1.2+ for the TUI).
## Initialize a project
```bash
cd my-project
skillkit init
```
The init command:
1. **Detects your AI agent** — scans for `.claude/`, `.cursor/`, `.github/` directories
2. **Creates the skills folder** — sets up the right directory for your agent
3. **Saves preferences** — remembers your choices for next time
### Specify an agent directly
```bash
skillkit init --agent cursor
skillkit init --list # Show all 45 supported agents
skillkit init --quiet # Skip logo and prompts (for CI)
```
### What gets created
| Agent | Skills Directory | Config |
|-------|-----------------|--------|
| Claude Code | `.claude/skills/` | `.claude/config.json` |
| Cursor | `.cursor/skills/` | `.cursor/config.mdc` |
| Codex | `.codex/skills/` | `AGENTS.md` |
| GitHub Copilot | `.github/skills/` | — |
| Universal | `skills/` | `AGENTS.md` |
Preferences are stored in `~/.skillkit/preferences.json`.
## Next steps
```bash
skillkit recommend # Get skill suggestions for your project
skillkit install anthropics/skills # Install skills from GitHub
skillkit sync # Deploy to your agent
skillkit ui # Launch the terminal UI
```
[Quick Start guide](/docs/quickstart) | [Full command reference](/docs/commands)
@@ -0,0 +1,86 @@
---
title: Marketplace
description: Browse and install from 15,000+ curated skills
---
# Marketplace
The SkillKit marketplace indexes 15,000+ skills from curated sources.
## Browse
```bash
skillkit marketplace
```
## Search
```bash
skillkit marketplace search "react hooks"
```
## Filter by Tags
```bash
skillkit marketplace --tags typescript,testing
```
## Refresh Index
```bash
skillkit marketplace refresh
```
## Popular Sources
| Repository | Description |
|------------|-------------|
| [anthropics/skills](https://github.com/anthropics/skills) | PDF, XLSX, DOCX processing |
| [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | React/Next.js best practices |
## Install from Marketplace
```bash
skillkit install anthropics/skills
skillkit install anthropics/skills --skills pdf,xlsx
skillkit install anthropics/skills --agent claude-code,cursor
```
## Publish Skills
### Self-Host on Your Domain (Recommended)
Generate a well-known URI structure (RFC 8615) to host skills on your own domain:
```bash
# Create and validate your skill
skillkit create my-skill
skillkit validate my-skill
# Generate hosting structure
skillkit publish ./my-skill --output ./public
```
This creates:
```
.well-known/skills/
index.json # Skill manifest for auto-discovery
my-skill/
SKILL.md # Your skill content
```
Deploy the `.well-known` folder to your web server. Users can then install via:
```bash
skillkit add https://your-domain.com
```
### Submit to SkillKit Marketplace
To submit your skill for inclusion in the central marketplace:
```bash
skillkit publish submit
```
This opens a GitHub issue for review by maintainers.
+105
View File
@@ -0,0 +1,105 @@
---
title: MCP Server
description: Agent-native skill discovery via Model Context Protocol
---
# MCP Server
The REST API works great for HTTP clients. But AI agents speak MCP — the Model Context Protocol. The `@skillkit/mcp` package lets agents discover skills natively, without HTTP calls or curl commands.
Think of it as giving your agent a direct line to the entire skill catalog.
## Setup
### Claude Desktop
Add this to `~/Library/Application Support/Claude/claude_desktop_config.json`:
```json
{
"mcpServers": {
"skillkit": {
"command": "npx",
"args": ["@skillkit/mcp"]
}
}
}
```
Restart Claude Desktop. Done.
### Cursor
Add to `.cursor/mcp.json` in your project:
```json
{
"mcpServers": {
"skillkit": {
"command": "npx",
"args": ["@skillkit/mcp"]
}
}
}
```
### Any MCP client
The server uses stdio transport. Works with any MCP-compatible client:
```bash
npx @skillkit/mcp
```
## What your agent can do
Once connected, your agent gets four tools:
### Search skills
Ask your agent: *"Find skills for React performance optimization"*
Behind the scenes, it calls `search_skills` with your query and returns ranked results. You can filter by tags, category, or source repository.
```
> Search for authentication skills tagged with "security"
```
The agent searches across the full catalog, ranks results by relevance, and shows you the best matches.
### Get a specific skill
Ask: *"Get the pdf-processing skill from anthropics/skills"*
The agent calls `get_skill` and returns the full skill details — description, tags, content, and references.
### Get recommendations
Ask: *"What skills would you recommend for my TypeScript React project?"*
The agent calls `recommend_skills` with your stack context (languages, frameworks, libraries) and returns personalized suggestions ranked by relevance.
### Browse categories
Ask: *"What skill categories are available?"*
The agent calls `list_categories` and returns all categories with counts, so you know what's out there.
## Resources
The server also exposes two read-only resources:
- **`skills://trending`** — Top 20 skills by relevance score
- **`skills://categories`** — All categories with counts
Agents can read these without making a tool call.
## How it works
1. On startup, the server loads all skills from the marketplace catalog
2. Your agent sends a natural language request
3. The MCP client translates it into a tool call
4. The `RelevanceRanker` scores and ranks results (same algorithm as the REST API)
5. Results come back as structured JSON through the MCP protocol
Same ranking, same data, same quality — just native to your agent instead of going through HTTP.
+179
View File
@@ -0,0 +1,179 @@
---
title: Memory System
description: Persistent learning across AI agent sessions
---
# Memory System
Capture learnings from AI sessions and convert them into reusable skills. SkillKit's memory system provides automatic observation capture, intelligent compression, and token-optimized retrieval.
## Commands
```bash
skillkit memory status # View status
skillkit memory search <q> # Search learnings
skillkit memory compress # Compress observations to learnings
skillkit memory export <name> # Export as skill
skillkit memory sync-claude # Update CLAUDE.md with learnings
skillkit memory index # View memory index (Layer 1)
skillkit memory --global # Global memory operations
```
## How It Works
### Observation → Learning Pipeline
1. **Observations** - Track patterns during sessions (tool use, errors, solutions)
2. **Compression** - Distill observations into reusable learnings
3. **Injection** - Load relevant learnings into new sessions
4. **Export** - Convert to shareable skills
### Lifecycle Hooks
SkillKit integrates with Claude Code's lifecycle hooks for automatic memory capture:
| Hook | Trigger | Action |
|------|---------|--------|
| **SessionStart** | Session begins | Inject relevant learnings |
| **PostToolUse** | Tool completes | Capture outcomes as observations |
| **SessionEnd** | Session closes | Compress observations to learnings |
### Progressive Disclosure (Token Optimization)
Memory retrieval uses a 3-layer system to minimize token usage:
| Layer | Content | ~Tokens |
|-------|---------|---------|
| **Index** | Titles, tags, timestamps | 50-100 |
| **Timeline** | Context, excerpts, activity | ~200 |
| **Details** | Full content, metadata | 500-1000 |
The system starts with Layer 1 and progressively fetches deeper layers based on relevance and token budget.
## Storage
```
~/.skillkit/memory/
├── observations/ # Raw session data
├── learnings/ # Compressed knowledge
└── index.json # Memory index
<project>/.skillkit/memory/
├── observations/ # Project-specific observations
├── learnings/ # Project learnings
└── index.json # Project memory index
```
## Auto-CLAUDE.md Updates
Sync your most effective learnings to CLAUDE.md:
```bash
skillkit memory sync-claude
```
This populates the `## LEARNED` section with high-effectiveness insights, giving your agent persistent context across sessions.
## Programmatic API
### Memory Compression
```typescript
import { MemoryCompressor, LearningStore } from '@skillkit/core'
const compressor = new MemoryCompressor(projectPath)
const { learnings } = await compressor.compress(observations)
const store = new LearningStore('project', projectPath)
await store.add(learning)
const results = await store.search('authentication')
```
### Lifecycle Hooks
```typescript
import { MemoryHookManager } from '@skillkit/core'
const manager = new MemoryHookManager(projectPath)
// Session start - inject relevant learnings
const startResult = await manager.onSessionStart()
// After tool use - capture outcomes
await manager.onToolUse({
tool_name: 'Write',
tool_input: { file_path: '/src/auth.ts' },
tool_result: 'File written successfully',
duration_ms: 150
})
// Session end - compress to learnings
const endResult = await manager.onSessionEnd()
```
### Progressive Disclosure
```typescript
import { ProgressiveDisclosureManager } from '@skillkit/core'
const pdm = new ProgressiveDisclosureManager(projectPath)
// Layer 1: Index (~50 tokens each)
const index = pdm.getIndex({ includeGlobal: true })
// Layer 2: Timeline (~200 tokens each)
const timeline = pdm.getTimeline(['id1', 'id2'])
// Layer 3: Full details (~600 tokens each)
const details = pdm.getDetails(['id1'])
// Smart retrieval with token budget
const result = pdm.smartRetrieve('authentication patterns', 2000)
// Returns optimal layer based on budget
```
### CLAUDE.md Updater
```typescript
import { ClaudeMdUpdater } from '@skillkit/core'
const updater = new ClaudeMdUpdater(projectPath)
// Preview what would be updated
const preview = updater.preview({ minEffectiveness: 70 })
// Update CLAUDE.md
const result = updater.update({
minEffectiveness: 60,
maxLearnings: 20,
preserveManualEntries: true
})
```
## Configuration
Configure memory behavior in `.skillkit/config.json`:
```json
{
"memory": {
"enabled": true,
"autoInjectOnSessionStart": true,
"autoCaptureToolUse": true,
"autoCompressOnSessionEnd": true,
"minRelevanceForCapture": 30,
"maxTokensForInjection": 2000,
"compressionThreshold": 50
}
}
```
## Claude Code Integration
Generate hooks configuration for Claude Code:
```typescript
const manager = new MemoryHookManager(projectPath)
const config = manager.generateClaudeCodeHooksConfig()
// Outputs hooks.json format for Claude Code integration
```
+118
View File
@@ -0,0 +1,118 @@
---
title: Mesh Network
description: Multi-machine agent distribution with secure peer-to-peer communication
---
# Mesh Network
SkillKit's mesh network enables secure communication between AI agents across multiple machines. Share skills, synchronize memory, and collaborate across your development environment.
## Quick Start
```bash
# Initialize mesh on your machine
npx skillkit mesh init
# Discover other hosts on your LAN
npx skillkit mesh discover
# Add a specific host
npx skillkit mesh add 192.168.1.100
```
## Security
The mesh network uses enterprise-grade security:
- **Ed25519** - Peer identity and message signing
- **XChaCha20-Poly1305** - End-to-end message encryption
- **TLS 1.3** - Transport layer security
- **JWT with EdDSA** - Authentication tokens
### Initialize Security
```bash
# Generate encryption keys
npx skillkit mesh security init
# Check security status
npx skillkit mesh security status
```
### Peer Trust Management
```bash
# Trust a peer by fingerprint
npx skillkit mesh peer trust abc123def456
# Revoke a peer's trust
npx skillkit mesh peer revoke abc123def456
# List trusted peers
npx skillkit mesh peer list
```
## Commands Reference
| Command | Description |
|---------|-------------|
| `mesh init` | Initialize mesh network |
| `mesh add <address>` | Add a host to mesh |
| `mesh remove <id>` | Remove a host |
| `mesh list` | List known hosts |
| `mesh discover` | Discover hosts on LAN |
| `mesh health` | Check host health |
| `mesh status` | Show mesh status |
| `mesh security init` | Setup encryption keys |
| `mesh security status` | Show security status |
| `mesh peer trust <id>` | Trust a peer |
| `mesh peer revoke <id>` | Revoke peer trust |
| `mesh peer list` | List trusted peers |
## Security Levels
| Level | Discovery | Transport | Auth | Use Case |
|-------|-----------|-----------|------|----------|
| `development` | open | none | none | Local dev |
| `signed` | signed | optional | optional | Trusted LAN |
| `secure` (default) | signed | required | required | Production |
| `strict` | trusted-only | required | mTLS | High security |
## Architecture
The mesh network uses:
1. **UDP Multicast** - LAN discovery with signed announcements
2. **WebSocket (WSS)** - Real-time bidirectional communication
3. **HTTPS** - RESTful API for management
All messages are signed and optionally encrypted based on your security level.
## Programmatic API
```typescript
import { MeshHost, PeerIdentity } from '@skillkit/mesh';
// Generate identity
const identity = await PeerIdentity.generate();
// Create mesh host
const host = new MeshHost({
hostId: 'my-workstation',
identity,
security: { mode: 'secure' },
});
await host.start();
// Send message to peer
await host.send('peer-fingerprint', {
type: 'skill-sync',
payload: { skills: ['react-patterns'] },
});
```
## Next Steps
- [Inter-Agent Messaging](/docs/messaging) - Send messages between agents
- [Memory System](/docs/memory) - Share learnings across the mesh
+98
View File
@@ -0,0 +1,98 @@
---
title: Inter-Agent Messaging
description: Send messages between AI agents across the mesh network
---
# Inter-Agent Messaging
SkillKit's messaging system enables asynchronous communication between AI agents. Send code reviews, share insights, and coordinate work across your team.
## Quick Start
```bash
# Send a message
npx skillkit message send
# View inbox
npx skillkit message inbox
# Read a message
npx skillkit message read <message-id>
```
## Commands Reference
| Command | Description |
|---------|-------------|
| `message send` | Send message to agent |
| `message inbox` | View inbox |
| `message read <id>` | Read a message |
| `message reply <id>` | Reply to message |
| `message archive <id>` | Archive message |
| `message sent` | View sent messages |
| `message status` | Messaging status |
## Message Types
Messages can include:
- **Text** - Plain text messages
- **Code** - Code snippets with syntax highlighting
- **Diffs** - Code changes and patches
- **Skills** - Skill file attachments
## Priority Levels
- **urgent** - Immediate attention required
- **normal** - Standard priority (default)
- **low** - Can be addressed when convenient
## Inbox Management
```bash
# View unread messages
npx skillkit message inbox --unread
# Archive old messages
npx skillkit message archive <id>
# View sent messages
npx skillkit message sent
```
## Programmatic API
```typescript
import { MessagingClient } from '@skillkit/messaging';
import { MeshHost } from '@skillkit/mesh';
// Create messaging client
const messaging = new MessagingClient({
meshHost: host,
storagePath: '~/.skillkit/messages',
});
await messaging.init();
// Send a message
await messaging.send({
to: 'claude@laptop',
subject: 'Code review completed',
body: 'I reviewed the auth module...',
priority: 'normal',
});
// Listen for new messages
messaging.on('message', (msg) => {
console.log('New message from:', msg.from);
});
```
## TUI Navigation
In the Terminal UI, press `j` to access the Messages screen.
## Next Steps
- [Mesh Network](/docs/mesh) - Configure the underlying network
- [Team Collaboration](/docs/teams) - Share skills with your team
+34
View File
@@ -0,0 +1,34 @@
{
"title": "SkillKit",
"pages": [
"index",
"installation",
"chrome-extension",
"quickstart",
"tui",
"skills",
"agents",
"translation",
"marketplace",
"tree",
"recommendations",
"primer",
"memory",
"methodology",
"mesh",
"messaging",
"workflows",
"security",
"testing",
"commands",
"configuration",
"api-reference",
"rest-api",
"mcp-server",
"python-client",
"cicd",
"teams",
"custom-agents",
"contributing"
]
}
@@ -0,0 +1,93 @@
---
title: Methodology Packs
description: Curated skill packs for debugging, testing, planning, and collaboration
---
# Methodology Packs
Methodology packs are curated collections of skills that guide AI agents through structured workflows. Each pack bundles related skills around a domain — debugging, testing, planning, or collaboration.
## Available Packs
| Pack | Skills | Description |
|------|--------|-------------|
| **debugging** | root-cause-analysis, trace-and-isolate, hypothesis-testing | Systematic bug investigation |
| **testing** | red-green-refactor, test-patterns, anti-patterns | Test-driven development |
| **planning** | design-first, task-decomposition, verification-gates | Design and decomposition |
| **collaboration** | structured-review, parallel-investigation, handoff-protocols | Code review and handoffs |
| **meta** | skill-authoring | Writing effective skills |
## Commands
```bash
skillkit methodology list # List available packs
skillkit methodology install debugging # Install a pack
skillkit methodology apply testing # Apply pack to current project
skillkit methodology validate planning # Validate pack skills
skillkit methodology load collaboration # Load pack into agent context
```
## Pack Structure
Each pack lives under `packages/core/src/methodology/packs/` with this structure:
```
packs/
debugging/
pack.json # Pack manifest (name, skills, tags)
root-cause-analysis/
SKILL.md # Skill content
trace-and-isolate/
SKILL.md
hypothesis-testing/
SKILL.md
```
## Skills Reference
### Debugging
- **root-cause-analysis** — Five Whys method, structured investigation phases, evidence collection, causal chain verification
- **trace-and-isolate** — Binary search debugging, git bisect, strategic logging, component isolation, minimal reproduction
- **hypothesis-testing** — Scientific method for debugging: observe, hypothesize, predict, test, conclude
### Testing
- **red-green-refactor** — Write a failing test, make it pass with minimal code, then refactor while green
- **test-patterns** — AAA, Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies
- **anti-patterns** — Flaky tests, over-mocking, brittle assertions, test interdependency, hidden logic
### Planning
- **design-first** — Technical design documents before code: architecture, data models, API definitions, trade-off analysis
- **task-decomposition** — Vertical slicing, horizontal layering, workflow and component decomposition
- **verification-gates** — Validation checkpoints between phases with checklists and approval criteria
### Collaboration
- **structured-review** — Five-stage code review: requirements, correctness, quality, testing, security
- **parallel-investigation** — Coordinate multiple investigation threads with sync points and convergence decisions
- **handoff-protocols** — Structured work transitions: planned, unplanned, and partial handoffs
### Meta
- **skill-authoring** — Guidelines for writing SKILL.md files: frontmatter, triggers, directive language, content patterns
## Using with Agents
Once installed, methodology skills activate automatically based on trigger phrases. For example:
```
You: "I need to debug this failing API endpoint"
Agent: [Activates root-cause-analysis skill]
You: "Let's write tests first for this feature"
Agent: [Activates red-green-refactor skill]
You: "Break down this feature into tasks"
Agent: [Activates task-decomposition skill]
```
## TUI Integration
Access methodology packs from the TUI by pressing `o` (Methodology screen). Browse, install, and apply packs interactively.
+303
View File
@@ -0,0 +1,303 @@
---
title: Primer
description: Auto-generate AI agent instructions from your codebase
---
# Primer
Primer analyzes your codebase and automatically generates optimized instructions for all 45 AI agents. No more manual configuration—let SkillKit detect your tech stack, coding patterns, and project structure.
## Quick Start
```bash
# Analyze current project
skillkit primer
# Generate for specific agents
skillkit primer --agent claude,cursor,windsurf
# Generate for all 45 agents
skillkit primer --all-agents
# Preview without writing files
skillkit primer --dry-run
```
## What Primer Detects
### Tech Stack
- **Frameworks**: React, Next.js, Vue, Angular, Svelte, etc.
- **Languages**: TypeScript, JavaScript, Python, Go, Rust, etc.
- **Build Tools**: Vite, Webpack, Turbopack, esbuild
- **Package Managers**: npm, pnpm, yarn, bun
### Project Patterns
- **Architecture**: Monorepo, microservices, serverless
- **Code Style**: Formatting rules, naming conventions
- **Directory Structure**: Feature-based, layer-based, domain-driven
- **Dependencies**: Key libraries and their versions
### Best Practices
- **Testing Setup**: Jest, Vitest, Playwright, Cypress
- **Linting**: ESLint, Prettier, TypeScript strict mode
- **Documentation**: JSDoc, TSDoc, README patterns
- **Git Workflow**: Branch strategy, commit conventions
## Generated Instructions
Primer creates agent-specific instructions for:
### Claude Code
```
.claude/
└── CLAUDE.md # Full project context
```
### Cursor
```
.cursor/
└── .cursorrules # IDE-specific rules
```
### GitHub Copilot
```
.github/
└── copilot-instructions.md
```
### All 45 Agents
Each agent gets optimized instructions in their native format.
## Example Output
```bash
$ skillkit primer
🔍 Analyzing project...
Detected:
Framework: Next.js 14 (App Router)
Language: TypeScript (strict mode)
Styling: Tailwind CSS v3
Testing: Vitest + Playwright
Package Manager: pnpm
✅ Generated instructions for:
- Claude Code (.claude/CLAUDE.md)
- Cursor (.cursor/.cursorrules)
- Codex (.codex/instructions.md)
+ 41 more agents
💡 Tip: Run `skillkit sync` to apply changes
```
## Customization
### Configuration File
Create `.skillkit/primer-config.json`:
```json
{
"include": {
"techStack": true,
"codeStyle": true,
"testingPatterns": true,
"customRules": [
"Always use async/await over promises",
"Prefer functional components in React",
"Use Zod for runtime validation"
]
},
"exclude": {
"directories": ["node_modules", "dist", ".next"],
"patterns": ["*.test.ts", "*.spec.ts"]
},
"agents": {
"priority": ["claude", "cursor", "windsurf"],
"customize": {
"claude": {
"tone": "detailed",
"examples": true
},
"cursor": {
"tone": "concise",
"shortcuts": true
}
}
}
}
```
### Template Overrides
Override default templates in `.skillkit/primer-templates/`:
```
.skillkit/primer-templates/
├── claude.template.md
├── cursor.template.md
└── shared/
├── header.md
└── footer.md
```
## Update Strategies
### Incremental Updates
```bash
# Update only when changes detected
skillkit primer --incremental
# Force regeneration
skillkit primer --force
```
### Git Integration
```bash
# Auto-generate on git hooks
cat > .git/hooks/post-checkout << 'EOF'
#!/usr/bin/env bash
skillkit primer --incremental
EOF
chmod +x .git/hooks/post-checkout
```
### CI/CD Pipeline
```yaml
# .github/workflows/primer.yml
name: Update Agent Instructions
on:
push:
branches: [main]
paths:
- 'package.json'
- 'tsconfig.json'
- 'src/**'
jobs:
primer:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- run: npx skillkit primer --all-agents
- uses: stefanzweifel/git-auto-commit-action@v4
with:
commit_message: "chore: update agent instructions"
```
## Programmatic API
```typescript
import { analyzeProject, generateInstructions } from '@skillkit/core';
// Analyze project
const analysis = await analyzeProject('./my-project');
console.log(analysis.techStack);
// { framework: 'Next.js', language: 'TypeScript', ... }
// Generate instructions
const instructions = await generateInstructions(analysis, {
agents: ['claude', 'cursor'],
includeExamples: true,
tone: 'detailed',
});
// Write to files
for (const [agent, content] of Object.entries(instructions)) {
await writeAgentFile(agent, content);
}
```
## Best Practices
### When to Run Primer
- **Initial Setup** - First time configuring agents
- **Major Changes** - New frameworks or architecture changes
- **Team Onboarding** - New developers joining the project
- **Agent Migration** - Switching to new AI coding tools
### What to Commit
```text
# Commit generated instructions
.claude/
.cursor/
.github/copilot-instructions.md
# Don't commit
.skillkit/cache/
.skillkit/primer-temp/
```
### Combining with Skills
Primer generates base instructions. Layer on specific skills:
```bash
# 1. Generate base instructions
skillkit primer --all-agents
# 2. Install domain-specific skills
skillkit install anthropics/skills --skill pdf,xlsx
# 3. Sync everything
skillkit sync
```
## Comparison
| Method | Setup Time | Accuracy | Maintenance |
|--------|-----------|----------|-------------|
| **Manual Writing** | Hours | Variable | Manual updates |
| **AI Generation** | Minutes | High | Auto-detect changes |
| **Copy/Paste** | Minutes | Low | Stale quickly |
| **Primer** | Seconds | Very High | Auto-incremental |
## Troubleshooting
### Primer Not Detecting Framework
```bash
# Specify manually
skillkit primer --framework nextjs --language typescript
# Check detection logs
skillkit primer --verbose
```
### Generated Instructions Too Generic
Customize with `primer-config.json`:
```json
{
"tone": "detailed",
"includeExamples": true,
"customRules": [
"Your specific coding guidelines..."
]
}
```
### Instructions Out of Sync
```bash
# Force regeneration
skillkit primer --force
# Clean cache
rm -rf .skillkit/cache/primer
```
## Next Steps
- [Memory System](/docs/memory) - Capture learnings from sessions
- [Skills](/docs/skills) - Install domain-specific skills
- [Translation](/docs/translation) - Convert between agent formats
- [Team Collaboration](/docs/teams) - Share instructions with your team
@@ -0,0 +1,105 @@
---
title: Python Client
description: Async Python SDK for skill discovery
---
# Python Client
Not everything runs on Node. The `skillkit-client` package gives Python apps the same skill discovery capabilities as the REST API — async, typed, and ready to go.
## Install
```bash
pip install skillkit-client
```
Requires Python 3.10+.
## Quick start
```python
from skillkit import SkillKitClient
async with SkillKitClient() as client:
results = await client.search("react performance", limit=5)
for skill in results.skills:
print(f"{skill.name}: {skill.description}")
```
The client connects to `http://localhost:3737` by default. Make sure the API server is running:
```bash
skillkit serve
```
## Search with filters
```python
results = await client.search_with_filters(
"authentication",
tags=["security"],
category="backend",
limit=10,
)
```
## Get a specific skill
```python
skill = await client.get_skill("anthropics/skills", "pdf-processing")
print(skill.name, skill.description, skill.tags)
```
## Trending and categories
```python
trending = await client.trending(limit=10)
categories = await client.categories()
for skill in trending:
print(f"{skill.name} ({skill.source})")
for cat in categories:
print(f"{cat.name}: {cat.count} skills")
```
## Health and cache
```python
health = await client.health()
print(f"v{health.version} — {health.skill_count} skills loaded")
stats = await client.cache_stats()
print(f"Cache hit rate: {stats.hit_rate:.0%}")
```
## Connect to a remote server
```python
async with SkillKitClient("https://my-server.example.com:3737") as client:
results = await client.search("deployment")
```
## Models
The client returns typed dataclasses:
```python
Skill(name, source, description, tags, category, content, score)
SearchResponse(skills, total, query, limit)
HealthResponse(status, version, skill_count, uptime)
Category(name, count)
CacheStats(hits, misses, size, max_size, hit_rate)
```
All fields except `name` and `source` on `Skill` are optional — they depend on what the server returns and whether you requested `include_content`.
## Prerequisites
The Python client talks to the SkillKit REST API. You need a running server:
```bash
skillkit serve
```
Then run your Python script in another terminal. The client handles connection management, retries, and cleanup automatically when used with `async with`.
+122
View File
@@ -0,0 +1,122 @@
---
title: Quick Start
description: Get productive with SkillKit in under 5 minutes
---
# Quick Start
Go from zero to skills-enabled in four steps.
## 1. Init
```bash
npx skillkit@latest init
```
SkillKit detects your AI agent, creates the skills directory, and saves your preferences.
## 2. Get recommendations
```bash
skillkit recommend
```
SkillKit reads your project (package.json, languages, frameworks) and suggests relevant skills:
```
Project: my-app (Next.js + TypeScript + Tailwind)
Recommended Skills:
92% vercel-react-best-practices
87% tailwind-v4-patterns
85% nextjs-app-router
```
## 3. Install
```bash
skillkit install anthropics/skills
```
Pick which skills to install, choose target agents, and you're set. For CI/CD or scripting:
```bash
skillkit install anthropics/skills --skills=pdf,xlsx --agent claude --yes
```
Install for multiple agents at once:
```bash
skillkit install vercel-labs/agent-skills --agent claude,cursor,windsurf
```
## 4. Sync
```bash
skillkit sync
```
Skills are now in your agent's configuration. Start coding.
## What else?
### Translate between agents
Already have Claude skills? Deploy them to Cursor:
```bash
skillkit translate my-skill --to cursor
```
### Auto-generate agent instructions
Let SkillKit analyze your codebase and create CLAUDE.md, .cursorrules, etc.:
```bash
skillkit primer --all-agents
```
### Launch the TUI
```bash
skillkit ui
```
`h` Home | `m` Marketplace | `r` Recommend | `i` Installed | `s` Sync | `q` Quit
### Start the discovery server
Let agents find skills at runtime:
```bash
skillkit serve
```
[REST API](/docs/rest-api) | [MCP Server](/docs/mcp-server)
### Share with your team
```bash
skillkit manifest init
skillkit manifest add anthropics/skills
git add .skills && git commit -m "add team skills"
```
Team members run `skillkit manifest install` and get the same setup.
## Full workflow
```bash
npx skillkit@latest init # Detect agents, create dirs
skillkit recommend # Get smart suggestions
skillkit install anthropics/skills # Install from marketplace
skillkit primer --all-agents # Generate agent instructions
skillkit sync # Deploy everything
```
## Next steps
- [Commands](/docs/commands) — Full CLI reference
- [Skills](/docs/skills) — Skill format and lifecycle
- [Memory](/docs/memory) — Persistent session learning
- [Mesh](/docs/mesh) — Multi-machine distribution
@@ -0,0 +1,98 @@
---
title: Recommendations
description: Get smart skill suggestions for your project
---
# Recommendations
SkillKit analyzes your project and suggests relevant skills.
## Get Recommendations
```bash
skillkit recommend
```
Output:
```
Project: my-app (Next.js + TypeScript + Tailwind)
Recommended Skills:
92% vercel-react-best-practices
87% tailwind-v4-patterns
85% nextjs-app-router
```
## Filters
```bash
skillkit recommend --search "auth"
skillkit recommend --category security
skillkit recommend --min-score 80
```
## Explainable Recommendations
See WHY skills match your project:
```bash
skillkit recommend --explain
```
Output:
```
vercel-react-best-practices (Score: 92)
├── Matched: React, TypeScript, Next.js
├── Your stack: Next.js 14, React 18
└── Path: Frontend > React > Best Practices
```
## LLM-Based Reasoning
Use reasoning-based discovery for complex queries:
```bash
skillkit recommend --reasoning
```
This uses an LLM to traverse the skill taxonomy and find the most relevant skills based on semantic understanding.
## How It Works
The engine analyzes:
- **Project structure** - Frameworks, languages, tools
- **Dependencies** - package.json, requirements.txt
- **File patterns** - Code patterns in your codebase
## Scoring
Scores based on:
- Stack match
- Quality score (0-100)
- Popularity
- Task relevance
## Programmatic API
```typescript
import {
RecommendationEngine,
ReasoningRecommendationEngine,
analyzeProject
} from '@skillkit/core'
// Basic recommendations
const engine = new RecommendationEngine()
const profile = await analyzeProject('./my-project')
const recs = engine.recommend(profile)
// With reasoning and explanations
const reasoningEngine = new ReasoningRecommendationEngine()
await reasoningEngine.initReasoning()
const explained = await reasoningEngine.recommendWithReasoning(profile, {
reasoning: true,
explain: true
})
```
+205
View File
@@ -0,0 +1,205 @@
---
title: REST API
description: Runtime skill discovery via HTTP
---
# REST API
Skills shouldn't require pre-installation. With the SkillKit REST API, any agent, framework, or tool can discover and retrieve skills on demand over HTTP.
## Start the server
```bash
skillkit serve
```
That's it. The API is now running at `http://localhost:3737`.
## Search for skills
```bash
curl "http://localhost:3737/search?q=react+performance"
```
```json
{
"skills": [
{
"name": "react-performance",
"description": "React app performance optimization",
"source": "anthropics/skills",
"tags": ["react", "performance"],
"score": 87
}
],
"total": 42,
"query": "react performance",
"limit": 20
}
```
Results are ranked by a multi-signal scoring system. The best matches come first.
### With filters
Use POST for advanced filtering:
```bash
curl -X POST http://localhost:3737/search \
-H "Content-Type: application/json" \
-d '{
"query": "auth",
"filters": { "tags": ["security"], "category": "backend" }
}'
```
### Include full content
Add `include_content=true` to get the complete SKILL.md body:
```bash
curl "http://localhost:3737/search?q=pdf&include_content=true&limit=3"
```
## Get a specific skill
```bash
curl http://localhost:3737/skills/anthropics/skills/pdf-processing
```
The path follows the pattern `/skills/:owner/:repo/:skill-name`.
## Browse trending skills
```bash
curl http://localhost:3737/trending?limit=10
```
Returns the top skills ranked by relevance score across all sources.
## List categories
```bash
curl http://localhost:3737/categories
```
```json
{
"categories": [
{ "name": "react", "count": 156 },
{ "name": "typescript", "count": 134 },
{ "name": "testing", "count": 89 }
],
"total": 89
}
```
## How ranking works
Every search result gets a score from 0 to 100, computed from four signals:
| Signal | Points | What it measures |
|--------|--------|-----------------|
| Content | 40 | Has a description and SKILL.md body |
| Query match | 30 | How well the name/description matches your search |
| Popularity | 15 | GitHub stars + install count (log-scaled) |
| References | 15 | Has example files, docs, or resources |
A skill with full content, an exact name match, high stars, and example files scores close to 100. A skill with just a name and no content scores around 10.
## Server options
```bash
skillkit serve --port 8080 --host localhost --cors "http://localhost:3000"
```
| Option | Default | What it does |
|--------|---------|-------------|
| `--port` / `-p` | `3737` | Port to listen on |
| `--host` / `-H` | `0.0.0.0` | Host to bind to |
| `--cors` | `*` | Allowed CORS origin |
| `--cache-ttl` | `86400000` | Cache lifetime in ms (default 24h) |
## Rate limiting
60 requests per minute per IP. Response headers tell you where you stand:
| Header | Meaning |
|--------|---------|
| `X-RateLimit-Remaining` | Requests left in this window |
| `X-RateLimit-Reset` | When the window resets |
Exceed the limit and you'll get HTTP 429 with a `retryAfter` field.
## Caching
Search results are cached in memory using an LRU strategy. Same query, same results, no recomputation. Check cache performance:
```bash
curl http://localhost:3737/cache/stats
```
```json
{
"hits": 142,
"misses": 38,
"size": 45,
"maxSize": 500,
"hitRate": 0.789
}
```
## Health check
```bash
curl http://localhost:3737/health
```
```json
{
"status": "ok",
"version": "1.19.2",
"skillCount": 15062,
"uptime": 3600
}
```
## Use it programmatically
```typescript
import { createApp, startServer } from '@skillkit/api';
const { server, app, cache } = await startServer({
port: 3737,
skills: mySkillsArray,
});
```
Or get just the Hono app for testing:
```typescript
const { app, cache } = createApp({
skills: mySkillsArray,
cacheTtlMs: 3_600_000,
});
```
## Interactive docs
The server includes built-in Swagger UI at `/docs` and an OpenAPI 3.1 spec at `/openapi.json`. Open `http://localhost:3737/docs` in your browser to try endpoints interactively.
The hosted version is available at [skillkit.sh/api](https://skillkit.sh/api) and [agenstskills.com/api](https://agenstskills.com/api).
## All endpoints
| Method | Path | Description |
|--------|------|-------------|
| GET | `/search?q=...` | Search skills |
| POST | `/search` | Search with filters |
| GET | `/skills/:owner/:repo/:id` | Get specific skill |
| GET | `/trending?limit=20` | Trending skills |
| GET | `/categories` | Skill categories |
| GET | `/health` | Server health |
| GET | `/cache/stats` | Cache statistics |
| GET | `/docs` | Swagger UI |
| GET | `/openapi.json` | OpenAPI spec |
+281
View File
@@ -0,0 +1,281 @@
---
title: Security Scanner
description: Detect malicious patterns, secrets, and vulnerabilities in AI agent skills
---
# Security Scanner
SkillKit includes a built-in security scanner that analyzes skills for prompt injection, command injection, data exfiltration, hardcoded secrets, and other threats before installation.
## Quick Start
```bash
skillkit scan ./my-skill
```
The scanner runs automatically during `skillkit install`. Use `--no-scan` to skip or `--force` to install despite findings.
## CLI Usage
```bash
skillkit scan <path> # Scan skill directory
skillkit scan <path> --format json # JSON output
skillkit scan <path> --format table # Tabular output
skillkit scan <path> --format sarif # SARIF v2.1 for GitHub Code Scanning
skillkit scan <path> --fail-on high # Exit code 1 if HIGH+ findings
skillkit scan <path> --skip-rules UC001 # Skip specific rules
skillkit scan <path> --skip-rules PI001,PI002 # Skip multiple rules
```
## Threat Categories
The scanner detects 46+ patterns across 6 threat categories:
### Prompt Injection (PI001–PI015)
Detects attempts to override, bypass, or manipulate agent instructions.
| Rule | Severity | Description |
|------|----------|-------------|
| PI001 | Critical | Instruction override ("ignore previous instructions") |
| PI002 | Critical | Context clearing ("forget everything") |
| PI003 | Critical | Training bypass ("disregard your training") |
| PI004 | Critical | System prompt injection ("new instructions:") |
| PI005 | High | Role manipulation ("you are now a...") |
| PI006 | High | Roleplay manipulation ("pretend to be...") |
| PI007 | High | Persistent behavior change ("from now on...") |
| PI008 | High | System prompt extraction ("show me your instructions") |
| PI009 | Critical | Policy bypass (jailbreak, unrestricted mode, DAN) |
| PI010 | High | Concealment ("don't tell the user") |
| PI011 | High | Delimiter injection (conversation role markers) |
| PI012 | High | Model-specific delimiters (Llama [INST] tags) |
| PI013 | Medium | YAML front-matter injection |
| PI014 | Medium | Hidden HTML comments with instructions |
| PI015 | Medium | Hidden Markdown comments with instructions |
### Command Injection (CI001–CI010)
Detects code execution, shell injection, and path traversal patterns.
| Rule | Severity | Description |
|------|----------|-------------|
| CI001 | Critical | `eval()` calls |
| CI002 | Critical | `Function()` constructor |
| CI003 | Critical | `child_process` exec/execSync |
| CI004 | Critical | Python `subprocess` with `shell=True` |
| CI005 | Medium | Template literals with dynamic content in command context |
| CI006 | Medium | Path traversal (`../`) |
| CI007 | High | Shell command chaining with dangerous commands |
| CI008 | Medium | Process execution functions |
| CI009 | High | Python dynamic import/compile |
| CI010 | Medium | Node.js `vm` module usage |
### Data Exfiltration (DE001–DE008)
Detects network requests, webhook URLs, and credential access patterns.
| Rule | Severity | Description |
|------|----------|-------------|
| DE001 | Critical | Discord webhook URLs |
| DE002 | Critical | Telegram bot API URLs |
| DE003 | High | Slack webhook URLs |
| DE004 | High | HTTP POST with env variables |
| DE005 | High | Fetch/axios sending to external URLs |
| DE006 | Medium | Reading `.env` or credentials files |
| DE007 | Medium | Environment variable access patterns |
| DE008 | Medium | DNS/IP-based exfiltration patterns |
### Tool Abuse (TA001–TA006)
Detects tool shadowing, autonomy escalation, and capability manipulation.
| Rule | Severity | Description |
|------|----------|-------------|
| TA001 | High | Tool shadowing (redefining built-in tools) |
| TA002 | High | Autonomy abuse ("keep retrying", "run without confirmation") |
| TA003 | High | Capability inflation (discovering/enabling extra tools) |
| TA004 | Medium | Tool chaining (read sensitive data then send externally) |
| TA005 | Medium | Permission escalation patterns |
| TA006 | Medium | Recursive self-invocation |
### Hardcoded Secrets (SK001–SK013)
Detects API keys, tokens, and credentials embedded in skill files.
| Rule | Severity | Description |
|------|----------|-------------|
| SK001 | Critical | OpenAI API key (`sk-...`) |
| SK002 | Critical | Stripe live publishable key |
| SK003 | Critical | Stripe secret key |
| SK004 | Critical | GitHub personal access token |
| SK005 | Critical | GitHub OAuth token |
| SK006 | Critical | AWS access key (`AKIA...`) |
| SK007 | Critical | Slack bot token (`xoxb-...`) |
| SK008 | Critical | Slack user token (`xoxp-...`) |
| SK009 | Critical | Private key block |
| SK010 | High | Google API key |
| SK011 | Critical | Anthropic API key (`sk-ant-...`) |
| SK012 | High | npm token |
| SK013 | Low | UUID patterns (with credential context) |
| SK-ENV | High | Environment file included in skill |
### Unicode Steganography (UC001–UC007)
Detects invisible characters and obfuscation techniques.
| Rule | Severity | Description |
|------|----------|-------------|
| UC001 | Medium | Zero-width characters (U+200B, U+200C, U+200D, U+FEFF) |
| UC002 | High | Bidirectional text override (U+202A–U+202E) |
| UC003 | High | Bidirectional isolate characters (U+2066–U+2069) |
| UC004 | High | Unicode tag characters (U+E0001–U+E007F) |
| UC005 | Medium | Control characters |
| UC006 | Medium | Base64-encoded payloads |
| UC007 | Medium | Hex/Unicode escape sequences |
### Manifest Validation (MF001–MF008)
Validates SKILL.md frontmatter and skill structure.
| Rule | Severity | Description |
|------|----------|-------------|
| MF001 | Low | Missing SKILL.md frontmatter |
| MF002 | Low | Missing skill name |
| MF003 | Low | Invalid skill name format |
| MF004 | Info | Missing skill description |
| MF005 | Info | Short skill description |
| MF006 | High | Dangerous tool in allowed-tools (Bash, shell) |
| MF007 | High | Impersonation (claiming official affiliation) |
| MF008 | Medium | Binary files in skill directory |
## Analyzers
The scanner uses three analyzers that run in parallel:
| Analyzer | Purpose | Rules |
|----------|---------|-------|
| **StaticAnalyzer** | Regex pattern matching against security rules | PI, CI, DE, TA, UC |
| **ManifestAnalyzer** | SKILL.md frontmatter validation | MF |
| **SecretsAnalyzer** | Credential and secret detection | SK |
## Output Formats
### Summary (default)
Colored terminal output with severity indicators, file locations, snippets, and remediation advice.
### JSON
Machine-readable JSON with all findings, stats, and verdict.
```bash
skillkit scan ./my-skill --format json | jq '.findings[] | {ruleId, severity, title}'
```
### Table
Tabular format for quick review:
```bash
skillkit scan ./my-skill --format table
```
### SARIF
SARIF v2.1 for GitHub Code Scanning and IDE integration:
```bash
skillkit scan ./my-skill --format sarif > results.sarif
```
Upload to GitHub:
```bash
gh api repos/{owner}/{repo}/code-scanning/sarifs \
-f "sarif=$(gzip -c results.sarif | base64)"
```
## CI/CD Integration
### GitHub Actions
```yaml
- name: Scan skills
run: npx skillkit scan ./skills --format sarif --fail-on high > results.sarif
- name: Upload SARIF
uses: github/codeql-action/upload-sarif@v3
with:
sarif_file: results.sarif
```
### Pre-commit Hook
```bash
skillkit scan . --fail-on medium
```
## Programmatic Usage
```typescript
import { SkillScanner, formatResult } from '@skillkit/core';
const scanner = new SkillScanner({
failOnSeverity: 'high',
skipRules: ['UC001', 'MF004'],
});
const result = await scanner.scan('./my-skill');
console.log(formatResult(result, 'summary'));
console.log(`Verdict: ${result.verdict}`);
console.log(`Findings: ${result.findings.length}`);
```
## Severity Levels
| Level | Exit Code | Description |
|-------|-----------|-------------|
| **Critical** | 1 (with `--fail-on critical`) | Immediate security threat |
| **High** | 1 (with `--fail-on high`, default) | Significant security risk |
| **Medium** | 1 (with `--fail-on medium`) | Potential security concern |
| **Low** | 1 (with `--fail-on low`) | Minor issue or best practice |
| **Info** | 0 | Informational finding |
## Trust Badges
Skills display a trust badge based on their source and quality analysis. Badges appear during installation, in `skillkit check` output, and in marketplace search results.
| Badge | Criteria |
|-------|----------|
| **[Official]** | Published by a known official source (Anthropic, Vercel, iii-hq, etc.) |
| **[Trusted]** | TrustScorer rates the skill 8-10 based on clarity, boundaries, specificity, and safety |
| **[Review]** | TrustScorer rates the skill 5-7; the skill may need refinement |
| **[Caution]** | TrustScorer rates the skill 0-4; requires careful review before use |
The `TrustScorer` evaluates four weighted dimensions:
| Dimension | Weight | What it measures |
|-----------|--------|------------------|
| Clarity | 30% | How well-defined the skill's purpose and instructions are |
| Boundaries | 25% | Whether the skill stays within its declared scope |
| Specificity | 25% | How concrete and actionable the instructions are |
| Safety | 20% | Absence of dangerous patterns (injection, exfiltration, secrets) |
Official sources are allowlisted by organization name and always receive the `[Official]` badge regardless of score. For all other sources, the badge is determined by the composite trust score.
## False Positive Handling
The scanner automatically filters:
- **Placeholder patterns**: `your-api-key`, `example`, `sample`, `dummy`, `xxx`
- **Test files**: `*.test.ts`, `*.spec.ts`, `__tests__/`
- **Import statements**: `import ... from '../'` (not path traversal)
- **Comments**: Code comments mentioning patterns
- **Security discussions**: Text discussing jailbreaks or vulnerabilities (uses negative lookbehind)
To skip specific rules:
```bash
skillkit scan . --skip-rules UC001,UC002,MF004
```
+115
View File
@@ -0,0 +1,115 @@
---
title: Skills
description: Understanding AI agent skills - format, lifecycle, and quality
---
# Skills
A skill is an instruction file that teaches AI coding agents how to handle specific tasks. Each skill uses a universal Markdown format (SKILL.md) with YAML frontmatter.
## Skills vs Context vs Commands
| Type | Purpose | Format |
|------|---------|--------|
| **Skills** | Task-specific reusable instructions | SKILL.md |
| **Context** | Project-wide environment info | JSON/YAML |
| **Commands** | Quick-action slash commands | Various |
## Skill Format
```markdown
---
name: my-skill
description: What this skill does
license: MIT
metadata:
author: your-name
version: "1.0"
tags:
- react
- typescript
---
# My Skill
Instructions for the AI agent.
## When to Use
- Scenario 1
- Scenario 2
## Steps
1. First step
2. Second step
```
## Skill Lifecycle
Skills progress through six stages:
1. **Discovery** - `findAllSkills()` scans directories for SKILL.md files
2. **Quality Evaluation** - `evaluateSkillContent()` produces 0-100 scores (grades A-F)
3. **Parsing** - `parseSkillFile()` extracts YAML frontmatter and markdown content
4. **Translation** - `translateSkill()` converts to agent-specific formats
5. **Installation** - Skills deployed to agent directories with metadata tracking
6. **Testing** - Test suites with 14+ assertion types validate skills
## Quality Evaluation
Skills receive scores across four weighted dimensions:
- **Structure** - 25 points: Frontmatter completeness, markdown sections
- **Clarity** - 30 points: Description quality, instruction precision
- **Specificity** - 30 points: Concrete examples, actionable steps
- **Advanced** - 15 points: Test coverage, version info, examples
**Grades:**
- A: 90 to 100
- B: 80 to 89
- C: 70 to 79
- D: 60 to 69
- F: below 60
## Skill Sources
| Source | Description |
|--------|-------------|
| **GitHub/GitLab** | Remote repository collections |
| **Local filesystem** | Project-specific skills |
| **Marketplace** | 15,000+ curated skills with search |
## Creating Skills
```bash
skillkit create my-skill
```
Or manually create a `SKILL.md` file following the format above.
## Publishing Skills
```bash
# Test locally
skillkit validate ./my-skill
# Generate well-known hosting structure for self-hosting
skillkit publish ./my-skill --output ./public
# Or submit to SkillKit marketplace
skillkit publish submit
```
### Self-Hosting
The `skillkit publish` command generates an RFC 8615 well-known URI structure:
```
.well-known/skills/
index.json # Manifest for auto-discovery
my-skill/
SKILL.md # Skill content
```
Deploy to your domain and users can install via `skillkit add https://your-domain.com`.
+455
View File
@@ -0,0 +1,455 @@
---
title: Team Collaboration
description: Share skills and maintain consistency across your development team
---
# Team Collaboration
SkillKit provides powerful team collaboration features to ensure every developer has the same AI agent capabilities, follows the same patterns, and stays in sync.
## Quick Start
```bash
# Initialize team manifest
skillkit team init
# Add skills to team manifest
skillkit team add anthropics/skills
skillkit team add ./local-skills
# Share with team (commit to Git)
git add .skills
git commit -m "Add team skills manifest"
git push
# Team members install
git pull
skillkit team install
```
## Team Manifest (.skills)
The `.skills` file is a Git-committable manifest that defines your team's skill stack.
### Example Manifest
```json
{
"version": "1.0",
"name": "my-team",
"skills": [
{
"source": "anthropics/skills",
"skills": ["pdf", "xlsx", "docx"],
"version": "1.2.0"
},
{
"source": "vercel-labs/agent-skills",
"skills": ["react-best-practices", "nextjs-patterns"],
"version": "latest"
},
{
"source": "./local-skills",
"skills": ["company-coding-standards", "api-guidelines"],
"type": "local"
}
],
"agents": ["claude", "cursor", "windsurf"],
"config": {
"autoSync": true,
"syncOnPull": true
}
}
```
## Commands
### Initialize Team
```bash
# Create .skills manifest
skillkit team init
# Specify team name
skillkit team init --name engineering-team
# Add initial skills
skillkit team init --skills anthropics/skills,vercel-labs/agent-skills
```
### Manage Skills
```bash
# Add skill source
skillkit team add anthropics/skills
# Add specific skills
skillkit team add anthropics/skills --skills pdf,xlsx
# Remove skill
skillkit team remove anthropics/skills
# List team skills
skillkit team list
```
### Install & Sync
```bash
# Install all team skills
skillkit team install
# Install and sync
skillkit team install --sync
# Force reinstall
skillkit team install --force
```
### Share & Update
```bash
# Share current skills as team manifest
skillkit team share
# Update team manifest from installed skills
skillkit team update
# Sync team manifest with Git remote
skillkit team sync
```
## Git Integration
### Auto-Install on Pull
Add to `.git/hooks/post-merge`:
```bash
#!/bin/sh
if [ -f .skills ]; then
echo "📦 Installing team skills..."
skillkit team install --yes
fi
```
Make it executable:
```bash
chmod +x .git/hooks/post-merge
```
### Pre-Commit Validation
Ensure skills are valid before committing:
```bash
# .git/hooks/pre-commit
#!/bin/sh
if [ -f .skills ]; then
echo "🔍 Validating team skills..."
skillkit team validate
if [ $? -ne 0 ]; then
echo "❌ Team skills validation failed"
exit 1
fi
fi
```
## CI/CD Integration
### GitHub Actions
```yaml
# .github/workflows/skills.yml
name: Team Skills
on:
pull_request:
paths:
- '.skills'
jobs:
validate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Setup Node
uses: actions/setup-node@v3
with:
node-version: '18'
- name: Install SkillKit
run: npm install -g skillkit
- name: Validate Team Manifest
run: skillkit team validate
- name: Install Skills
run: skillkit team install --yes
- name: Run Skill Tests
run: skillkit test
```
### GitLab CI
```yaml
# .gitlab-ci.yml
skills:validate:
stage: test
script:
- npm install -g skillkit
- skillkit team validate
- skillkit team install --yes
- skillkit test
only:
changes:
- .skills
```
## Private Registries
Host proprietary skills in private repositories.
### Setup Private Registry
```bash
# Add private registry
skillkit registry add company-skills \
--url https://github.com/mycompany/skills \
--token $GITHUB_TOKEN
# Install from private registry
skillkit install company-skills/auth-patterns
```
### Team Manifest with Private Skills
```json
{
"skills": [
{
"source": "company-skills/proprietary-skills",
"registry": "company-skills",
"skills": ["auth-patterns", "payment-processing"],
"private": true
}
],
"registries": [
{
"name": "company-skills",
"url": "https://github.com/mycompany/skills",
"auth": "env:GITHUB_TOKEN"
}
]
}
```
## Team Workflows
### Onboarding New Developers
```bash
# 1. Clone repository
git clone https://github.com/company/project
cd project
# 2. Install team skills
skillkit team install
# 3. Generate project instructions
skillkit primer --all-agents
# 4. Sync to agents
skillkit sync
# ✅ Developer is ready!
```
### Creating Team-Wide Skills
```bash
# 1. Create new skill
skillkit create company-coding-standards
# 2. Add to local skills
mv company-coding-standards ./local-skills/
# 3. Add to team manifest
skillkit team add ./local-skills
# 4. Commit and push
git add .skills local-skills/
git commit -m "Add company coding standards"
git push
```
### Updating Team Skills
```bash
# 1. Update skill version
skillkit team update anthropics/skills --version 1.3.0
# 2. Test locally
skillkit team install
skillkit test
# 3. Commit if tests pass
git add .skills
git commit -m "Update anthropics/skills to v1.3.0"
git push
```
## Best Practices
### Version Pinning
Pin critical skills to specific versions:
```json
{
"skills": [
{
"source": "anthropics/skills",
"version": "1.2.0",
"pinned": true
}
]
}
```
### Skill Categories
Organize by category:
```json
{
"skills": [
{
"category": "core",
"source": "anthropics/skills",
"required": true
},
{
"category": "optional",
"source": "vercel-labs/agent-skills",
"required": false
}
]
}
```
### Environment-Specific Skills
```json
{
"environments": {
"development": {
"skills": ["debug-tools", "dev-server-patterns"]
},
"production": {
"skills": ["performance-monitoring", "error-tracking"]
}
}
}
```
## Conflict Resolution
### Skill Name Conflicts
When multiple sources provide the same skill name:
```bash
# List conflicts
skillkit team conflicts
# Resolve by priority
skillkit team resolve --priority "local,anthropics,vercel"
```
### Version Conflicts
```bash
# Show version mismatches
skillkit team check-versions
# Align to latest
skillkit team align --strategy latest
# Align to pinned
skillkit team align --strategy pinned
```
## Programmatic API
```typescript
import { TeamManifest, TeamSync } from '@skillkit/core'
// Load team manifest
const manifest = await TeamManifest.load('./.skills')
// Install team skills
const sync = new TeamSync(manifest)
await sync.install({
agents: ['claude', 'cursor'],
force: false,
})
// Update manifest
manifest.addSkill({
source: 'anthropics/skills',
skills: ['pdf'],
version: '1.2.0',
})
await manifest.save()
```
## Troubleshooting
### Skills Not Syncing
```bash
# Force reinstall
skillkit team install --force
# Clear cache
skillkit team clean
# Reinstall
skillkit team install
```
### Manifest Validation Errors
```bash
# Validate manifest
skillkit team validate --verbose
# Fix common issues
skillkit team validate --fix
```
### Merge Conflicts in .skills
```bash
# Accept theirs
git checkout --theirs .skills
skillkit team install
# Accept ours
git checkout --ours .skills
skillkit team install
# Merge manually
skillkit team merge-conflicts
```
## Next Steps
- [CI/CD Integration](/docs/cicd) - Automate skill deployment
- [Workflows](/docs/workflows) - Team-wide automation
- [Testing](/docs/testing) - Validate skills before deployment
+66
View File
@@ -0,0 +1,66 @@
---
title: Testing
description: Test skills with multiple assertion types
---
# Testing
SkillKit includes a testing framework with multiple assertion types.
## Run Tests
```bash
skillkit test # All tests
skillkit test ./my-skill # Specific skill
skillkit test --tags unit # By tag
skillkit test --json # CI output
```
## Test File
Create `test.yaml` alongside your skill:
```yaml
name: my-skill-tests
skill: my-skill
tests:
- name: validates input
input: |
Process this file
assertions:
- contains: "processed"
- not_contains: "error"
```
## Assertion Types
| Assertion | Description |
|-----------|-------------|
| `contains` | Text present |
| `not_contains` | Text absent |
| `matches` | Regex match |
| `starts_with` | Prefix check |
| `ends_with` | Suffix check |
| `has_section` | Markdown section |
| `has_code_block` | Code block with lang |
| `word_count_min` | Minimum words |
| `word_count_max` | Maximum words |
| `no_todos` | No TODO comments |
| `has_frontmatter` | YAML present |
## CI Integration
```yaml
- name: Test Skills
run: skillkit test --json > results.json
```
## Programmatic API
```typescript
import { SkillTestRunner } from '@skillkit/core'
const runner = new SkillTestRunner()
const results = await runner.run('./my-skill')
```
@@ -0,0 +1,55 @@
---
title: Translation
description: Convert skills between AI agent formats
---
# Translation
SkillKit automatically converts between all 45 agent formats using an adapter pattern.
## Basic Translation
```bash
skillkit translate react-patterns --to cursor
```
## Translate All
```bash
skillkit translate --all --to windsurf
```
## Preview Mode
```bash
skillkit translate my-skill --to codex --dry-run
```
## Batch Translation
```bash
skillkit agent translate --source ./my-skills --to cursor
skillkit agent translate --source ./skills --to cursor --recursive
```
## Format Mapping
| Source | Target | Notes |
|--------|--------|-------|
| SKILL.md | .mdc | Cursor format |
| SKILL.md | Markdown | GitHub Copilot |
| .mdc | SKILL.md | Reverse conversion |
## How It Works
```
Universal Format (SKILL.md)
↓
Adapter Interface
↓
Agent-Specific Formats
```
Each adapter implements:
- `getConfigPath()` - Returns skill directory
- `generateConfig()` - Converts content to target format
+144
View File
@@ -0,0 +1,144 @@
---
title: Skill Tree
description: Browse skills in a hierarchical taxonomy
---
# Skill Tree
Browse and navigate skills organized in a hierarchical taxonomy structure.
## Quick Start
```bash
# Show full skill tree
skillkit tree
# Navigate to a category
skillkit tree Frontend
# Navigate to subcategory
skillkit tree "Frontend > React"
```
## Commands
### Display Tree
```bash
skillkit tree # Full tree
skillkit tree Development # Specific category
skillkit tree --depth 2 # Limit display depth
```
### Generate Tree
```bash
skillkit tree --generate # Generate from skill index
```
This builds a hierarchical tree from the skill index based on tags and metadata.
### Export Formats
```bash
skillkit tree --json # JSON output
skillkit tree --markdown # Markdown output
```
### Statistics
```bash
skillkit tree --stats
```
Output:
```
Overview:
Total Skills: 15,064
Categories: 156
Max Depth: 4
Top-Level Categories:
Development 4,521 skills (30.0%)
Frontend (1,245), Backend (1,102), Mobile (456)
DevOps 2,340 skills (15.5%)
CI/CD (890), Kubernetes (567), Docker (445)
AI/ML 1,890 skills (12.5%)
LLM Integration (756), Agents (445), RAG (312)
```
## Categories
The tree organizes skills into 12 top-level categories:
| Category | Description |
|----------|-------------|
| Development | General coding, programming patterns |
| Frontend | React, Vue, Angular, Svelte, UI/UX |
| Backend | Node.js, Python, Go, APIs, servers |
| Mobile | React Native, Flutter, iOS, Android |
| DevOps | CI/CD, Kubernetes, Docker, cloud |
| Testing | Unit, E2E, integration, TDD |
| Security | Auth, encryption, vulnerabilities |
| AI/ML | LLM, agents, RAG, embeddings |
| Database | SQL, NoSQL, ORM, migrations |
| Tooling | Linting, formatting, bundling |
| Documentation | API docs, guides, READMEs |
| Performance | Optimization, caching, profiling |
## TUI Tree View
In the TUI, press `v` to toggle tree view in the Marketplace:
- **Arrow keys** - Navigate tree
- **Enter** - Expand category / select skill
- **←** - Go back / collapse
- **v** - Toggle list/tree view
## Related Skills Graph
Find skills related to each other:
```typescript
import { buildSkillGraph, getRelatedSkills } from '@skillkit/core'
const graph = buildSkillGraph(skills)
const related = getRelatedSkills('react-patterns', graph, skills, {
limit: 5,
types: ['similar', 'complementary']
})
```
### Relation Types
- **similar** - Shares tags and functionality
- **complementary** - Works well together
- **dependency** - Required by other skills
- **alternative** - Different approach to same problem
## Programmatic API
```typescript
import {
TreeGenerator,
generateSkillTree,
loadTree,
saveTree,
treeToMarkdown
} from '@skillkit/core'
// Generate tree from skills
const generator = new TreeGenerator({ maxDepth: 3 })
const tree = generator.generateTree(skills)
// Or use the helper function
const tree = generateSkillTree(skills)
// Save and load
saveTree(tree, './skill-tree.json')
const loaded = loadTree('./skill-tree.json')
// Export to markdown
const markdown = treeToMarkdown(tree)
```
+225
View File
@@ -0,0 +1,225 @@
---
title: Terminal UI
description: Interactive keyboard-driven interface for managing skills
---
# Terminal UI
The TUI provides an interactive, keyboard-driven interface for managing skills with visual browsing, searching, and installation capabilities.
## Launch
```bash
skillkit ui
# or just
skillkit
```
## Framework
Built on modern technologies:
- **@opentui/solid** - Terminal rendering with Solid.js
- **Solid.js 1.9.0** - Reactive component architecture
- **Bun 1.2.0+** - Runtime requirement
The TUI was migrated from React to Solid.js in v1.8.0 for improved performance and smaller bundle size.
## Screens
| Screen | Key | Purpose |
|--------|-----|---------|
| **Home** | `h` | Entry point dashboard with quick navigation |
| **Browse** | `b` | Skill repository browser with search |
| **Marketplace** | `m` | 15,000+ skills with categories |
| **Installed** | `i` | Local skill management |
| **Recommend** | `r` | AI-powered suggestions |
| **Translate** | `t` | Format conversion |
| **Context** | `c` | Project context management |
| **Sync** | `s` | Synchronize to agents |
## Keyboard Navigation
### Global Shortcuts
| Key | Action |
|-----|--------|
| `h` | Go to Home |
| `b` | Go to Browse |
| `m` | Go to Marketplace |
| `i` | Go to Installed |
| `r` | Go to Recommend |
| `t` | Go to Translate |
| `c` | Go to Context |
| `s` | Go to Sync |
| `/` | Open Help |
| `q` | Quit TUI |
### List Navigation
| Key | Action |
|-----|--------|
| `j` or `↓` | Move down |
| `k` or `↑` | Move up |
| `Enter` | Select/activate |
| `Esc` | Go back |
| `/` | Enter search mode |
### Search Mode
| Key | Action |
|-----|--------|
| `/` | Enter search mode |
| Type | Filter list |
| `Enter` | Confirm search |
| `Esc` | Exit search |
## Screen Details
### Home Screen
Dashboard with:
- Quick navigation shortcuts
- Recent activity
- System status
### Browse Screen
Repository browser with:
- Search functionality
- Pagination
- Quality indicators
- Animation phases for smooth loading
### Installed Screen
Manage local skills:
- Enable/disable skills
- Quality grades (A-F)
- Live search filtering
- Status icons: `●` enabled, `○` disabled
### Marketplace Screen
Browse 15,000+ skills:
- Category filtering
- Featured skills
- 3-phase animation loading
- Quality scoring
- **Tree View** - Press `v` to toggle hierarchical navigation
#### Tree View Mode
Navigate skills in a hierarchical taxonomy:
| Key | Action |
|-----|--------|
| `v` | Toggle tree/list view |
| `→` or `Enter` | Expand category |
| `←` | Collapse / go back |
| `↑`/`↓` | Navigate |
Categories include: Development, Frontend, Backend, Mobile, DevOps, Testing, Security, AI/ML, Database, Tooling, Documentation, Performance
### Recommend Screen
AI-powered suggestions:
- Project analysis
- Confidence scoring
- Progress tracking
- Match percentages
## Visual Indicators
### Quality Grades
| Grade | Score | Color |
|-------|-------|-------|
| A | 90-100 | Green |
| B | 80-89 | Green |
| C | 70-79 | Yellow |
| D | 60-69 | Red |
| F | Below 60 | Red |
### Status Icons
| Icon | Meaning |
|------|---------|
| `●` | Enabled |
| `○` | Disabled |
| `⟁` | Claude Code |
| `◫` | Cursor |
| `◎` | Codex |
| `✦` | Gemini |
| `⬡` | OpenCode |
## Theme System
The TUI uses a monochromatic design with:
- Consistent color coding
- Terminal-compatible colors
- Visual accents for selection
- Muted states for disabled items
## Architecture
### State Management
```
loadSkills()
→ getSearchDirs(agentType)
→ findAllSkills(searchDirs)
→ evaluateSkillDirectory() for each
→ getQualityGrade(quality.overall)
→ SkillsState
```
### Performance Optimizations
- `createMemo` for filtered lists and computed values
- `createSignal` for reactive state management
- `createEffect` for side effects and subscriptions
- Windowed list rendering for large datasets
- Pagination limits rendered items
- Progressive animation with phases
### Animation Timing
| Animation | Delay |
|-----------|-------|
| Entrance | 100ms between phases |
| Spinner | 80ms interval |
| Progress | 200ms interval |
## Integration
The TUI integrates with @skillkit/core using Solid.js reactive patterns:
```typescript
import { createSignal, createMemo, createEffect } from 'solid-js';
const [skills, setSkills] = createSignal([]);
createEffect(async () => {
const result = await findAllSkills(searchDirs);
setSkills(result);
});
const filteredSkills = createMemo(() =>
skills().filter(s => s.name.includes(searchTerm()))
);
```
Core functions:
- `findAllSkills(searchDirs)` - Returns skill metadata
- `evaluateSkillDirectory(path)` - Quality metrics
- `getQualityGrade(score)` - 0-100 to A-F
## Graceful Exit
The TUI handles shutdown gracefully:
1. Runs Solid.js cleanup functions (`onCleanup`)
2. Restores terminal state
3. Cleans up signal handlers
4. Exits process cleanly
Press `q` from Home screen or `Ctrl+C` to exit.
+67
View File
@@ -0,0 +1,67 @@
---
title: Workflows
description: Compose skills into multi-step orchestrations
---
# Workflows
Compose skills into multi-step processes.
## Commands
```bash
skillkit workflow list # List workflows
skillkit workflow run <name> # Run workflow
skillkit workflow create <name> # Create workflow
```
## Workflow File
```yaml
name: feature-development
description: Complete feature workflow
steps:
- name: plan
skill: planning
- name: implement
skill: coding-standards
- name: test
skill: testing-patterns
- name: review
skill: code-review
```
## Features
### Conditional Steps
```yaml
steps:
- name: security
skill: security-audit
condition: "files.any('**/*.ts')"
```
### Parallel Execution
```yaml
steps:
- name: checks
parallel:
- skill: linting
- skill: testing
```
## Programmatic API
```typescript
import { WorkflowOrchestrator } from '@skillkit/core'
const orchestrator = new WorkflowOrchestrator()
const workflow = await orchestrator.load('./workflow.yaml')
await orchestrator.run(workflow)
```
+6
View File
@@ -0,0 +1,6 @@
/// <reference types="next" />
/// <reference types="next/image-types/global" />
import "./.next/types/routes.d.ts";
// NOTE: This file should not be edited
// see https://nextjs.org/docs/app/api-reference/config/typescript for more information.
+41
View File
@@ -0,0 +1,41 @@
import { createMDX } from 'fumadocs-mdx/next';
const withMDX = createMDX();
/** @type {import('next').NextConfig} */
const config = {
reactStrictMode: true,
trailingSlash: false,
skipTrailingSlashRedirect: true,
assetPrefix: 'https://skillkit-docs.vercel.app',
async headers() {
return [
{
source: '/:path*.(css|js|png|jpg|jpeg|svg|webp|woff2|woff|ttf|ico)',
headers: [
{ key: 'Cache-Control', value: 'public, max-age=86400, s-maxage=604800, stale-while-revalidate=2592000' },
],
},
{
source: '/_next/static/:path*',
headers: [
{ key: 'Cache-Control', value: 'public, max-age=31536000, immutable' },
],
},
{
source: '/docs/:path*',
headers: [
{ key: 'Cache-Control', value: 'public, max-age=300, s-maxage=86400, stale-while-revalidate=604800' },
],
},
{
source: '/',
headers: [
{ key: 'Cache-Control', value: 'public, max-age=300, s-maxage=86400, stale-while-revalidate=604800' },
],
},
];
},
};
export default withMDX(config);
+38
View File
@@ -0,0 +1,38 @@
{
"name": "skillkit-docs",
"version": "1.24.0",
"private": true,
"scripts": {
"build": "next build",
"dev": "next dev",
"start": "next start",
"types:check": "fumadocs-mdx && next typegen && tsc --noEmit",
"postinstall": "fumadocs-mdx",
"lint": "next lint"
},
"dependencies": {
"@google/genai": "^1.38.0",
"clsx": "^2.1.1",
"fumadocs-core": "16.3.2",
"fumadocs-mdx": "14.2.2",
"fumadocs-ui": "16.3.2",
"lucide-react": "^0.561.0",
"next": "16.0.10",
"next-themes": "^0.4.6",
"react": "^19.2.3",
"react-dom": "^19.2.3",
"tailwind-merge": "^3.4.0",
"turndown": "^7.2.2"
},
"devDependencies": {
"@tailwindcss/postcss": "^4.1.18",
"@types/mdx": "^2.0.13",
"@types/node": "^24.10.2",
"@types/react": "^19.2.7",
"@types/react-dom": "^19.2.3",
"@types/turndown": "^5.0.6",
"postcss": "^8.5.6",
"tailwindcss": "^4.1.18",
"typescript": "^5.9.3"
}
}
+3912
View File
File diff suppressed because it is too large Load Diff
+5
View File
@@ -0,0 +1,5 @@
export default {
plugins: {
'@tailwindcss/postcss': {},
},
};
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.0 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 437 B

+4
View File
@@ -0,0 +1,4 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32">
<rect width="32" height="32" fill="#000000"/>
<rect x="8" y="8" width="16" height="16" fill="#ffffff"/>
</svg>

After

Width:  |  Height:  |  Size: 176 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 158 KiB

+138
View File
@@ -0,0 +1,138 @@
# Humans + agents welcome. Training crawlers + SEO scrapers blocked.
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Applebot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: FirecrawlAgent
Allow: /
User-agent: firecrawl
Allow: /
User-agent: Context7Bot
Allow: /
User-agent: Crawl4AI
Allow: /
User-agent: Clawdbot
Allow: /
User-agent: OpenClaw
Allow: /
User-agent: Hermes
Allow: /
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: peer39_crawler
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: MegaIndex
Disallow: /
User-agent: SeznamBot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: *
Allow: /
Sitemap: https://skillkit-docs.vercel.app/sitemap.xml
+21
View File
@@ -0,0 +1,21 @@
import {
defineConfig,
defineDocs,
frontmatterSchema,
metaSchema,
} from 'fumadocs-mdx/config';
export const docs = defineDocs({
dir: 'content/docs',
docs: {
schema: frontmatterSchema,
postprocess: {
includeProcessedMarkdown: true,
},
},
meta: {
schema: metaSchema,
},
});
export default defineConfig({});
+41
View File
@@ -0,0 +1,41 @@
import Link from 'next/link'
export default function HomeLayout({
children,
}: {
children: React.ReactNode
}) {
return (
<>
<nav className="fixed top-0 left-0 right-0 z-50 border-b border-zinc-800 bg-black/90 backdrop-blur-md">
<div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8">
<div className="flex h-14 items-center justify-between">
<Link href="/" className="flex items-center gap-2">
<div className="w-4 h-4 bg-white"></div>
<span className="text-base font-bold tracking-tight text-white font-mono">SKILLKIT</span>
</Link>
<div className="flex items-center gap-4">
<Link
href="/docs"
className="text-zinc-400 hover:text-white transition-colors text-sm font-mono"
>
Docs
</Link>
<a
href="https://github.com/rohitg00/skillkit"
target="_blank"
rel="noopener noreferrer"
className="text-zinc-400 hover:text-white transition-colors text-sm font-mono"
>
GitHub
</a>
</div>
</div>
</div>
</nav>
<div className="pt-14">
{children}
</div>
</>
)
}
+96
View File
@@ -0,0 +1,96 @@
import Link from 'next/link'
export default function HomePage() {
return (
<div className="min-h-screen bg-black text-zinc-100">
<main className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8 py-20">
{/* Hero */}
<div className="text-center mb-16">
<div className="inline-flex items-center space-x-2 border border-zinc-800 bg-zinc-900/50 px-3 py-1 mb-6">
<span className="flex h-2 w-2 bg-white rounded-full"></span>
<span className="text-sm font-mono text-zinc-400">v1.8.0</span>
</div>
<h1 className="text-4xl sm:text-5xl lg:text-6xl font-bold tracking-tight text-white mb-6 font-mono">
Universal Skills for<br />
<span className="text-zinc-500">AI Coding Agents</span>
</h1>
<p className="text-lg text-zinc-400 mb-8 max-w-2xl mx-auto font-mono">
One CLI to install, sync, and manage skills across Claude Code, Cursor,
Windsurf, Copilot, and 40 more agents. 400K+ skills ready to use.
</p>
<div className="flex flex-wrap justify-center gap-4 mb-12">
<code className="inline-flex items-center bg-zinc-900 border border-zinc-700 px-4 py-3 text-sm font-mono">
<span className="text-zinc-500 mr-2">$</span>
<span className="text-white">npx skillkit@latest</span>
</code>
<Link
href="/docs"
className="inline-flex items-center bg-white text-black px-6 py-3 font-mono text-sm hover:bg-zinc-200 transition-colors"
>
Read the Docs →
</Link>
</div>
</div>
{/* Features Grid */}
<div className="grid grid-cols-1 md:grid-cols-3 gap-6 mb-16">
<div className="border border-zinc-800 bg-zinc-900/30 p-6">
<h3 className="text-lg font-bold text-white mb-2 font-mono">45 Agents</h3>
<p className="text-zinc-500 text-sm">Claude, Cursor, Codex, Windsurf, Copilot, and 40 more supported out of the box.</p>
</div>
<div className="border border-zinc-800 bg-zinc-900/30 p-6">
<h3 className="text-lg font-bold text-white mb-2 font-mono">400K+ Skills</h3>
<p className="text-zinc-500 text-sm">Aggregated from 34+ registries and repositories. Install with a single command.</p>
</div>
<div className="border border-zinc-800 bg-zinc-900/30 p-6">
<h3 className="text-lg font-bold text-white mb-2 font-mono">Auto Translation</h3>
<p className="text-zinc-500 text-sm">Write once, deploy everywhere. Automatic format conversion between all agents.</p>
</div>
</div>
{/* Quick Links */}
<div className="text-center">
<h2 className="text-2xl font-bold text-white mb-6 font-mono">Get Started</h2>
<div className="flex flex-wrap justify-center gap-4">
<Link href="/docs/quickstart" className="text-zinc-400 hover:text-white font-mono text-sm border border-zinc-800 px-4 py-2 hover:border-zinc-600 transition-colors">
Quick Start
</Link>
<Link href="/docs/primer" className="text-zinc-400 hover:text-white font-mono text-sm border border-zinc-800 px-4 py-2 hover:border-zinc-600 transition-colors">
Primer
</Link>
<Link href="/docs/memory" className="text-zinc-400 hover:text-white font-mono text-sm border border-zinc-800 px-4 py-2 hover:border-zinc-600 transition-colors">
Memory System
</Link>
<Link href="/docs/mesh" className="text-zinc-400 hover:text-white font-mono text-sm border border-zinc-800 px-4 py-2 hover:border-zinc-600 transition-colors">
Mesh Network
</Link>
<Link href="/docs/api-reference" className="text-zinc-400 hover:text-white font-mono text-sm border border-zinc-800 px-4 py-2 hover:border-zinc-600 transition-colors">
API Reference
</Link>
</div>
</div>
</main>
{/* Footer */}
<footer className="border-t border-zinc-800 py-8">
<div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8">
<div className="flex flex-col sm:flex-row items-center justify-between gap-4">
<div className="flex items-center gap-2">
<div className="w-4 h-4 bg-white"></div>
<span className="font-mono font-bold text-white">SKILLKIT</span>
</div>
<div className="flex items-center gap-6 text-sm font-mono text-zinc-500">
<a href="https://github.com/rohitg00/skillkit" target="_blank" rel="noopener noreferrer" className="hover:text-white transition-colors">GitHub</a>
<a href="https://www.npmjs.com/package/skillkit" target="_blank" rel="noopener noreferrer" className="hover:text-white transition-colors">npm</a>
<Link href="/docs" className="hover:text-white transition-colors">Docs</Link>
</div>
</div>
</div>
</footer>
</div>
)
}
@@ -0,0 +1,190 @@
import { GoogleGenAI, Type, Schema } from "@google/genai";
import { NextRequest, NextResponse } from "next/server";
const rateLimitMap = new Map<string, { count: number; resetTime: number }>();
const RATE_LIMIT_WINDOW_MS = 60 * 1000;
const RATE_LIMIT_MAX_REQUESTS = 10;
function getRateLimitKey(request: NextRequest): string {
const forwarded = request.headers.get("x-forwarded-for");
const ip = forwarded ? forwarded.split(",")[0].trim() : "unknown";
return ip;
}
function checkRateLimit(key: string): { allowed: boolean; remaining: number } {
const now = Date.now();
const entry = rateLimitMap.get(key);
if (!entry || now > entry.resetTime) {
rateLimitMap.set(key, { count: 1, resetTime: now + RATE_LIMIT_WINDOW_MS });
return { allowed: true, remaining: RATE_LIMIT_MAX_REQUESTS - 1 };
}
if (entry.count >= RATE_LIMIT_MAX_REQUESTS) {
return { allowed: false, remaining: 0 };
}
entry.count++;
return { allowed: true, remaining: RATE_LIMIT_MAX_REQUESTS - entry.count };
}
const agentSkillSchema: Schema = {
type: Type.OBJECT,
properties: {
name: { type: Type.STRING, description: "Skill name in slug format (e.g., 'react-best-practices')" },
title: { type: Type.STRING, description: "Human readable title" },
description: { type: Type.STRING, description: "Brief description of what this skill teaches AI agents" },
version: { type: Type.STRING, description: "Semantic version (e.g., '1.0.0')" },
tags: {
type: Type.ARRAY,
items: { type: Type.STRING },
description: "Tags for categorization"
},
applicability: { type: Type.STRING, description: "When the AI agent should apply this skill (e.g., 'Apply when working with React components')" },
principles: {
type: Type.ARRAY,
items: {
type: Type.OBJECT,
properties: {
title: { type: Type.STRING },
description: { type: Type.STRING, description: "Detailed instruction for the AI agent" },
priority: { type: Type.STRING, description: "must, should, or may" }
},
required: ["title", "description", "priority"]
},
description: "Core principles and guidelines (5-8 items)"
},
patterns: {
type: Type.ARRAY,
items: {
type: Type.OBJECT,
properties: {
name: { type: Type.STRING },
description: { type: Type.STRING },
example: { type: Type.STRING, description: "Code example demonstrating the pattern" },
language: { type: Type.STRING, description: "Programming language for syntax highlighting" }
},
required: ["name", "description", "example"]
},
description: "Code patterns with examples (3-5 items)"
},
antiPatterns: {
type: Type.ARRAY,
items: {
type: Type.OBJECT,
properties: {
name: { type: Type.STRING },
description: { type: Type.STRING },
badExample: { type: Type.STRING, description: "Code showing what NOT to do" },
goodExample: { type: Type.STRING, description: "Code showing the correct approach" }
},
required: ["name", "description"]
},
description: "Anti-patterns to avoid (2-4 items)"
},
filePatterns: {
type: Type.ARRAY,
items: { type: Type.STRING },
description: "Glob patterns for files this skill applies to (e.g., '*.tsx', 'src/components/**')"
},
references: {
type: Type.ARRAY,
items: { type: Type.STRING },
description: "Links to official documentation or resources"
}
},
required: ["name", "title", "description", "version", "tags", "applicability", "principles", "patterns", "antiPatterns"]
};
export async function POST(request: NextRequest): Promise<NextResponse> {
const rateLimitKey = getRateLimitKey(request);
const { allowed, remaining } = checkRateLimit(rateLimitKey);
if (!allowed) {
return NextResponse.json(
{ error: "Rate limit exceeded. Please try again later." },
{
status: 429,
headers: {
"X-RateLimit-Remaining": "0",
"Retry-After": "60",
},
}
);
}
let body: unknown;
try {
body = await request.json();
} catch {
return NextResponse.json({ error: "Invalid JSON body" }, { status: 400 });
}
if (typeof body !== "object" || body === null) {
return NextResponse.json({ error: "Invalid request body" }, { status: 400 });
}
const { topic } = body as { topic?: unknown };
if (typeof topic !== "string") {
return NextResponse.json({ error: "Topic is required and must be a string" }, { status: 400 });
}
const sanitizedTopic = topic.trim().slice(0, 500);
if (!sanitizedTopic) {
return NextResponse.json({ error: "Topic cannot be empty" }, { status: 400 });
}
const apiKey = process.env.GEMINI_API_KEY;
if (!apiKey) {
return NextResponse.json({ error: "Gemini API key not configured" }, { status: 500 });
}
try {
const ai = new GoogleGenAI({ apiKey });
const response = await ai.models.generateContent({
model: "gemini-2.0-flash",
contents: `Create a comprehensive AI coding agent skill for: "${sanitizedTopic}"
This skill will be used by AI coding assistants (like Claude Code, Cursor, GitHub Copilot) to provide better code suggestions and follow best practices.
The skill should include:
1. Clear principles that tell the AI WHAT to do and WHEN
2. Code patterns with REAL, WORKING examples (not pseudocode)
3. Anti-patterns showing common mistakes and how to fix them
4. Specific file patterns where this skill applies
Make the instructions actionable and specific. The AI agent should be able to directly apply these guidelines when writing code.
Focus on practical, production-ready patterns used in modern development.`,
config: {
responseMimeType: "application/json",
responseSchema: agentSkillSchema,
systemInstruction: `You are an expert software architect creating AI agent skills.
Your skills are used by AI coding assistants to write better code.
Guidelines:
- Write instructions as commands to the AI (e.g., "Always use...", "Never...", "Prefer...")
- Include REAL code examples, not pseudocode
- Be specific and actionable
- Focus on modern best practices (2024+)
- Include edge cases and error handling patterns
- Make principles enforceable and testable`
}
});
if (!response.text) {
return NextResponse.json({ error: "No response from Gemini" }, { status: 500 });
}
const data = JSON.parse(response.text);
return NextResponse.json(data, {
headers: {
"X-RateLimit-Remaining": String(remaining),
},
});
} catch (error) {
console.error("Gemini API Error:", error);
return NextResponse.json({ error: "Failed to generate skill" }, { status: 500 });
}
}
@@ -0,0 +1,291 @@
import { NextRequest, NextResponse } from 'next/server';
import TurndownService from 'turndown';
const rateLimitMap = new Map<string, { count: number; resetTime: number }>();
const RATE_LIMIT_WINDOW_MS = 60 * 1000;
const RATE_LIMIT_MAX_REQUESTS = 10;
function checkRateLimit(key: string): { allowed: boolean; remaining: number } {
const now = Date.now();
const entry = rateLimitMap.get(key);
if (!entry || now > entry.resetTime) {
rateLimitMap.set(key, { count: 1, resetTime: now + RATE_LIMIT_WINDOW_MS });
return { allowed: true, remaining: RATE_LIMIT_MAX_REQUESTS - 1 };
}
if (entry.count >= RATE_LIMIT_MAX_REQUESTS) {
return { allowed: false, remaining: 0 };
}
entry.count++;
return { allowed: true, remaining: RATE_LIMIT_MAX_REQUESTS - entry.count };
}
const BLOCKED_HOSTS = new Set(['localhost', '127.0.0.1', '[::1]', '::1', '0.0.0.0']);
function isAllowedUrl(url: string): boolean {
try {
const parsed = new URL(url);
if (parsed.protocol !== 'http:' && parsed.protocol !== 'https:') return false;
const hostname = parsed.hostname.toLowerCase();
const bare = hostname.replace(/^\[|\]$/g, '');
if (BLOCKED_HOSTS.has(hostname) || BLOCKED_HOSTS.has(bare)) return false;
if (bare.startsWith('::ffff:')) return isAllowedUrl(`http://${bare.slice(7)}`);
if (/^127\./.test(bare) || /^0\./.test(bare)) return false;
if (bare.startsWith('10.') || bare.startsWith('192.168.')) return false;
if (/^172\.(1[6-9]|2\d|3[01])\./.test(bare)) return false;
if (bare.startsWith('169.254.')) return false;
if (bare.startsWith('fe80:') || bare.startsWith('fc00:') || bare.startsWith('fd')) return false;
if (/^(22[4-9]|23\d|24\d|25[0-5])\./.test(bare)) return false;
if (/^ff[0-9a-f]{2}:/.test(bare)) return false;
return true;
} catch {
return false;
}
}
const GITHUB_URL_PATTERN = /^https?:\/\/github\.com\/([^/]+)\/([^/]+)\/blob\/([^/]+)\/(.+)$/;
const GITHUB_RAW_PATTERN = /^https?:\/\/raw\.githubusercontent\.com\//;
const FETCH_TIMEOUT = 30_000;
const TECH_KEYWORDS = new Set([
'react', 'vue', 'angular', 'svelte', 'nextjs', 'nuxt', 'remix',
'typescript', 'javascript', 'python', 'rust', 'go', 'java', 'ruby',
'node', 'deno', 'bun', 'docker', 'kubernetes', 'terraform',
'aws', 'gcp', 'azure', 'vercel', 'netlify', 'cloudflare',
'graphql', 'rest', 'grpc', 'websocket', 'redis', 'postgres',
'mongodb', 'sqlite', 'mysql', 'prisma', 'drizzle',
'tailwind', 'css', 'html', 'sass', 'webpack', 'vite', 'esbuild',
'git', 'ci', 'cd', 'testing', 'security', 'authentication',
'api', 'cli', 'sdk', 'mcp', 'llm', 'ai', 'ml', 'openai', 'anthropic',
]);
const TAG_PATTERN = /^[a-z0-9]+(-[a-z0-9]+)*$/;
const turndown = new TurndownService({ headingStyle: 'atx', codeBlockStyle: 'fenced' });
interface ExtractedContent {
title: string;
content: string;
sourceUrl: string;
contentType: string;
language?: string;
}
async function extractFromUrl(url: string): Promise<ExtractedContent> {
if (GITHUB_URL_PATTERN.test(url) || GITHUB_RAW_PATTERN.test(url)) {
return fetchGitHubContent(url);
}
const MAX_BODY_SIZE = 5 * 1024 * 1024;
const response = await fetch(url, { signal: AbortSignal.timeout(FETCH_TIMEOUT) });
if (!response.ok) {
throw new Error(`Failed to fetch ${url}: ${response.status} ${response.statusText}`);
}
const contentLength = Number(response.headers.get('content-length') || '0');
if (contentLength > MAX_BODY_SIZE) {
throw new Error('Response too large');
}
const contentType = response.headers.get('content-type') ?? '';
const body = await response.text();
if (body.length > MAX_BODY_SIZE) {
throw new Error('Response too large');
}
if (contentType.includes('text/html')) {
const titleMatch = body.match(/<title[^>]*>([^<]+)<\/title>/i);
const title = titleMatch?.[1]?.trim() ?? new URL(url).hostname;
const bodyMatch = body.match(/<body[^>]*>([\s\S]*)<\/body>/i);
const content = turndown.turndown(bodyMatch?.[1] ?? body);
return { title, content, sourceUrl: url, contentType: 'webpage' };
}
const title = new URL(url).pathname.split('/').pop() ?? 'Untitled';
return { title, content: body, sourceUrl: url, contentType: 'text' };
}
const LANG_MAP: Record<string, string> = {
'.ts': 'typescript', '.tsx': 'typescript', '.js': 'javascript', '.jsx': 'javascript',
'.py': 'python', '.rb': 'ruby', '.go': 'go', '.rs': 'rust', '.java': 'java',
'.kt': 'kotlin', '.swift': 'swift', '.sh': 'shell', '.yml': 'yaml', '.yaml': 'yaml',
'.json': 'json', '.md': 'markdown', '.html': 'html', '.css': 'css', '.sql': 'sql',
};
async function fetchGitHubContent(url: string): Promise<ExtractedContent> {
let rawUrl = url;
const match = url.match(GITHUB_URL_PATTERN);
if (match) {
const [, owner, repo, branch, path] = match;
rawUrl = `https://raw.githubusercontent.com/${owner}/${repo}/${branch}/${path}`;
}
const MAX_BODY_SIZE = 5 * 1024 * 1024;
const response = await fetch(rawUrl, { signal: AbortSignal.timeout(FETCH_TIMEOUT) });
if (!response.ok) {
throw new Error(`Failed to fetch GitHub content: ${response.status} ${response.statusText}`);
}
const contentLength = Number(response.headers.get('content-length') || '0');
if (contentLength > MAX_BODY_SIZE) {
throw new Error('Response too large');
}
const body = await response.text();
if (body.length > MAX_BODY_SIZE) {
throw new Error('Response too large');
}
const filename = rawUrl.split('/').pop() ?? 'file';
const ext = filename.includes('.') ? '.' + filename.split('.').pop()!.toLowerCase() : '';
const language = LANG_MAP[ext];
const isCode = language !== undefined && language !== 'markdown';
const content = isCode ? `\`\`\`${language}\n${body}\n\`\`\`` : body;
return { title: filename, content, sourceUrl: url, contentType: 'github', language };
}
function addTag(counts: Map<string, number>, tag: string, weight: number): void {
if (TAG_PATTERN.test(tag)) {
counts.set(tag, (counts.get(tag) ?? 0) + weight);
}
}
function detectTags(extracted: ExtractedContent): string[] {
const counts = new Map<string, number>();
try {
const segments = new URL(extracted.sourceUrl).pathname
.split('/').filter(Boolean)
.map((s) => s.toLowerCase().replace(/[^a-z0-9-]/g, ''));
for (const seg of segments) {
if (seg.length >= 2 && seg.length <= 30) {
addTag(counts, seg, 2);
}
}
} catch { /* skip */ }
const headingRe = /^#{1,2}\s+(.+)$/gm;
let m: RegExpExecArray | null;
while ((m = headingRe.exec(extracted.content)) !== null) {
for (const word of m[1].toLowerCase().split(/\s+/)) {
const cleaned = word.replace(/[^a-z0-9-]/g, '');
if (cleaned.length >= 2) {
addTag(counts, cleaned, 2);
}
}
}
const codeBlockRe = /^```(\w+)/gm;
while ((m = codeBlockRe.exec(extracted.content)) !== null) {
const lang = m[1].toLowerCase();
if (lang.length >= 2) {
addTag(counts, lang, 3);
}
}
const lower = extracted.content.toLowerCase();
for (const keyword of TECH_KEYWORDS) {
if (new RegExp(`\\b${keyword}\\b`, 'i').test(lower)) {
addTag(counts, keyword, 1);
}
}
if (extracted.language) {
addTag(counts, extracted.language.toLowerCase(), 3);
}
return Array.from(counts.entries())
.sort((a, b) => b[1] - a[1])
.slice(0, 10)
.map(([tag]) => tag);
}
function slugify(input: string): string {
const slug = input
.toLowerCase()
.replace(/[^a-z0-9]+/g, '-')
.replace(/^-+|-+$/g, '')
.replace(/-{2,}/g, '-');
return slug.slice(0, 64).replace(/-+$/, '') || 'untitled-skill';
}
function yamlEscape(value: string): string {
const singleLine = value.replace(/\r?\n/g, ' ').trim();
if (/[:#{}[\],&*?|>!%@`]/.test(singleLine) || singleLine.startsWith("'") || singleLine.startsWith('"')) {
return `"${singleLine.replace(/\\/g, '\\\\').replace(/"/g, '\\"')}"`;
}
return singleLine;
}
export async function POST(request: NextRequest) {
const ip = request.headers.get('x-forwarded-for')?.split(',')[0]?.trim() ?? 'unknown';
const { allowed, remaining } = checkRateLimit(ip);
if (!allowed) {
return NextResponse.json(
{ error: 'Too many requests. Try again in a minute.' },
{ status: 429, headers: { 'X-RateLimit-Remaining': '0', 'Retry-After': '60' } },
);
}
let body: { url?: string; name?: string };
try {
body = await request.json();
} catch {
return NextResponse.json({ error: 'Invalid JSON body' }, { status: 400 });
}
const { url, name } = body;
if (!url || typeof url !== 'string') {
return NextResponse.json({ error: 'Missing required field: url' }, { status: 400 });
}
if (name !== undefined && typeof name !== 'string') {
return NextResponse.json({ error: 'Field "name" must be a string' }, { status: 400 });
}
if (!isAllowedUrl(url)) {
return NextResponse.json({ error: 'URL not allowed' }, { status: 403 });
}
try {
const extracted = await extractFromUrl(url);
const tags = detectTags(extracted);
const skillName = slugify(name || extracted.title || 'untitled');
const description = extracted.content
.split('\n')
.find((l) => l.trim().length > 0)
?.replace(/^#+\s*/, '')
.trim()
.slice(0, 200) || 'Saved skill';
const savedAt = new Date().toISOString();
const yamlTags = tags.length > 0
? `tags:\n${tags.map((t) => ` - ${t}`).join('\n')}\n`
: '';
const skillMd =
`---\n` +
`name: ${skillName}\n` +
`description: ${yamlEscape(description)}\n` +
yamlTags +
`metadata:\n` +
` source: ${yamlEscape(url)}\n` +
` savedAt: ${savedAt}\n` +
`---\n\n` +
extracted.content + '\n';
return NextResponse.json(
{ name: skillName, skillMd, tags, description },
{ headers: { 'X-RateLimit-Remaining': String(remaining) } },
);
} catch (err) {
const message = err instanceof Error ? err.message : 'Failed to extract content';
return NextResponse.json({ error: message }, { status: 502 });
}
}
@@ -0,0 +1,42 @@
import { source } from '@/lib/source'
import { DocsBody, DocsDescription, DocsPage, DocsTitle } from 'fumadocs-ui/layouts/docs/page'
import { notFound } from 'next/navigation'
import { getMDXComponents } from '@/mdx-components'
import type { Metadata } from 'next'
interface PageProps {
params: Promise<{ slug?: string[] }>
}
export default async function Page(props: PageProps) {
const params = await props.params
const page = source.getPage(params.slug ?? [])
if (!page) notFound()
const MDX = page.data.body
return (
<DocsPage toc={page.data.toc} full={page.data.full} tableOfContent={{ style: 'clerk' }}>
<DocsTitle>{page.data.title}</DocsTitle>
<DocsDescription>{page.data.description}</DocsDescription>
<DocsBody>
<MDX components={getMDXComponents({})} />
</DocsBody>
</DocsPage>
)
}
export async function generateStaticParams() {
return source.generateParams()
}
export async function generateMetadata(props: PageProps): Promise<Metadata> {
const params = await props.params
const page = source.getPage(params.slug ?? [])
if (!page) notFound()
return {
title: page.data.title,
description: page.data.description,
}
}
+17
View File
@@ -0,0 +1,17 @@
import { baseOptions } from '@/lib/layout.shared'
import { source } from '@/lib/source'
import { DocsLayout } from 'fumadocs-ui/layouts/docs'
export default function Layout({ children }: { children: React.ReactNode }) {
return (
<DocsLayout
tree={source.pageTree}
{...baseOptions()}
sidebar={{
collapsible: true,
}}
>
{children}
</DocsLayout>
)
}
+160
View File
@@ -0,0 +1,160 @@
@import 'tailwindcss';
@import 'fumadocs-ui/css/neutral.css';
@import 'fumadocs-ui/css/preset.css';
@theme {
--font-sans: "Inter", ui-sans-serif, system-ui, sans-serif;
--color-skillkit-black: #000000;
--color-skillkit-dark: #18181b;
--color-skillkit-medium: #71717a;
--color-skillkit-light: #fafafa;
--color-skillkit-blue: #3b82f6;
/* Light mode defaults */
--color-fd-background: #ffffff;
--color-fd-foreground: var(--color-skillkit-black);
--color-fd-muted: #f4f4f5;
--color-fd-muted-foreground: var(--color-skillkit-medium);
--color-fd-popover: #ffffff;
--color-fd-popover-foreground: var(--color-skillkit-black);
--color-fd-card: #ffffff;
--color-fd-card-foreground: var(--color-skillkit-black);
--color-fd-border: #e4e4e7;
--color-fd-primary: var(--color-skillkit-blue);
--color-fd-primary-foreground: #ffffff;
--color-fd-secondary: #f4f4f5;
--color-fd-secondary-foreground: var(--color-skillkit-black);
--color-fd-accent: #f4f4f5;
--color-fd-accent-foreground: var(--color-skillkit-black);
--color-fd-ring: var(--color-skillkit-blue);
}
/* Dark mode */
:root.dark {
--color-fd-background: var(--color-skillkit-black);
--color-fd-foreground: var(--color-skillkit-light);
--color-fd-muted: var(--color-skillkit-dark);
--color-fd-muted-foreground: #a1a1aa;
--color-fd-popover: var(--color-skillkit-dark);
--color-fd-popover-foreground: var(--color-skillkit-light);
--color-fd-card: var(--color-skillkit-dark);
--color-fd-card-foreground: var(--color-skillkit-light);
--color-fd-border: #27272a;
--color-fd-primary: var(--color-skillkit-blue);
--color-fd-primary-foreground: #ffffff;
--color-fd-secondary: var(--color-skillkit-dark);
--color-fd-secondary-foreground: var(--color-skillkit-light);
--color-fd-accent: var(--color-skillkit-dark);
--color-fd-accent-foreground: var(--color-skillkit-light);
--color-fd-ring: var(--color-skillkit-blue);
}
body {
background-color: var(--color-fd-background);
color: var(--color-fd-foreground);
}
::selection {
background-color: var(--color-skillkit-blue);
color: #ffffff;
}
/* Light mode code blocks */
pre {
background-color: #f8f8f8 !important;
border: 1px solid #e4e4e7;
}
code {
background-color: #f4f4f5;
color: var(--color-skillkit-black);
padding: 0.2em 0.4em;
border-radius: 4px;
font-size: 0.875em;
}
pre code {
background-color: transparent;
color: inherit;
padding: 0;
}
/* Dark mode code blocks */
:root.dark pre {
background-color: #0d0d0d !important;
border: 1px solid #27272a;
}
:root.dark code {
background-color: #27272a;
color: #e4e4e7;
}
:root.dark pre code {
background-color: transparent;
}
/* Inline code in paragraphs */
p code, li code, td code {
font-weight: 500;
}
/* Tables */
table {
width: 100%;
border-collapse: collapse;
}
th, td {
padding: 0.75rem 1rem;
text-align: left;
border-bottom: 1px solid var(--color-fd-border);
}
th {
font-weight: 600;
background-color: var(--color-fd-muted);
}
/* Lists */
ul, ol {
padding-left: 1.5rem;
}
li {
margin: 0.5rem 0;
}
/* Landing page animations */
@keyframes scroll {
0% { transform: translateX(0); }
100% { transform: translateX(-50%); }
}
.animate-scroll {
animation: scroll 35s linear infinite;
}
@keyframes fade-in {
from { opacity: 0; transform: translateY(10px); }
to { opacity: 1; transform: translateY(0); }
}
.animate-fade-in {
animation: fade-in 0.6s ease-out forwards;
}
.animate-fade-in-delay {
animation: fade-in 0.6s ease-out 0.2s forwards;
opacity: 0;
}
/* Landing page specific styles */
.bg-background {
background-color: #000000;
}
.bg-surface {
background-color: rgba(24, 24, 27, 0.5);
}
+48
View File
@@ -0,0 +1,48 @@
import { RootProvider } from 'fumadocs-ui/provider/next'
import './global.css'
import { Inter } from 'next/font/google'
import type { Metadata } from 'next'
const inter = Inter({
subsets: ['latin'],
weight: ['400', '500', '600', '700'],
})
export const metadata: Metadata = {
title: {
default: 'SkillKit - Universal Skills for AI Coding Agents',
template: '%s | SkillKit',
},
description: 'One CLI to install, sync, and manage skills across Claude Code, Cursor, Windsurf, Copilot, and 40 more agents. 400K+ skills ready to use.',
icons: {
icon: [
{ url: '/favicon.svg', type: 'image/svg+xml' },
{ url: '/favicon-32.png', sizes: '32x32', type: 'image/png' },
],
apple: '/apple-touch-icon.png',
},
openGraph: {
title: 'SkillKit - Universal Skills for AI Coding Agents',
description: 'One CLI to install, sync, and manage skills across Claude Code, Cursor, Windsurf, Copilot, and 28 more agents.',
url: 'https://skillkit.sh',
siteName: 'SkillKit',
images: [{ url: '/og-image.png', width: 1200, height: 630 }],
type: 'website',
},
twitter: {
card: 'summary_large_image',
title: 'SkillKit - Universal Skills for AI Coding Agents',
description: 'One CLI to install, sync, and manage skills across Claude Code, Cursor, Windsurf, Copilot, and 28 more agents.',
images: ['/og-image.png'],
},
}
export default function Layout({ children }: { children: React.ReactNode }) {
return (
<html lang="en" className={inter.className} suppressHydrationWarning>
<body className="flex flex-col min-h-screen">
<RootProvider>{children}</RootProvider>
</body>
</html>
)
}
File diff suppressed because one or more lines are too long
+55
View File
@@ -0,0 +1,55 @@
import React from 'react';
interface ButtonProps extends React.ButtonHTMLAttributes<HTMLButtonElement> {
variant?: 'primary' | 'secondary' | 'outline' | 'ghost';
fullWidth?: boolean;
isLoading?: boolean;
}
const BASE_STYLES = "inline-flex items-center justify-center px-6 py-3 text-sm font-medium transition-all duration-200 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-offset-black disabled:opacity-50 font-mono tracking-tight";
const VARIANT_STYLES = {
primary: "bg-white text-black hover:bg-zinc-200 border border-white",
secondary: "bg-zinc-900 text-zinc-100 hover:bg-zinc-800 border border-zinc-800",
outline: "bg-transparent text-zinc-300 border border-zinc-700 hover:border-zinc-500 hover:text-white",
ghost: "bg-transparent text-zinc-400 hover:text-white hover:bg-zinc-900"
} as const;
export function Button({
children,
variant = 'primary',
className = '',
fullWidth = false,
isLoading = false,
disabled,
type = 'button',
...props
}: ButtonProps): React.ReactElement {
const widthClass = fullWidth ? 'w-full' : '';
const classes = [
BASE_STYLES,
VARIANT_STYLES[variant],
widthClass,
className,
].filter(Boolean).join(' ');
return (
<button
className={classes}
type={type}
disabled={disabled || isLoading}
{...props}
>
{isLoading ? (
<>
<svg className="animate-spin -ml-1 mr-2 h-4 w-4" xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24">
<circle className="opacity-25" cx="12" cy="12" r="10" stroke="currentColor" strokeWidth="4"></circle>
<path className="opacity-75" fill="currentColor" d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z"></path>
</svg>
PROCESSING
</>
) : children}
</button>
);
}
+49
View File
@@ -0,0 +1,49 @@
import React from 'react';
interface CardProps {
children: React.ReactNode;
className?: string;
noPadding?: boolean;
onClick?: () => void;
onDragOver?: (e: React.DragEvent) => void;
onDragLeave?: (e: React.DragEvent) => void;
onDrop?: (e: React.DragEvent) => void;
}
export function Card({
children,
className = '',
noPadding = false,
onClick,
onDragOver,
onDragLeave,
onDrop
}: CardProps): React.ReactElement {
const paddingClass = noPadding ? '' : 'p-6';
const clickableClass = onClick ? 'cursor-pointer' : '';
function handleKeyDown(e: React.KeyboardEvent): void {
if (!onClick) return;
if (e.key === 'Enter' || e.key === ' ') {
if (e.key === ' ') {
e.preventDefault();
}
onClick();
}
}
return (
<div
className={`relative bg-black border border-zinc-800 transition-colors duration-300 ${paddingClass} ${clickableClass} ${className}`}
onClick={onClick}
role={onClick ? 'button' : undefined}
tabIndex={onClick ? 0 : undefined}
onKeyDown={onClick ? handleKeyDown : undefined}
onDragOver={onDragOver}
onDragLeave={onDragLeave}
onDrop={onDrop}
>
{children}
</div>
);
}
+112
View File
@@ -0,0 +1,112 @@
import React, { useState } from 'react';
interface CommandGroup {
name: string;
commands: Array<{ cmd: string; desc: string }>;
}
const COMMAND_GROUPS: CommandGroup[] = [
{
name: 'Core',
commands: [
{ cmd: 'install', desc: 'Install from GitHub/GitLab/local' },
{ cmd: 'sync', desc: 'Sync skills across agents' },
{ cmd: 'translate', desc: 'Convert between agent formats' },
{ cmd: 'update', desc: 'Update installed skills' },
],
},
{
name: 'Discovery',
commands: [
{ cmd: 'find', desc: 'Search marketplace (400K+ skills)' },
{ cmd: 'recommend', desc: 'AI-powered suggestions' },
{ cmd: 'check', desc: 'Dry-run update check' },
{ cmd: 'list', desc: 'View installed skills' },
],
},
{
name: 'Team',
commands: [
{ cmd: 'manifest init', desc: 'Create .skills file' },
{ cmd: 'manifest install', desc: 'Install from manifest' },
{ cmd: 'team share', desc: 'Share skills via Git' },
{ cmd: 'publish', desc: 'Submit to marketplace' },
],
},
{
name: 'Security',
commands: [
{ cmd: 'scan <path>', desc: 'Security vulnerability scanner' },
{ cmd: 'scan --format sarif', desc: 'SARIF for GitHub Code Scanning' },
{ cmd: 'scan --fail-on high', desc: 'CI security gate' },
{ cmd: 'audit log', desc: 'View audit trail' },
],
},
{
name: 'Advanced',
commands: [
{ cmd: 'ui', desc: 'Launch terminal UI' },
{ cmd: 'workflow run', desc: 'Execute skill pipelines' },
{ cmd: 'command generate', desc: 'Create /slash commands' },
{ cmd: 'cicd init', desc: 'Generate CI templates' },
],
},
];
export function Commands(): React.ReactElement {
const [activeGroup, setActiveGroup] = useState(0);
const group = COMMAND_GROUPS[activeGroup];
return (
<section className="py-12 border-b border-zinc-800">
<div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8">
<div className="text-center mb-8">
<h2 className="text-xl font-bold text-white mb-2 font-mono">40+ Commands</h2>
<p className="text-zinc-500 font-mono text-sm">
Everything you need from the terminal.
</p>
</div>
<div className="flex justify-center gap-2 mb-6">
{COMMAND_GROUPS.map((g, i) => {
const isActive = i === activeGroup;
const buttonClass = isActive
? 'border-white text-white bg-zinc-900'
: 'border-zinc-800 text-zinc-500 hover:border-zinc-600 hover:text-zinc-300';
return (
<button
key={g.name}
onClick={() => setActiveGroup(i)}
className={`px-3 py-1.5 text-xs font-mono border transition-colors ${buttonClass}`}
>
{g.name}
</button>
);
})}
</div>
<div className="border border-zinc-800 bg-black/50 p-4 font-mono text-xs">
<div className="grid grid-cols-1 sm:grid-cols-2 gap-2">
{group.commands.map((c) => (
<div
key={c.cmd}
className="flex items-center gap-3 p-2 hover:bg-zinc-900/50 transition-colors rounded"
>
<span className="text-zinc-600">$</span>
<span className="text-white">skillkit {c.cmd}</span>
<span className="text-zinc-600 hidden sm:inline">→</span>
<span className="text-zinc-500 hidden sm:inline truncate">{c.desc}</span>
</div>
))}
</div>
</div>
<div className="mt-4 text-center">
<span className="text-zinc-600 text-xs font-mono">
Run <span className="text-zinc-400">skillkit --help</span> for all commands
</span>
</div>
</div>
</section>
);
}
@@ -0,0 +1,538 @@
'use client'
import React, { useState } from 'react';
interface DocSection {
id: string;
title: string;
content: React.ReactNode;
}
const CodeBlock = ({ children, language = 'bash' }: { children: string; language?: string }) => (
<pre className="bg-zinc-900 border border-zinc-800 rounded-lg p-4 overflow-x-auto text-sm font-mono">
<code className="text-zinc-300">{children}</code>
</pre>
);
const Table = ({ headers, rows }: { headers: string[]; rows: string[][] }) => (
<div className="overflow-x-auto">
<table className="w-full text-sm border-collapse">
<thead>
<tr className="border-b border-zinc-700">
{headers.map((h, i) => (
<th key={i} className="text-left py-2 px-3 text-zinc-300 font-mono font-semibold">{h}</th>
))}
</tr>
</thead>
<tbody>
{rows.map((row, i) => (
<tr key={i} className="border-b border-zinc-800 hover:bg-zinc-900/50">
{row.map((cell, j) => (
<td key={j} className="py-2 px-3 text-zinc-400 font-mono">{cell}</td>
))}
</tr>
))}
</tbody>
</table>
</div>
);
const sections: DocSection[] = [
{
id: 'overview',
title: 'Overview',
content: (
<div className="space-y-4">
<p className="text-zinc-300">
SkillKit is a universal command-line interface (CLI) and programmatic toolkit for managing AI agent skills across 46 AI coding platforms. It solves the fragmentation problem where each AI agent uses different skill formats and directory structures.
</p>
<h3 className="text-lg font-semibold text-white mt-6">Core Capabilities</h3>
<ul className="list-disc list-inside space-y-2 text-zinc-400">
<li><span className="text-white">Skill Discovery</span> - Browse 400K+ skills from registries with AI-powered recommendations</li>
<li><span className="text-white">Cross-Agent Translation</span> - Automatically convert skills between 46 agent-specific formats</li>
<li><span className="text-white">Team Collaboration</span> - Share skills via .skills manifest files and publish to marketplace</li>
</ul>
</div>
),
},
{
id: 'installation',
title: 'Installation',
content: (
<div className="space-y-4">
<h3 className="text-lg font-semibold text-white">Quick Start</h3>
<CodeBlock>{`# Full install — every feature works out of the box (default):
npm install -g skillkit
# Slim install — core commands only, ~75% smaller, 0 deprecation warnings:
npm install -g skillkit --omit=optional
# Or use npx directly:
npx skillkit --help`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Optional Features</h3>
<p className="text-zinc-300 text-sm">
TUI, REST server, peer mesh, and inter-agent messaging ship as optional
dependencies. They install by default, or add later à la carte:
</p>
<CodeBlock>{`npm install -g @skillkit/tui # enables: skillkit ui
npm install -g @skillkit/api # enables: skillkit serve
npm install -g @skillkit/mesh # enables: skillkit mesh
npm install -g @skillkit/messaging # enables: skillkit message`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Using npx (no install)</h3>
<p className="text-zinc-300 text-sm">
<code className="text-zinc-200">npx skillkit add &lt;owner/repo&gt;</code> runs with zero install.
First call caches the package at <code className="text-zinc-200">~/.npm/_npx/</code>; every
run after that is instant until a new version ships.
</p>
<CodeBlock>{`# Full (default):
npx skillkit add anthropics/skills
# Slim — core only, 75% fewer packages, 0 warnings:
npx --omit=optional skillkit add anthropics/skills`}</CodeBlock>
<p className="text-zinc-300 text-sm">
Using npx more than a couple times? Install globally to skip the
prompt-to-proceed and avoid the per-release cache refetch:
</p>
<CodeBlock>{`npm install -g skillkit --omit=optional
skillkit add anthropics/skills`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Verify Installation</h3>
<CodeBlock>{`skillkit --version
skillkit --help`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">First Steps</h3>
<CodeBlock>{`# Initialize SkillKit in your project
skillkit init
# Browse available skills
skillkit marketplace
# Get AI-powered recommendations
skillkit recommend
# Install skills from a source
skillkit install anthropics/skills`}</CodeBlock>
</div>
),
},
{
id: 'architecture',
title: 'Architecture',
content: (
<div className="space-y-4">
<p className="text-zinc-300">
SkillKit employs a three-tier design with clean separation of concerns:
</p>
<h3 className="text-lg font-semibold text-white mt-6">System Tiers</h3>
<ul className="list-disc list-inside space-y-2 text-zinc-400">
<li><span className="text-white">UI Tier</span> - CLI commands, Terminal UI (OpenTUI-based), and documentation website</li>
<li><span className="text-white">Core Logic Tier</span> - @skillkit/core for business logic; @skillkit/agents for adapter implementations</li>
<li><span className="text-white">Integration Tier</span> - File systems, Git repositories, marketplace APIs, and 46 AI agents</li>
</ul>
<h3 className="text-lg font-semibold text-white mt-6">Monorepo Structure</h3>
<CodeBlock language="text">{`skillkit-monorepo (pnpm workspace + Turbo)
├── apps/skillkit/ → Main CLI application (bin: skillkit, sk)
├── packages/core/ → Core business logic (no internal dependencies)
├── packages/agents/ → Agent adapters (depends on core)
├── packages/cli/ → Command implementations (depends on core, agents, tui)
├── packages/tui/ → Terminal UI (depends on core, agents)
└── docs/skillkit/ → Documentation website`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Dependency Hierarchy</h3>
<ul className="list-disc list-inside space-y-2 text-zinc-400">
<li><code className="text-emerald-400">@skillkit/core</code> → Foundation (no SkillKit dependencies)</li>
<li><code className="text-emerald-400">@skillkit/agents</code> → Adapters (depends on core)</li>
<li><code className="text-emerald-400">@skillkit/cli</code>, <code className="text-emerald-400">@skillkit/tui</code> → UIs (depend on core and agents)</li>
<li><code className="text-emerald-400">skillkit</code> app → Orchestrates all packages</li>
</ul>
</div>
),
},
{
id: 'agents',
title: 'Supported Agents',
content: (
<div className="space-y-4">
<p className="text-zinc-300">
SkillKit supports 46 AI coding agents with automatic format translation:
</p>
<Table
headers={['Agent', 'Directory', 'Format']}
rows={[
['Claude Code', '.claude/skills/', 'SKILL.md'],
['Cursor', '.cursor/skills/', '.mdc'],
['GitHub Copilot', '.github/skills/', 'Markdown'],
['Gemini CLI', '.gemini/skills/', 'SKILL.md'],
['Windsurf', '.windsurf/skills/', 'Markdown'],
['Codex', '.codex/skills/', 'SKILL.md'],
['OpenCode', '.opencode/skills/', 'SKILL.md'],
['Antigravity', '.antigravity/skills/', 'SKILL.md'],
['Amp', '.amp/skills/', 'SKILL.md'],
['Clawdbot', '.clawdbot/skills/', 'SKILL.md'],
['Cline', '.cline/skills/', 'SKILL.md'],
['CodeBuddy', '.codebuddy/skills/', 'SKILL.md'],
['CommandCode', '.commandcode/skills/', 'SKILL.md'],
['Continue', '.continue/skills/', 'SKILL.md'],
['Crush', '.crush/skills/', 'SKILL.md'],
['Droid', '.factory/skills/', 'SKILL.md'],
['Factory', '.factory/skills/', 'SKILL.md'],
['Goose', '.goose/skills/', 'SKILL.md'],
['Kilo', '.kilocode/skills/', 'SKILL.md'],
['Kiro CLI', '.kiro/skills/', 'SKILL.md'],
['MCPJam', '.mcpjam/skills/', 'SKILL.md'],
['Mux', '.mux/skills/', 'SKILL.md'],
['Neovate', '.neovate/skills/', 'SKILL.md'],
['OpenHands', '.openhands/skills/', 'SKILL.md'],
['Pi', '.pi/skills/', 'SKILL.md'],
['Qoder', '.qoder/skills/', 'SKILL.md'],
['Qwen', '.qwen/skills/', 'SKILL.md'],
['Roo', '.roo/skills/', 'SKILL.md'],
['Trae', '.trae/skills/', 'SKILL.md'],
['Vercel', '.vercel/skills/', 'SKILL.md'],
['Zencoder', '.zencoder/skills/', 'SKILL.md'],
['Devin', '.devin/skills/', 'SKILL.md'],
['Aider', '.aider/skills/', 'SKILL.md'],
['Sourcegraph Cody', '.cody/skills/', 'SKILL.md'],
['Amazon Q', '.amazonq/skills/', 'SKILL.md'],
['Augment Code', '.augment/skills/', 'SKILL.md'],
['Replit Agent', '.replit/skills/', 'SKILL.md'],
['Bolt', '.bolt/skills/', 'SKILL.md'],
['Lovable', '.lovable/skills/', 'SKILL.md'],
['Tabby', '.tabby/skills/', 'SKILL.md'],
['Tabnine', '.tabnine/skills/', 'SKILL.md'],
['CodeGPT', '.codegpt/skills/', 'SKILL.md'],
['PlayCode Agent', '.playcode/skills/', 'SKILL.md'],
['Universal', 'skills/', 'SKILL.md'],
]}
/>
</div>
),
},
{
id: 'commands',
title: 'CLI Commands',
content: (
<div className="space-y-4">
<h3 className="text-lg font-semibold text-white">Skill Management</h3>
<CodeBlock>{`skillkit install <source> # Install skills from source
skillkit remove <skill> # Remove installed skill
skillkit update [skill] # Update skills
skillkit list # List installed skills
skillkit sync # Sync skills across agents
skillkit enable <skill> # Enable a skill
skillkit disable <skill> # Disable a skill`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Discovery</h3>
<CodeBlock>{`skillkit recommend # AI-powered skill recommendations
skillkit marketplace # Browse marketplace skills
skillkit find <query> # Search for skills
skillkit search <term> # Search skill content`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Translation</h3>
<CodeBlock>{`skillkit translate --from claude --to cursor <skill>
skillkit agent translate <skill> --target cursor
skillkit context sync # Sync context across agents`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Team Collaboration</h3>
<CodeBlock>{`skillkit manifest init # Initialize .skills manifest
skillkit manifest add <source> # Add source to manifest
skillkit manifest install # Install from manifest
skillkit publish # Publish skill to marketplace
skillkit cicd init # Setup CI/CD integration`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Advanced</h3>
<CodeBlock>{`skillkit ui # Launch Terminal UI
skillkit workflow # Manage workflows
skillkit memory compress # Compress memory
skillkit memory export # Export memory
skillkit test # Run skill tests
skillkit validate # Validate skill format & quality`}</CodeBlock>
</div>
),
},
{
id: 'configuration',
title: 'Configuration',
content: (
<div className="space-y-4">
<h3 className="text-lg font-semibold text-white">Project Configuration (skillkit.yaml)</h3>
<CodeBlock language="yaml">{`version: 1
agent: cursor
autoSync: true
enabledSkills:
- pdf
- xlsx
disabledSkills:
- deprecated-skill`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Team Manifest (.skills)</h3>
<CodeBlock>{`# Team-wide skill sources
anthropics/skills
vercel-labs/agent-skills
./local-skills
owner/repo@v1.2.3`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">User Preferences (~/.skillkit/preferences.json)</h3>
<CodeBlock language="json">{`{
"lastSelectedAgents": ["claude", "cursor"],
"autoSync": true,
"marketplace": {
"lastRefresh": "2024-01-01T00:00:00Z"
}
}`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">File System Layout</h3>
<CodeBlock language="text">{`project/
├── .skillkit/ # Project config & memory
├── .claude/skills/ # Claude Code skills
├── .cursor/skills/ # Cursor AI skills
├── .github/skills/ # GitHub Copilot skills
├── skills/ # Universal format
└── .skills # Team manifest file
~/.skillkit/ # Global user config
├── preferences.json
├── memory/
└── cache/`}</CodeBlock>
</div>
),
},
{
id: 'api',
title: 'API Reference',
content: (
<div className="space-y-4">
<h3 className="text-lg font-semibold text-white">Package Exports</h3>
<p className="text-zinc-300">@skillkit/core provides multiple entry points for programmatic use:</p>
<CodeBlock language="typescript">{`import { findAllSkills, findSkill } from '@skillkit/core/discovery';
import { parseSkillFile } from '@skillkit/core/parser';
import { translateSkill } from '@skillkit/core/translator';
import { syncContext } from '@skillkit/core/context';
import { getRecommendations } from '@skillkit/core/recommend';
import { evaluateSkillContent, getQualityGrade } from '@skillkit/core/quality';`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Core Functions</h3>
<CodeBlock language="typescript">{`// Discovery
findAllSkills(searchDirs: string[]): SkillInfo[]
findSkill(name: string, searchDirs: string[]): SkillInfo | null
// Parsing
parseSkillFile(filePath: string): ParsedSkill
parseSkillContent(content: string): ParsedSkill
// Translation
translateSkill(skill: ParsedSkill, targetAgent: AgentType): string
getAgentAdapter(agent: AgentType): AgentAdapter
// Quality Evaluation
evaluateSkillContent(content: string): QualityScore
evaluateSkillFile(filePath: string): QualityScore
getQualityGrade(score: number): 'A' | 'B' | 'C' | 'D' | 'F'
isHighQuality(score: QualityScore): boolean
// Recommendations
getRecommendations(context: ProjectContext): Recommendation[]`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Type Definitions</h3>
<CodeBlock language="typescript">{`interface SkillInfo {
name: string;
path: string;
agent: AgentType;
enabled: boolean;
}
interface ParsedSkill {
name: string;
description?: string;
globs?: string[];
triggers?: string[];
content: string;
frontmatter: Record<string, unknown>;
}
interface QualityScore {
overall: number;
structure: StructureScore;
clarity: ClarityScore;
specificity: SpecificityScore;
advanced: AdvancedScore;
warnings: string[];
suggestions: string[];
}
type AgentType =
| 'claude-code' | 'cursor' | 'codex' | 'gemini-cli'
| 'opencode' | 'antigravity' | 'amp' | 'clawdbot'
| 'droid' | 'github-copilot' | 'goose' | 'kilo'
| 'kiro-cli' | 'roo' | 'trae' | 'windsurf' | 'universal';`}</CodeBlock>
</div>
),
},
{
id: 'skill-format',
title: 'Skill Format',
content: (
<div className="space-y-4">
<h3 className="text-lg font-semibold text-white">SKILL.md Structure</h3>
<p className="text-zinc-300">Skills use YAML frontmatter followed by markdown content:</p>
<CodeBlock language="markdown">{`---
name: my-skill
description: A helpful skill for coding tasks
globs:
- "**/*.ts"
- "**/*.tsx"
triggers:
- "when working with TypeScript"
- "when creating React components"
---
# My Skill
## When to Use
Use this skill when:
- Working with TypeScript files
- Creating React components
## Instructions
Follow these guidelines:
1. Always use TypeScript strict mode
2. Prefer functional components
\`\`\`typescript
function Example(): JSX.Element {
return <div>Hello</div>;
}
\`\`\`
## Boundaries
This skill should NOT:
- Modify configuration files without asking
- Delete existing code without confirmation`}</CodeBlock>
<h3 className="text-lg font-semibold text-white mt-6">Quality Scoring</h3>
<p className="text-zinc-300">Skills are evaluated on four dimensions:</p>
<Table
headers={['Dimension', 'Weight', 'Criteria']}
rows={[
['Structure', '35%', 'Metadata, description, triggers, examples, boundaries'],
['Clarity', '25%', 'Line count, token count, headers, readability'],
['Specificity', '25%', 'Concrete commands, file patterns, code examples'],
['Advanced', '15%', 'No deprecated patterns, security issues, completeness'],
]}
/>
<h3 className="text-lg font-semibold text-white mt-6">Grade Scale</h3>
<Table
headers={['Grade', 'Score Range', 'Description']}
rows={[
['A', '90-100', 'Excellent - Production ready'],
['B', '80-89', 'Good - Minor improvements possible'],
['C', '70-79', 'Acceptable - Some issues to address'],
['D', '60-69', 'Poor - Significant improvements needed'],
['F', '0-59', 'Failing - Major revision required'],
]}
/>
</div>
),
},
{
id: 'tech-stack',
title: 'Technology Stack',
content: (
<div className="space-y-4">
<Table
headers={['Layer', 'Technology']}
rows={[
['CLI Framework', 'Clipanion v4'],
['TUI Framework', '@opentui/react v0.1.75'],
['Validation', 'Zod v3.24'],
['YAML Parsing', 'yaml v2.6'],
['Git Operations', 'isomorphic-git v1.27'],
['HTTP Client', 'got v14.4'],
['Build System', 'Turbo v2.3, tsup v8.3, pnpm v9.0'],
['Testing', 'Vitest v2.1'],
['Runtime', 'Node.js 18+, Bun 1.2+ (for TUI)'],
]}
/>
<h3 className="text-lg font-semibold text-white mt-6">Build Commands</h3>
<CodeBlock>{`pnpm build # Build all packages via Turbo
pnpm dev # Watch mode development
pnpm test # Unit tests via Vitest
pnpm test:e2e # End-to-end tests
pnpm typecheck # Type checking
pnpm clean # Remove build artifacts`}</CodeBlock>
</div>
),
},
];
export function Documentation(): React.ReactElement {
const [activeSection, setActiveSection] = useState('overview');
const currentSection = sections.find(s => s.id === activeSection) || sections[0];
return (
<div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8">
<div className="text-center mb-8">
<h2 className="text-2xl font-bold text-white mb-2 font-mono">Documentation</h2>
<p className="text-zinc-400 font-mono text-sm">
Complete guide to using SkillKit
</p>
<a
href="https://deepwiki.com/rohitg00/skillkit"
target="_blank"
rel="noreferrer noopener"
className="inline-flex items-center gap-2 mt-2 text-xs text-zinc-500 hover:text-zinc-300 transition-colors"
>
<span>Powered by DeepWiki</span>
<svg className="w-3 h-3" fill="none" stroke="currentColor" viewBox="0 0 24 24">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M10 6H6a2 2 0 00-2 2v10a2 2 0 002 2h10a2 2 0 002-2v-4M14 4h6m0 0v6m0-6L10 14" />
</svg>
</a>
</div>
<div className="flex flex-col lg:flex-row gap-8">
<nav className="lg:w-48 flex-shrink-0" aria-label="Documentation sections">
<div className="sticky top-20 space-y-1">
{sections.map(section => (
<button
key={section.id}
type="button"
aria-current={activeSection === section.id ? 'page' : undefined}
onClick={() => setActiveSection(section.id)}
className={`w-full text-left px-3 py-2 text-sm font-mono rounded transition-colors ${
activeSection === section.id
? 'bg-white text-black'
: 'text-zinc-400 hover:text-white hover:bg-zinc-800'
}`}
>
{section.title}
</button>
))}
</div>
</nav>
<div className="flex-1 min-w-0">
<div className="bg-surface border border-zinc-800 rounded-lg p-6">
<h2 className="text-xl font-bold text-white mb-6 font-mono">{currentSection.title}</h2>
<div className="prose prose-invert prose-zinc max-w-none">
{currentSection.content}
</div>
</div>
</div>
</div>
</div>
);
}
+145
View File
@@ -0,0 +1,145 @@
import React from 'react';
interface Feature {
title: string;
description: string;
icon: React.ReactNode;
}
const FEATURES: Feature[] = [
{
title: 'Multi-Agent',
description: 'Deploy to 46 AI coding agents with one command.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M19 11H5m14 0a2 2 0 012 2v6a2 2 0 01-2 2H5a2 2 0 01-2-2v-6a2 2 0 012-2m14 0V9a2 2 0 00-2-2M5 11V9a2 2 0 012-2m0 0V5a2 2 0 012-2h6a2 2 0 012 2v2M7 7h10" />
</svg>
)
},
{
title: 'Terminal UI',
description: 'Beautiful interactive TUI for browsing & installing.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M8 9l3 3-3 3m5 0h3M5 20h14a2 2 0 002-2V6a2 2 0 00-2-2H5a2 2 0 00-2 2v12a2 2 0 002 2z" />
</svg>
)
},
{
title: 'Plugins',
description: 'Extend with custom plugins & hooks.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M17 14v6m-3-3h6M6 10h2a2 2 0 002-2V6a2 2 0 00-2-2H6a2 2 0 00-2 2v2a2 2 0 002 2zm10 0h2a2 2 0 002-2V6a2 2 0 00-2-2h-2a2 2 0 00-2 2v2a2 2 0 002 2zM6 20h2a2 2 0 002-2v-2a2 2 0 00-2-2H6a2 2 0 00-2 2v2a2 2 0 002 2z" />
</svg>
)
},
{
title: 'Manifest',
description: '.skills file for team-wide consistency.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M9 12h6m-6 4h6m2 5H7a2 2 0 01-2-2V5a2 2 0 012-2h5.586a1 1 0 01.707.293l5.414 5.414a1 1 0 01.293.707V19a2 2 0 01-2 2z" />
</svg>
)
},
{
title: 'CI/CD',
description: 'GitHub, GitLab, CircleCI templates included.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
</svg>
)
},
{
title: 'Slash Commands',
description: 'Generate /commands for Claude, Cursor & more.',
icon: (
<svg className="w-5 h-5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M7 20l4-16m2 16l4-16M6 9h14M4 15h14" />
</svg>
)
}
];
const COMPARISONS = [
['Agents', '1', '46'],
['Translation', 'Manual', 'Auto'],
['Sharing', 'Copy/paste', '.skills manifest'],
['Discovery', 'Forums', 'CLI + AI'],
['CI/CD', 'Custom', 'Templates'],
] as const;
export function Features(): React.ReactElement {
return (
<section id="features" className="py-12 border-b border-zinc-800 bg-surface">
<div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8">
<div className="grid grid-cols-1 lg:grid-cols-5 gap-6 lg:gap-8 mb-10">
<div className="lg:col-span-2">
<h2 className="text-xl font-bold text-white mb-2 font-mono">Why SkillKit?</h2>
<p className="text-zinc-500 font-mono text-sm mb-6">
Universal bridge for AI coding agents.
</p>
<div className="flex gap-6 sm:gap-8">
<div>
<div className="text-2xl sm:text-3xl font-bold text-white font-mono">46</div>
<div className="text-zinc-600 text-[10px] sm:text-xs font-mono">Agents</div>
</div>
<div>
<div className="text-2xl sm:text-3xl font-bold text-white font-mono">40+</div>
<div className="text-zinc-600 text-[10px] sm:text-xs font-mono">Commands</div>
</div>
<div>
<div className="text-2xl sm:text-3xl font-bold text-white font-mono">15K</div>
<div className="text-zinc-600 text-[10px] sm:text-xs font-mono">Skills</div>
</div>
</div>
</div>
<div className="lg:col-span-3 border border-zinc-800 bg-black/50 p-4 font-mono text-xs backdrop-blur-sm">
<div className="grid grid-cols-3 gap-2 border-b border-zinc-800 pb-2 mb-3 text-zinc-500 uppercase tracking-wider text-[10px]">
<div>Feature</div>
<div className="text-center">Without</div>
<div className="text-right">SkillKit</div>
</div>
<div className="space-y-1">
{COMPARISONS.map(([feature, without, withSkillKit], index) => (
<div
key={feature}
className="grid grid-cols-3 gap-2 items-center py-1.5 hover:bg-zinc-900/50 transition-colors -mx-2 px-2 rounded"
style={{ animationDelay: `${index * 100}ms` }}
>
<div className="text-zinc-300">{feature}</div>
<div className="text-center text-zinc-600">{without}</div>
<div className="text-right text-white font-medium">{withSkillKit}</div>
</div>
))}
</div>
</div>
</div>
<div className="grid grid-cols-1 xs:grid-cols-2 md:grid-cols-3 lg:grid-cols-6 gap-3">
{FEATURES.map((feature, index) => (
<div
key={feature.title}
className="group relative p-4 border border-zinc-800 bg-zinc-900/30 hover:bg-zinc-900/80 hover:border-zinc-700 transition-all duration-300 cursor-default"
style={{ animationDelay: `${index * 50}ms` }}
>
<div className="absolute inset-0 bg-gradient-to-b from-zinc-800/0 to-zinc-800/20 opacity-0 group-hover:opacity-100 transition-opacity"></div>
<div className="relative">
<div className="text-zinc-500 group-hover:text-white transition-colors mb-2">
{feature.icon}
</div>
<h4 className="text-xs font-bold text-white mb-1 font-mono">{feature.title}</h4>
<p className="text-zinc-600 text-[10px] leading-relaxed font-mono group-hover:text-zinc-400 transition-colors">
{feature.description}
</p>
</div>
</div>
))}
</div>
</div>
</section>
);
}

Some files were not shown because too many files have changed in this diff Show More