315 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
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.
v1.23.0
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 v1.22.1 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 v1.22.0 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 v1.21.0 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