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
- 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)
- 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
- 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
- --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
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.
* 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
* 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
* 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
* 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.
* 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.
* 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.
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.
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.
* 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"
* 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)
* 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
* 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
* 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.
- 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
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
* 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
* 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
* 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.