Agent Skills Hub

What is Agent Skills Hub about?

Agent Skills Hub aggregates, cleans, scores, and presents open‑source repositories that implement agent skills, MCP servers, and related AI tools. It provides a searchable web UI and a REST API so developers can quickly find high‑quality, up‑to‑date components.

How to use Agent Skills Hub?

1. Explore via the web UI – Visit https://agentskillshub.top, browse categories, apply filters, and view detailed scores.
2. Consume the API – Call endpoints such as /api/skills, /api/trending, /api/top-rated to retrieve paginated lists, rankings, and statistics in JSON.
3. Submit a repository – POST to /api/submit-skill with a GitHub repo URL to propose new entries.
4. Stay updated – The platform runs an automated sync every 8 hours (full sync on Sundays) that pulls the latest data from GitHub.

Key features of Agent Skills Hub

• 6‑phase data pipeline (collection → cleaning → evaluation → scoring → presentation).
• Quality analysis across six dimensions (completeness, clarity, specificity, examples, README structure, agent readiness).
• Composite scoring that combines quality, stars, recency, forks, commits, issue resolution, momentum, author followers, and size bonus.
• Trending & rising lists based on star velocity and recent activity.
• Full‑text search powered by PostgreSQL tsvector with GIN indexing.
• Dual‑mode API – production uses Supabase PostgREST/RPC, development runs a FastAPI service.
• Automatic GitHub rate‑limit handling and incremental syncs.
• Newsletter & RSS feed for community updates.

Use cases of Agent Skills Hub

• Agent developers can find ready‑to‑use skills or MCP server implementations that match their language or framework.
• Tool curators can benchmark open‑source projects against community scores and trends.
• Researchers can analyze ecosystem health, growth patterns, and composability of agent skills.
• Product teams can discover reusable components to accelerate AI‑agent features.
• Community contributors can submit and promote their own repos, gaining visibility.

FAQ from the Agent Skills Hub

Q: How often is the data refreshed? A: An automated GitHub Actions workflow runs every 8 hours; full syncs happen on Sundays, incremental updates on weekdays.

Q: Can I host the platform myself? A: Yes. Clone the repo, set up the FastAPI backend (Python 3.12) and the React frontend, configure a Supabase PostgreSQL instance or use the provided SQLite for local testing, and run the GitHub sync workflow.

Q: What criteria affect the quality score? A: The score combines six quality dimensions (README completeness, clarity, specificity, examples, structure, and agent readiness) and nine weighted signals such as stars, recency, forks, commit activity, issue resolution rate, momentum, author followers, and repository size.

Agent Skills Hub

Discover, evaluate, and compare 6,000+ open-source Agent Skills, MCP servers, and AI tools.

🌐 Live: agentskillshub.top · 📰 Newsletter · 𝕏 Follow

Architecture

GitHub API ──▸ Collection ──▸ Cleaning ──▸ Evaluation ──▸ Scoring ──▸ Presentation
               (6 phases)    (classify)   (6 dimensions)  (0-100)    (Web + API)

Layer	Stack
Backend	Python 3.12 · FastAPI · SQLAlchemy · httpx
Frontend	React 18 · TypeScript · Vite · TailwindCSS v4
Database	Supabase (PostgreSQL) / SQLite (local)
Deploy	GitHub Pages + GitHub Actions (every 8h)
Email	Resend API · Supabase pg_net

Data Pipeline

1. Collection (scheduler/jobs.py)

Every 8 hours, GitHub Actions triggers a 6-phase sync:

Phase	What	Budget
Search	10+ GitHub queries (mcp-server, claude-skill, agent-tool...)	~30
Masters	Fetch repos from verified skill creators	~18
Extra	Community-submitted + curated repos	~14
Enrich	Owner profiles (followers)	≤500
README	Full README content (≤50KB each)	≤300
Upsert	Clean → score → save	0

• Incremental sync on weekdays (only new/updated repos), full sync on Sundays
• Smart rate-limit handling: waits for actual GitHub reset time

2. Cleaning (services/data_cleaner.py)

• Deduplication by repo_full_name
• Keyword-based category classification: mcp-server · claude-skill · codex-skill · agent-tool · ai-skill · llm-plugin · youmind-plugin
• Project type inference (framework / skill / tool)
• Size categorization (micro ≤50KB → large >5MB)

3. Evaluation

Quality Analysis — 6 dimensions (services/quality_analyzer.py):

Dimension	Weight	Key Signals
Completeness	15%	README size, license, description, stars
Clarity	15%	Description quality, topics, naming
Specificity	15%	Language, topic count, category, size
Examples	12%	Code examples, commits, contributors
README Structure	23%	Sections, code blocks, badges, TOC
Agent Readiness	20%	API docs, config, install, MCP compliance

Composite Score — 9 weighted signals (services/scorer.py):

Signal	Weight	Method
Quality	20%	6-dimension aggregate
Stars	18%	log₁₊ₓ normalization
Recency	11%	Exponential decay e⁻⁰·⁰¹ᵈ
Forks	10%	log₁₊ₓ
Commits	10%	log₁₊ₓ
Issue Resolution	10%	resolved / total
Momentum	8%	Z-score star growth
Author Followers	8%	log₁₊ₓ
Size Bonus	5%	Smaller = higher

Also: Platform Inference (17 platforms), Token Estimation, Composability (TF-IDF + 8-signal skill pairing).

4. Presentation

Dual-mode API client: Production uses Supabase PostgREST + RPCs directly; dev uses FastAPI backend.

Key optimizations:

• get_landing_data() RPC replaces 7+ API calls
• Database views: v_trending, v_top_rated, v_rising, etc.
• Full-text search via PostgreSQL tsvector + GIN index
• HTTP caching: 5min (trending) → 1hr (stats)

Quick Start

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

API Endpoints

Method	Path	Description
GET	/api/skills	Paginated list (search, filter, sort)
GET	/api/skills/{id}	Skill detail + compatible skills
GET	/api/trending	Star velocity leaders (7 days)
GET	/api/rising	New this week
GET	/api/top-rated	Highest scored
GET	/api/most-starred	Community classics (6+ months)
GET	/api/masters	Verified creators + org builders
GET	/api/landing	Bundled homepage data
GET	/api/stats	Summary statistics
GET	/api/feed.xml	RSS 2.0 feed
GET	/api/sitemap.xml	SEO sitemap (6,000+ URLs)
POST	/api/submit-skill	Submit a GitHub repo
POST	/api/subscribe	Newsletter signup

Deployment

┌─────────── GitHub Actions ───────────┐
│  sync.yml (8h) · deploy.yml · newsletter.yml (Mon) │
└──────┬──────────────┬────────────────┬──┘
       ▼              ▼                ▼
   Supabase      GitHub Pages     Resend API
  (PostgreSQL)    (React SPA)     (Emails)

Environment Variables

GITHUB_TOKEN=ghp_xxx          # GitHub API (required)
SUPABASE_DB_URL=postgresql://  # Production database
RESEND_API_KEY=re_xxx          # Email service
ADMIN_TOKEN=sk-xxx             # Admin API auth
SYNC_INTERVAL_HOURS=8          # Sync frequency

Docs

• Scoring Algorithm — Full scoring design
• System Architecture — Detailed pipeline reference