🔍 Skill Research Hub

A professional full-stack research dashboard designed to crawl, analyze, and visualize the AI Agent Skill ecosystem. Inspired by the Agent Skills Blue Book 2026, this tool provides deep insights into market distribution, predictive trends, and automated AI reporting.

---

🚀 Key Features

📊 Advanced Market Analytics (Blue Book Standard)

• Gini Coefficient Optimization: Precise measurement of "star wealth" inequality in the ecosystem.
• Long-Tail Distribution: Interactive visualization of the "silent majority" (0-star skills).
• Data Provenance & Reliability: Every record tracks its source, source_url, and metadata_quality. Inferred fields are clearly flagged.
• Historical Snapshots: Daily time-series tracking of skill metrics (stars) for advanced trend analysis.

🕸️ Multi-Source Intelligent Discovery

• Deep Traversal: Automatically paginates through entire keyword/tag sets from SkillsMP.
• GitHub Integration: Direct discovery of mcp-server topics and SKILL.md feature files.
• Dynamic Trending: Advanced leaderboards for Growth (velocity), New Comers (recent discovery), and Revivals (resurgent skills).
• Persistent Cooldown: Intelligent 12-hour collection cooldown stored in SQLite.

🏗️ Technical Architecture

• Performance Storage: High-performance SQLite with WAL mode, batch write transactions, and optimized indexing.
• Environment Driven: Fully configurable via environment variables for easy deployment (ALLOW_ORIGINS, VITE_API_BASE_URL).
• Background Processing: Non-blocking data collection using FastAPI BackgroundTasks.

✍️ Automated Research Reporting

• AI Synthesis: Generates professional-grade research articles using Gemini 1.5 Flash.
• Markdown & Prose: Beautifully formatted reports using Tailwind Typography for a journal-like reading experience.
• Sample Reports: English Version | Chinese Version

🩺 Ecosystem Health

• Activity Lifecycles: Categorizes skills as Active, Stale, Decaying, or Dead based on update recency.

---

🏗️ Project Structure

.
├── backend/                # FastAPI Application
│   ├── app/
│   │   ├── api/           # API Endpoints (Market, Predictions, Reports)
│   │   ├── services/      # Core Logic (Analytics, AI Reporter, Collector)
│   │   └── cache.py       # Data Persistence Layer
│   └── requirements.txt    # Python Dependencies
├── frontend/               # React TypeScript Application (Vite)
│   ├── src/
│   │   ├── components/    # Recharts & UI Components
│   │   ├── api/           # Typed API Client
│   │   └── App.tsx        # Main Dashboard Layout
│   └── package.json        # Node Dependencies
└── README.md

---

🛠️ Tech Stack

• Backend: Python 3.8+, FastAPI, Uvicorn, google-generativeai.
• Frontend: React 19, TypeScript, Vite, Recharts, Tailwind CSS.
• Data: Deterministic metadata simulation for consistent research datasets.

---

🏃 Getting Started

Prerequisites

• Python 3.8+
• Node.js 18+ & npm
• Google Gemini API Key (Optional, for AI reporting)

Setup & Run

1. Clone the repository

   git clone https://github.com/alingowangxr/skill-research-hub.git
   cd skill-research-hub

2. Backend Setup

   cd backend
   pip install -r requirements.txt
   # Create .env and add:
   # GOOGLE_API_KEY=your_key
   python -m uvicorn app.main:app --reload

3. Frontend Setup

   cd frontend
   npm install
   npm run dev

4. Visit Dashboard: http://localhost:5173

---

🤝 Contributing

Contributions are welcome! Whether it's adding new data sources, refining the prediction model, or improving the UI.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📝 License

Distributed under the MIT License. See README.md for more information.

🙏 Acknowledgments

• Inspired by the Agent Skills Blue Book 2026.
• Built with ❤️ for the AI Agent community.