<div align="center">

skilltap

Turn a folder of Markdown agent skills into MCP tools that any coding agent can list, search, and load.

<img src="demo.gif" alt="Demo" width="700" />

</div>

---

🎯 Why?

Agent skills and MCP servers are trending, but local procedural knowledge is still trapped in loose Markdown files. Memory MCP servers store facts, not reusable runbooks, and coding agents lack a zero-dependency way to discover team skills. skilltap bridges that gap by indexing a skills folder and exposing safe list/get/search tools over MCP stdio.

Target audience: Developers and platform teams building with Claude Code, Cursor, or custom MCP agents who want reusable, version-controlled operational skills without running extra infrastructure.

✨ Features

• ✨ Scans a directory of Markdown skills with simple frontmatter and safe path handling
• ✨ Exposes list_skills, get_skill, and search_skills MCP tools over stdio
• ✨ Includes a human CLI for listing, searching, printing, and inspecting tools

🚀 Quick Start

# Install
pip install skilltap

# Run
skilltap --help

📦 Installation

From Source

git clone https://github.com/YOUR_USERNAME/skilltap.git
cd skilltap

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v

🎬 Demo

The GIF above was recorded using Charm VHS:

vhs < demo.tape

📖 Usage

# Show help
skilltap --help

# Common usage examples
skilltap --example

🏗️ Architecture

graph LR
    A[Input] --> B[Core Engine]
    B --> C[Output]
    B --> D[Plugins]
    D --> E[Extensions]

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repo
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

MIT © 2026 — See LICENSE for details.

---

<div align="center">

If this project helped you, please ⭐ star it!

Made with ❤️ and AI

</div>