mcp-skills

Dynamic RAG-powered skills for code assistants via Model Context Protocol (MCP)

mcp-skills is a standalone Python application that provides intelligent, context-aware skills to code assistants through hybrid RAG (vector + knowledge graph). Unlike static skills that load at startup, mcp-skills enables runtime skill discovery, automatic recommendations based on your project's toolchain, and dynamic loading optimized for your workflow.

Key Features

• 🚀 Zero Config: mcp-skills setup handles everything automatically

• 🧠 Intelligent: Auto-detects your project's toolchain (Python, TypeScript, Rust, Go, etc.)

• 🔍 Dynamic Discovery: Vector similarity + knowledge graph for better skill finding

• 📦 Multi-Source: Pulls skills from multiple git repositories

• ⚡ On-Demand Loading: Skills loaded when needed, not all at startup

• 🔌 MCP Native: First-class Model Context Protocol integration

Installation

From PyPI

From Source

Quick Start

1. Setup

Run the interactive setup wizard to configure mcp-skills for your project:

This will:

• Detect your project's toolchain

• Clone relevant skill repositories

• Build vector + knowledge graph indices

• Configure MCP server integration

• Validate the setup

2. Start the MCP Server

The server will start and expose skills to your code assistant via MCP protocol.

3. Use with Claude Code

Skills are automatically available in Claude Code. Try:

• "What testing skills are available for Python?"

• "Show me debugging skills"

• "Recommend skills for my project"

Project Structure

Architecture

mcp-skills uses a hybrid RAG approach combining:

Vector Store (ChromaDB/Qdrant):

• Fast semantic search over skill descriptions

• Embeddings generated with sentence-transformers

Knowledge Graph (NetworkX):

• Skill relationships and dependencies

• Category and toolchain associations

• Related skill discovery

Toolchain Detection:

• Automatic detection of programming languages

• Framework and build tool identification

• Intelligent skill recommendations

Configuration

Global Configuration (~/.mcp-skills/config.yaml)

Project Configuration (.mcp-skills.yaml)

CLI Commands

MCP Tools

mcp-skills exposes these tools to code assistants:

• search_skills: Natural language skill search

• get_skill: Load full skill instructions by ID

• recommend_skills: Get recommendations for current project

• list_categories: List all skill categories

• update_repositories: Pull latest skills from git

Development

Requirements

• Python 3.11+

• Git

Setup Development Environment

Run Tests

Linting and Formatting

Documentation

Architecture

See docs/architecture/README.md for detailed architecture design.

Skills Collections

See docs/skills/RESOURCES.md for a comprehensive index of skill repositories compatible with mcp-skills, including:

• Official Anthropic skills

• Community collections (obra/superpowers, claude-mpm-skills, etc.)

• Toolchain-specific skills (Python, TypeScript, Rust, Go, Java)

• Operations & DevOps skills

• MCP servers that provide skill-like capabilities

Contributing

Contributions welcome! Please read our contributing guidelines first.

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Run make quality to ensure tests pass

5. Submit a pull request

License

MIT License - see LICENSE for details.

Acknowledgments

• Built on the Model Context Protocol

• Inspired by Claude Skills

• Uses ChromaDB for vector search

• Embeddings via sentence-transformers

Links

• Documentation: GitHub Wiki

• Issue Tracker: GitHub Issues

• MCP Registry: MCP Servers

Status: 🚧 Early development - MVP in progress