intellectronica/skillz

Registry

Summary

Skillz is an MCP (Model Context Protocol) server that functions as a shim layer, enabling non-Claude clients to load and utilize Claude Skills. It provides a bridge for AI agents and applications to access a repository of skills.

Key features

• MCP server implementation
• Shim layer for non-Claude clients
• Skill loading functionality
• Python-based development
• Facilitates AI agent tooling

Use cases

• Integrating Claude Skills into other AI platforms
• Building AI agents that utilize external skill sets
• Creating MCP-compatible applications
• Developing toolchains for AI-assisted workflows

README excerpt

# Skillz ## 👌 **Use _skills_ in any agent** _(Codex, Copilot, Cursor, etc...)_ [](https://pypi.org/project/skillz/) [](https://pypi.org/project/skillz/) > ⚠️ **Experimental proof‑of‑concept. Potentially unsafe. Treat skills like untrusted code and run in sandboxes/containers. Use at your own risk.** **Skillz** is an MCP server that turns [Claude-style skills](https://github.com/anthropics/skills) _(`SKILL.md` plus optional resources)_ into callable tools for any MCP client. It discovers each skill, exposes the authored instructions and resources, and can run bundled helper scripts. > 💡 You can find skills to install at the **[Skills Supermarket](http://skills.intellectronica.net/)** directory. ## Quick Start To run the MCP server in your agent, use the following config (or equivalent): ```json { "skillz": { "command": "uvx", "args": ["skillz@latest"] } } ``` with the skills residing at `~/.skillz` _or_ ```json { "skillz": { "command": "uvx", "args": ["skillz@latest", "/path/to/skills/direcotry"] } } ``` or Docker You can run Skillz using Docker for isolation. The image is available on Docker Hub at `intellectronica/skillz`. To run the Skillz MCP server with your skills directory mounted using Docker, configure your agent as follows: Replace `/path/to/skills` with the path to your actual skills directory. Any arguments after `intellectronica/skillz` in the array are passed directly to the Skillz CLI. ```json { "skillz": { "command": "docker", "args": [ "run", "-i", "--rm", "-v", "/path/to/skills:/skillz", "intellectronica/skillz", "/skillz" ] } } ``` ## Gemi

Topics