skillz and local-skills-mcp
These are complements: skillz provides a standardized MCP interface for skill loading that works across multiple LLM clients, while local-skills-mcp implements that same pattern specifically optimized for filesystem-based skills with lazy loading, allowing them to be used together to serve different deployment scenarios (remote vs. local skills).
About skillz
intellectronica/skillz
An MCP server for loading skills (shim for non-claude clients).
This tool allows developers to integrate custom "skills" into various AI agents like Codex, Copilot, or Cursor. You provide a directory containing skill definitions (like a SKILL.md file and helper scripts), and the tool makes these skills callable by your agent. It's designed for developers building or extending AI agents who want to add specific functionalities easily.
About local-skills-mcp
kdpa-llc/local-skills-mcp
Universal MCP server enabling any LLM or AI agent to utilize expert skills from your local filesystem. Reduces context consumption through lazy loading. Works with Claude, Cline, and any MCP-compatible client.
This project helps AI developers and power users extend the capabilities of their AI agents and Large Language Models (LLMs). It allows you to organize and store specialized instructions, or "skills," for your AI on your local computer. Your AI agents can then access these skills on demand, allowing them to perform complex, domain-specific tasks without consuming excessive context.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work