skillz and skill-mcp
These are complements: skillz provides a framework for loading pre-built skills via MCP, while skill-mcp adds programmatic skill creation and management capabilities on top of that infrastructure, allowing users to both define and execute skills within the same MCP ecosystem.
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 skill-mcp
fkesheh/skill-mcp
LLM-managed skills platform using MCP - create, edit, and execute skills programmatically in Claude, Cursor, and any MCP-compatible client without manual file uploads.
This system helps AI agents like Claude manage and execute specialized functions, or 'skills', automatically. Instead of manually uploading code or files, the AI can create, edit, and run these skills on the fly. It takes natural language commands from the AI and allows it to produce unified code that combines multiple skills, acting as an extension of the AI's capabilities for complex tasks.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work