skill-mcp and skillboss-skills
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.
# Technical Summary Provides a 22-module MCP server that enables LLMs to unify multiple skills in single code executions through cross-skill imports and automatic dependency/environment aggregation—achieving 98.7% token efficiency gains by following Anthropic's MCP code-execution pattern. Features CRUD operations for skill management stored in `~/.skill-mcp/skills/`, with support for Python/Bash script execution using PEP 723 inline dependencies and per-skill `.env` files. Architecture remains client-agnostic via standard MCP protocol, compatible with Claude Desktop, Cursor, claude.ai, and any MCP-compatible application without vendor lock-in.
About skillboss-skills
SkillBoss-AI/skillboss-skills
MCP server & Claude Code skills for 100+ AI services (LLMs, image/video gen, TTS). One API key, OpenAI-compatible.
Provides a unified abstraction layer for 100+ AI service APIs through MCP server transport and native skill integrations, enabling Claude Code and other agents to deploy full-stack applications, manage databases/storage, and automate real-world workflows. Implements a modular skills architecture with production-ready capabilities for payments, authentication, and content generation, rather than requiring agents to integrate individual provider APIs separately.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work