A universal MCP server that loads Markdown skills from arbitrary folders, enabling lazy discovery and execution of skills across multiple MCP-capable tools.
A minimal MCP server that resolves skill names to filesystem paths + metadata, enabling on-demand skill retrieval without loading full content into context.
Semantic skill-library search MCP server that finds relevant skills or Markdown knowledge files from local directories using embeddings, SQLite vector storage, and Reciprocal Rank Fusion.
MCP server that unifies and synchronizes AI coding skills across multiple tools, exposing skill discovery and retrieval via list_skills and read_skill.
An MCP server that acts as an AI knowledge and skills hub, automatically discovering, indexing, and serving skill libraries to any MCP client with full-text search, rich metadata, and hot reload.