What problem does it solve? Finding information across large collections of personal notes, meeting transcripts, and documentation is slow with plain grep and inaccurate with keyword-only search. This Skill sets up and operates qmd, a fully local search engine that combines keyword matching, semantic vector search, and LLM reranking without any cloud dependency. ## Core Features & Use Cases - Three Search Modes: BM25 keyword search for exact terms, vector search for conceptual queries, and hybrid query mode with query expansion and reranking for best quality. - Collection Management: Add directories as named collections, attach context descriptions to improve retrieval, and generate embeddings with a single command. - MCP Integration: Expose search tools directly to the agent via stdio or a persistent HTTP daemon that keeps models warm for fast repeated queries. - Use Case: A user with hundreds of markdown meeting notes asks "what decisions were made about the database migration" and gets reranked, contextually relevant excerpts in seconds. ## Quick Start Install qmd with npm, add my notes folder as a collection, run embedding, then search my notes for everything about the API redesign decisions.
