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 so you can query your knowledge base in natural language without sending data to the cloud. ## Core Features & Use Cases - Three Search Modes: Use qmd search for instant BM25 keyword lookup, qmd vsearch for semantic vector search, and qmd query for hybrid search with query expansion and LLM reranking. - Collection Management: Add directories as named collections, attach context descriptions to improve retrieval quality, and generate embeddings with qmd embed. - 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: You have years of meeting transcripts and project docs in markdown. Add them as qmd collections, then ask "what decisions were made about the database migration" and get reranked, contextually relevant excerpts in seconds. ## Quick Start Install qmd with npm, add my notes folder as a collection, run the embedding step, and then search my notes for everything about the API redesign decisions.
