What problem does it solve? Finding information across large collections of personal notes, meeting transcripts, and documentation is slow with plain grep and impossible to do semantically without sending data to the cloud. This Skill sets up and operates qmd, a fully local search engine that indexes text files and answers both keyword and conceptual queries on-device. ## Core Features & Use Cases - Hybrid Local Search: Combines BM25 keyword matching, semantic vector search, and LLM reranking using three local GGUF models with no cloud dependencies. - Collection Management: Add directories as named collections, attach context descriptions to improve retrieval, and generate embeddings with qmd embed. - MCP Integration: Expose search tools directly to the agent via an MCP server in stdio mode or as a persistent HTTP daemon that keeps models warm. - Use Case: A user with years of markdown journal entries and meeting transcripts asks "what decisions were made about the database migration" and gets reranked, context-aware results from the hybrid query pipeline. ## 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.
