What problem does it solve? Finding information across large collections of personal notes, meeting transcripts, and documentation is slow with plain keyword grep, and cloud search services compromise privacy. This Skill indexes local text files and retrieves answers using keyword matching, semantic understanding, and LLM reranking entirely on-device. ## Core Features & Use Cases - Hybrid Local Search: Combines BM25 keyword search, vector embeddings, and LLM reranking with query expansion for high-quality retrieval without cloud dependencies. - Collection Management: Add directories as named collections, attach context descriptions to improve retrieval accuracy, and generate embeddings with simple CLI commands. - MCP Integration: Exposes search tools directly to the agent via stdio or an HTTP daemon that keeps models warm for fast repeated queries. - Use Case: A user with years of markdown meeting notes asks "what decisions were made about the database migration" and gets reranked, contextually relevant excerpts in seconds. ## Quick Start Use the qmd skill to search my notes collection for anything about the API redesign decisions.
