Index and search local markdown notes using BM25 and semantic embeddings.
npx skills add https://github.com/icyzh/hermes-web --skill qmd-icyzh
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/icyzh/hermes-web/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/icyzh/hermes-web --skill qmd-icyzh
This skill solves the challenge of fragmented personal knowledge by providing a unified, local-first search engine that indexes markdown notes, transcripts, and documentation without relying on cloud services.
Use the qmd skill to perform a deep hybrid search for information regarding the database migration plan across all indexed collections.
High-intent search queries and answers about installing and using this skill.
You can perform local semantic search on markdown notes by indexing them with BM25 keyword matching and vector embeddings. This approach retrieves specific documentation or meeting transcripts locally, ensuring data privacy without relying on cloud services.
Hybrid search improves knowledge base retrieval by combining BM25 keyword matching with semantic vector search and LLM-powered reranking. This multi-layered approach increases precision when querying complex local documentation and transcripts using natural language.
Yes, you can index diverse file types like meeting transcripts and project documentation to make your entire local knowledge base queryable. This allows you to quickly find specific decisions made in past meetings using natural language queries.
Yes, local AI knowledge search requires Node.js 22 and local GGUF model support. These dependencies are necessary to maintain privacy and performance without cloud dependencies during the indexing and retrieval process.
The best way to find past decisions in local meeting transcripts is using a local-first RAG search engine. It applies query expansion and LLM-based reranking to retrieve high-precision results across hundreds of indexed files.
cxnaiveIndex local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
anukkrit149Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.
Tommy-ywSearch local knowledge bases with keyword, semantic, and LLM reranking.
ginkidaDesign embeddings pipelines, indexing strategies, and RAG retrieval systems.
