Search and rerank passages across locally indexed markdown knowledge bases.
npx skills add https://github.com/ZardLi1115/zedclaw --skill qmd-zardli1115
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/ZardLi1115/zedclaw/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill qmd-zardli1115
QMD removes the pain of finding the right information inside large collections of personal markdown notes, documents, and transcripts by providing fast local retrieval plus high-quality hybrid semantic search.
Run a hybrid search across your indexed notes for the question “what decisions were made about the API redesign”.
High-intent search queries and answers about installing and using this skill.
Local semantic search of markdown notes combines BM25 keyword matching and vector embeddings to retrieve relevant passages. This hybrid approach finds exact keyword hits and conceptually related information across your personal knowledge base.
Hybrid search reranking applies an optional GGUF model to evaluate and re-sort initial BM25 and vector search results. This process surfaces the most semantically relevant passages from your indexed documents and meeting transcripts.
Yes, you can query local markdown documentation through an MCP server using stdio or HTTP daemon modes. This allows agent-based tools to access your indexed knowledge base for retrieval and documentation exploration tasks.
Indexing markdown documents for local retrieval requires SQLite-backed storage to manage BM25 keyword data and vector embeddings. This local indexing setup enables fast discovery of relevant passages across your personal notes.
Local knowledge base search supports CLI workflows, allowing you to run hybrid queries directly from the terminal. This provides an alternative to MCP server integration for users who prefer command-line document exploration.
steipeteIndex local files and search them with BM25, vector, and hybrid queries.
zhangyuyuanzuGenerate standardized citations and bibliographies in APA, MLA, Chicago, and simplified formats.
overviewlabsSearch local Markdown collections with hybrid keyword and vector retrieval.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
