Search personal markdown knowledge bases with hybrid BM25 and vector retrieval.
npx skills add https://github.com/tc9011/my-skills --skill qmd-tc9011
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/tc9011/my-skills/tree/main/skills/qmd Command: npx skills add https://github.com/tc9011/my-skills --skill qmd-tc9011
This Skill allows you to quickly and efficiently search through your personal markdown knowledge bases, notes, meeting transcripts, and documentation, even when you don't remember the exact keywords.
qmd query "client onboarding" to find the most relevant notes or transcripts.Search your notes for information about "project timelines".
High-intent search queries and answers about installing and using this skill.
To search your knowledge base without exact keywords, use semantic vector search to find conceptual matches. This approach retrieves relevant markdown notes and documentation by analyzing the meaning of your query rather than relying solely on specific terms.
The best way to find old meeting transcripts is using a hybrid search engine. It combines BM25 keyword search with vector semantic search and LLM re-ranking to retrieve documents based on conceptual terms like "client onboarding" even months later.
Hybrid search for personal notes works by combining fast BM25 keyword search, semantic vector search for conceptual matches, and LLM re-ranking. This comprehensive retrieval process ensures you find the most relevant information across your documentation.
Yes, you can retrieve specific markdown documents by their file path or a unique ID. This document retrieval feature allows you to bypass search and directly access exact files within your personal knowledge base collections.
You need to manage search indexes by checking their status and managing collections before querying your documentation. Index management ensures your markdown notes and transcripts are properly processed for accurate BM25 and vector search retrieval.
Chris-Chai-MinjaeIndex local text files for hybrid keyword and semantic search.
anukkrit149Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.
aivos-xieParse Markdown documents into a structured knowledge base for cross-referencing and queries.
JSai23Enable semantic search of local vault notes using qmd with BM25, vector search, and LLM re-ranking.