Index and search local Markdown collections with BM25 keyword search.
npx skills add https://github.com/KARENLHAO/skills --skill qmd-karenlhao
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/KARENLHAO/skills/tree/main/qmd-skill Command: npx skills add https://github.com/KARENLHAO/skills --skill qmd-karenlhao
Local search for Markdown notes, docs, and knowledge bases to quickly find, relate, and retrieve content from indexed collections.
Index your Markdown collection with qmd and run a search query to retrieve relevant notes.
High-intent search queries and answers about installing and using this skill.
To search local Markdown notes, you can index your collection and run a keyword query to retrieve relevant docs quickly. This provides fast BM25-based search across your local knowledge base files.
Yes, you can use optional semantic search to find related content in Markdown notes. This feature uses vector similarity to discover related documents beyond exact keyword matches within indexed collections.
BM25 keyword search is the default ranking algorithm used to locate notes and docs in local Markdown collections. It indexes your files and retrieves specific documents based on term frequency and relevance.
You index a local Markdown collection by running the provided commands to scan and catalog your notes. This process prepares your docs for fast keyword search and optional embedding for semantic retrieval.
No, this local search tool requires no external dependencies to index and search Markdown collections. It operates entirely on your local machine using built-in commands for indexing, embedding, and maintenance.
Use BM25 keyword search for fast exact term retrieval in Markdown notes, and switch to semantic search when you need to discover related content through vector similarity. Semantic search requires generating embeddings first.
ChimeraFoundationaIndex local markdown notes, transcripts, and docs for hybrid on-device search.
Blake-JohnExport Feishu documents and knowledge-base nodes to Markdown, PDF, or Word.
bajajvinamrSearch documents semantically using AgentDB vector embeddings with HNSW indexing.
aliyunBuild Hologres knowledge bases with vector and full-text indexes.
