skills.rest
aiguy611
aiguy611COMMUNITY
Explore all skills by this author →
WebsiteGitHub

qmd

Index local markdown files and run hybrid BM25-vector-reranker queries.

Updated Aug 23, 2026
Search Tags:#embeddings#llm#semantic#hybrid#bm25#local-search#qmd
One-click install
npx skills add https://github.com/aiguy611/cc-tools --skill qmd-aiguy611
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/aiguy611/cc-tools/tree/main/.github/skills/qmd
Command: npx skills add https://github.com/aiguy611/cc-tools --skill qmd-aiguy611

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locally-powered search across markdown collections by combining fast BM25 keyword matching with vector embeddings and LLM-based re-ranking, enabling precise results without cloud access.

Core Features & Use Cases

  • Hybrid search that fuses BM25, vector similarity, and re-ranking for top results.
  • Semantic search using embeddings for concept-based retrieval across notes, docs, and transcripts stored locally.
  • Workflow: index files with update, embed embeddings with embed, then query with query/vsearch for flexible search scenarios.

Quick Start

Install qmd globally, add a collection, run embedding, then begin searching with qmd query.

Frequently Asked Questions about qmd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform local semantic search across markdown files without cloud access?▼

Hybrid search across local markdown combines BM25 keyword matching with vector embeddings and LLM-based re-ranking. This approach fuses semantic concepts with exact keywords, returning calibrated results that single-method searches miss.

How do I index and query local markdown collections on-device?▼

Hybrid search across local markdown combines BM25 keyword matching with vector embeddings and LLM-based re-ranking. This approach fuses semantic concepts with exact keywords, returning calibrated results that single-method searches miss.

Can I integrate on-device markdown search results with LLM agents?▼

Hybrid search across local markdown combines BM25 keyword matching with vector embeddings and LLM-based re-ranking. This approach fuses semantic concepts with exact keywords, returning calibrated results that single-method searches miss.

What is the best way to combine BM25 keyword matching with vector embeddings for local notes?▼

Hybrid search across local markdown combines BM25 keyword matching with vector embeddings and LLM-based re-ranking. This approach fuses semantic concepts with exact keywords, returning calibrated results that single-method searches miss.

Do I need an internet connection to run semantic search on my local markdown documents?▼

Hybrid search across local markdown combines BM25 keyword matching with vector embeddings and LLM-based re-ranking. This approach fuses semantic concepts with exact keywords, returning calibrated results that single-method searches miss.

Related Skills

Explore More Software Engineering Skills→
cdeistopenedcdeistopened
2

local-markdown-search

Index and search local Markdown collections with BM25 and vector embeddings.

Community
Intermediate
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
JSai23JSai23
1

vault-sem-search-a

Enable semantic search of local vault notes using qmd with BM25, vector search, and LLM re-ranking.

Community
Intermediate
pbdeuchlerpbdeuchler
13

howto-qmd

Search markdown collections using BM25, vector, and hybrid re-ranking.

Community
Intermediate