←Leaderboard/Knowledge/qmd-skill
Last commit on February 25, 2026·Created on January 27, 2026

levineam/qmd-skill

“A local hybrid search engine for markdown notes and knowledge bases”
Combined rank
#500
across all skills
In Knowledge
#22
category rank
Stars
706
+0.4% in last 7d
Forks
55
0.0% in last 7d
Watchers
2
0.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

qmd provides a mechanism for indexing and retrieving information from local markdown collections. It allows users to navigate large sets of documentation or personal notes through a combination of keyword and semantic search.

The tool is designed for users who need to find related content or retrieve specific documents from indexed collections without relying on external cloud services.

WHO IT'S FOR
Knowledge management power users
searching local markdown notes and docs
Technical writers
retrieving documents from indexed collections
Personal knowledge base curators
finding related notes via semantic similarity
CLI tool enthusiasts
indexing local markdown files for fast search
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill

Follow the documented setup, then try a first task.

See the repository for installation instructions.

Open repository instructions ↗

Give it something to do.

Suggested first task

Search an indexed Markdown collection

Uses qmd

  • A local qmd installation with Bun >= 1.0.0 and $HOME/.bun/bin on PATH
  • An existing indexed qmd collection name to replace <COLLECTION_NAME>
  • Search text to replace <QUERY>
  • On macOS, SQLite extensions installed as documented

Make sure qmd is installed in your agent before trying this task.

Use the qmd skill to run its default BM25 keyword search for <QUERY> in the already indexed collection <COLLECTION_NAME>, and return the matching file paths. Replace <QUERY> with the text to find and <COLLECTION_NAME> with the existing qmd collection name.
SKILL.md ↗ · Checked Oct 18, 2026