How do I install the necessary QMD components?

You can install the QMD CLI globally using the command: bun install -g https://github.com/tobi/qmd.

What is the difference between keyword and semantic search in QMD?

Keyword search (BM25) looks for exact word matches, while semantic search (vector search) finds results based on the meaning and context of your query even if exact words aren't present.

Can I search specific folders or categories?

Yes, QMD supports collections. You can restrict your search to specific collections using the --collection flag to improve speed and relevance.

Does QMD require an internet connection to search my notes?

No, QMD operates locally on your device, ensuring your private notes and documentation remain secure and accessible offline.

What is QMD and how does it work with Claude?

QMD is a local search engine for markdown files. This skill allows Claude to use QMD's indexing capabilities to find and retrieve information from your personal notes and documents.

QMD Markdown Search

Name: QMD Markdown Search
Author: yash1258

byyash1258

0•

Productividad y Flujo de Trabajo

Searches personal markdown knowledge bases and documentation using a local hybrid search engine combining BM25, vector search, and LLM re-ranking.

QMD is a powerful, on-device search utility designed for developers and power users who maintain extensive markdown-based knowledge bases, meeting notes, and technical documentation. By integrating this skill, Claude gains the ability to intelligently query your local files using multiple search modes—ranging from fast keyword matching to deep conceptual semantic search. Whether you are looking for a specific meeting transcript or a complex implementation detail buried in your notes, QMD provides highly relevant results with scoring and full document retrieval capabilities.

Características Principales

01Collection-based filtering to narrow down searches to specific projects or folders

02On-device indexing for fast retrieval of notes, transcripts, and documentation

03Seamless integration via standard CLI commands or Model Context Protocol (MCP)

040 GitHub stars

05Multiple search modes optimized for speed or conceptual precision

06Hybrid search combining BM25 keywords, vector embeddings, and LLM re-ranking

Casos de Uso

01Finding action items or historical context within meeting transcripts

02Searching across multi-file project documentation to understand complex implementations

03Retrieving specific information from a massive collection of personal developer notes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yash1258/qmd-renoa qmd

For use in Claude.ai and ChatGPT

Download Skill