qmd

Index Markdown content and retrieve relevant documents using BM25 and vector search.

Updated Aug 23, 2026

Search Tags:#documentation #markdown #knowledge-base #vector-search #bm25 #local-search #qmd

Ready to run

npx skills add https://github.com/samuelcastro/noter --skill qmd-samuelcastro

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/samuelcastro/noter/tree/main/.agents/skills/qmd
Command: npx skills add https://github.com/samuelcastro/noter --skill qmd-samuelcastro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Quickly locate information hidden in Markdown documents and notes across local repos, replacing slow keyword hunts with fast, structured search over your knowledge base.

Core Features & Use Cases

Local search over Markdown content using BM25 and vector-based semantics.
MCP server integration to power AI assistants with fast, relevant results.
Use cases include finding policy docs, notes, API docs, and project briefs across repositories.

Quick Start

Install the QMD CLI and run a sample query against your knowledge base.

Frequently Asked Questions about qmd

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

FAQPage Schema

How do I search markdown documentation locally across multiple repositories?▼

You can search markdown documentation locally by indexing content across repositories and querying it with BM25 and vector search. This returns relevant documents from your local notes and knowledge base without relying on external services.

What is the difference between lexical and vector search for a markdown knowledge base?▼

Lexical search uses BM25 keyword matching to find exact terms in markdown files, while vector search applies semantic matching to retrieve conceptually relevant documents. You can choose lex, vec, or hyde query types to control retrieval behavior.

Can I use an MCP server to give my AI assistant access to local markdown notes?▼

Yes, you can integrate an MCP server to connect AI assistants with your indexed markdown knowledge base. This allows the assistant to query local notes, policy docs, and API documentation, receiving fast and relevant search results.

What is the best way to find specific policy docs and project briefs across local repos?▼

The best way to find policy docs and project briefs is indexing markdown content with combined BM25 and vector search. This replaces slow keyword hunts with structured queries that return relevant documents across your local repositories.

How does hyde query type work when searching local documentation?▼

The hyde query type enhances vector search by generating hypothetical answers to expand your query semantically. This improves retrieval of relevant markdown documents when searching complex or indirect questions in your knowledge base.

Are there limitations when searching markdown notes with local search?▼

Local search is limited to markdown content and requires proper indexing before querying. Safe defaults and strong error handling manage collection controls, but complex queries across unindexed repositories will not return relevant documents.