KS
Killer-Skills

qmd — how to use qmd how to use qmd, qmd alternative, qmd setup guide, what is qmd, qmd vs other search tools, qmd install for Claude Code, optimized file search for AI agents, semantic indexing for codebases, reducing token usage with qmd

v1.0.0
GitHub

About this Skill

Perfect for Knowledge Retrieval Agents needing rapid Markdown search capabilities for codebases and documentation. qmd is a quick Markdown search tool that enables optimized file search and semantic indexing for large codebases in Claude Code.

Features

Local search engine for Markdown notes and documentation
Semantic indexing for large codebases in Claude Code
Reduces token usage by searching for relevant files before reading them
Supports exploration of codebases and documentation
Finds specific functionality or concepts within codebases
Identifies related files to a topic or question

# Core Topics

iagocavalcante iagocavalcante
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
57
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add iagocavalcante/claude-turbo-search

Agent Capability Analysis

The qmd MCP Server by iagocavalcante is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use qmd, qmd alternative, qmd setup guide.

Ideal Agent Persona

Perfect for Knowledge Retrieval Agents needing rapid Markdown search capabilities for codebases and documentation.

Core Value

Empowers agents to efficiently locate specific functionality or concepts within Markdown notes, docs, and knowledge bases using local search, dramatically reducing token usage and improving overall performance with Markdown file support.

Capabilities Granted for qmd MCP Server

Exploring codebases for specific functionality
Finding related Markdown files on a topic
Answering questions about codebases and documentation

! Prerequisites & Limits

  • Requires local Markdown files
  • Limited to Markdown file format
Project
SKILL.md
2.5 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

qmd - Quick Markdown Search

Local search engine for Markdown notes, docs, and knowledge bases. Use this to find relevant files BEFORE reading them to dramatically reduce token usage.

When to Use (IMPORTANT)

ALWAYS prefer qmd search over reading files directly when:

  • Exploring a codebase or documentation
  • Looking for specific functionality or concepts
  • Finding related files to a topic
  • Answering questions about the codebase

Token savings: Instead of reading 5 files (5000+ tokens), search first (50 tokens) and read only the relevant sections (200 tokens).

Search Priority (follow this order)

  1. qmd search "query" - Fast BM25 keyword search. Use this first, it's instant.
  2. qmd vsearch "query" - Semantic similarity. Use only if keyword search fails.
  3. qmd query "query" - Hybrid + reranking. Avoid unless user explicitly requests highest quality.

Common Commands

bash
1# Fast keyword search (DEFAULT - use this first) 2qmd search "authentication" -n 10 3 4# Search specific collection 5qmd search "api routes" -c my-project 6 7# Get file paths only (for deciding what to read) 8qmd search "database schema" --files 9 10# JSON output for parsing 11qmd search "error handling" --json 12 13# Semantic search (slower, use as fallback) 14qmd vsearch "how does the login flow work"

Retrieve Documents

bash
1# Get specific file 2qmd get "path/to/file.md" 3 4# Get by document ID from search results 5qmd get "#docid" 6 7# Get multiple files 8qmd multi-get "docs/*.md" --json

Workflow Example

Bad (token expensive):

1. Read src/auth/login.ts (800 tokens)
2. Read src/auth/session.ts (600 tokens)
3. Read src/auth/middleware.ts (500 tokens)
4. Read src/auth/types.ts (400 tokens)
→ Found answer in middleware.ts
Total: 2300 tokens

Good (token efficient):

1. qmd search "authentication middleware" --files (response: 50 tokens)
   → Returns: src/auth/middleware.ts:45-62
2. Read only the relevant section (150 tokens)
Total: 200 tokens (90% savings!)

Tips for Claude

  • Search before reading: Always try qmd search first
  • Use --files flag: Get paths without content to decide what to read
  • Be specific: More specific queries = better results
  • Check collections: Use qmd status to see indexed collections
  • Combine with cartographer: CODEBASE_MAP.md gives structure, qmd gives content

Maintenance

bash
1qmd status # Check index health and collections 2qmd update # Re-index changed files (fast) 3qmd embed # Update vector embeddings (slower)

Related Skills

Looking for an alternative to qmd or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication