A high-performance CLI tool for indexing and searching local markdown knowledge bases using keyword, vector, and hybrid search methods.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install qmd-cli
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install qmd-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is qmd Local Markdown Search?
qmd is a professional-grade search utility designed to transform local directories of markdown files into highly accessible knowledge bases. It bridges the gap between static files and intelligent retrieval by offering multiple search modes, ranging from fast keyword matching to sophisticated semantic vector search.
This skill is particularly valuable for developers and researchers using Openclaw Skills who need to integrate their personal notes, technical documentation, or meeting transcripts into AI-driven workflows. By providing structured JSON output and an integrated MCP server, it allows AI agents to precisely locate and retrieve the context they need from your local environment.
qmd Local Markdown Search Use Cases
- Finding specific implementation details within large technical documentation sets.
- Performing semantic queries across personal notes to find related concepts without exact keyword matches.
- Feeding relevant local context into AI coding agents to improve generation accuracy.
- Retrieving specific segments of meeting transcripts using line-based retrieval.
How qmd Local Markdown Search Works
- The user defines a collection by pointing qmd to a local directory containing markdown files.
- An embedding process is initiated to generate vector representations of the content for semantic understanding.
- The user or an agent issues a search command using one of three modes: BM25 (keyword), vsearch (vector), or query (hybrid LLM).
- qmd processes the request and returns structured data, which can include document snippets, full text, or specific line ranges.
qmd Local Markdown Search Setup
To get started with this skill for your Openclaw Skills setup, follow these steps:
# Install the qmd CLI globally
bun install -g https://github.com/tobi/qmd
# Initialize your first collection
qmd collection add ~/your-notes-folder --name notes --mask "**/*.md"
# Generate embeddings for semantic search
qmd embed
qmd Local Markdown Search Data Schema & Taxonomy
qmd manages your knowledge through a structured indexing system. The following table describes how it organizes data:
| Component | Description |
|---|---|
| Collection | A named group of files defined by a path and a file mask. |
| BM25 Index | Optimized for lightning-fast exact keyword matches. |
| Vector Index | Stores high-dimensional embeddings for conceptual search. |
| JSON Schema | All outputs provide metadata including file paths, scores, and line numbers. |
qmd Local Markdown Search Advanced Features
- Hybrid LLM re-ranking that uses language models to ensure the most relevant results are ranked first.
- Integrated MCP Server support for native integration with modern AI agent protocols.
- Multi-get capabilities allowing the retrieval of multiple documents or glob patterns in a single command.
- Flexible retrieval options including specific line ranges and byte-count limits to respect context windows.
SKILL.md
Loading
Related Openclaw Skills
Naver Search Skill
A specialized search integration for OpenClaw agents to access real-time Korean web data including news, shopping, images, and local business information.
MoltSci
MoltSci is a decentralized research repository designed for AI agents to publish, peer-review, and discover high-rigor scientific papers.
Agent Zero Bridge
A bidirectional bridge enabling Clawdbot to delegate complex, autonomous coding and research tasks to the Agent Zero framework.
Affiliatematic - Amazon Affiliate AI Automation
Automate your Amazon affiliate marketing with AI-driven product recommendations that match your content perfectly.
Reve AI Image Generation
A high-performance CLI tool for generating, editing, and remixing images using the Reve AI API and Bun runtime.
Star Office UI
A collaborative pixel-art dashboard that visualizes the real-time status and movement of multiple AI agents in a virtual workspace.
Featured*
