QMD Plus enhances local markdown search by using LLMs to expand simple queries into sophisticated lexical and semantic search variations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install qmd-plus
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-plus 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 Plus?
QMD Plus is a powerful enhancement for the qmd search engine, specifically designed to bridge the gap between simple keyword lookups and intelligent information retrieval. By integrating LLM-powered query expansion, this skill transforms a single user prompt into multiple search strategies, including BM25 lexical matching, vector-based semantic search, and Hypothetical Document Embeddings (HyDE).
As a specialized tool within the Openclaw Skills ecosystem, it addresses the challenges of searching large, multilingual markdown knowledge bases. It allows users to find information based on intent and concepts rather than just exact string matches, significantly improving recall and precision for developers and researchers managing extensive personal or technical documentation.
QMD Plus Use Cases
- Navigating massive multilingual markdown note collections where specific keywords may be forgotten.
- Retrieving technical documentation using natural language questions instead of strict CLI syntax.
- Disambiguating vague search terms like "performance" or "logs" by providing intent-based steering signals.
- Finding relevant content in deep archives by generating hypothetical answers (HyDE) to match against existing notes.
How QMD Plus Works
- The user inputs a natural language query via the qmd-plus CLI or MCP interface.
- The skill generates a structured prompt for an external LLM to expand the query into relevant keywords and semantic concepts.
- The external LLM returns a JSON object containing lexical (lex) and vector (vec) search variants.
- QMD Plus constructs a multi-layered qmd query using these expanded terms.
- The local qmd engine executes the search across indexed collections, applying Reciprocal Rank Fusion (RRF) to rerank and present the most relevant results.
QMD Plus Setup
To use this skill, you must have the qmd engine installed and your notes indexed.
# Install the core qmd engine
npm install -g @tobilu/qmd
# Install the qmd-plus skill via ClawHub
clawhub install qmd-plus
# Add your notes to a collection and generate embeddings
qmd collection add ~/my-notes --name notes
qmd embed
QMD Plus Data Schema & Taxonomy
The skill interacts with the qmd engine using a structured query schema to ensure high-fidelity results:
| Component | Type | Description |
|---|---|---|
| lex | Lexical | BM25 keyword matching for exact terms and code identifiers. |
| vec | Vector | Semantic similarity for natural language questions. |
| hyde | Vector | Hypothetical Document Embeddings for finding answers based on expected content. |
| intent | Signal | Contextual steering to disambiguate similar terms. |
| collections | Filter | Optional array to restrict search to specific folders or tags. |
QMD Plus Advanced Features
- Multilingual expansion support to ensure high-quality search results in languages like Chinese and English.
- RRF (Reciprocal Rank Fusion) reranking that blends keyword and semantic scores for optimal result ordering.
- Customizable LLM integration allows you to use your preferred provider (Claude, Kimi, or local models) via CLI wrappers.
- Explain mode to debug search traces and see exactly how different query variations contributed to the final score.
SKILL.md
Loading
Related Openclaw Skills
Harness Evolve
A self-evolution engine that consumes research logs and performs system self-checks to optimize AI agent architectures automatically.
Harness Research
Harness Research is an automated intelligence engine that tracks, analyzes, and maps the latest AI agent research papers directly to your system's improvement goals.
Creem Agent
An autonomous store operations manager that monitors SaaS health, manages failed payments, and handles churn winbacks for Creem.io merchants.
Axios Malware Scanner
A specialized security diagnostic tool to identify and mitigate the 2026 axios supply-chain attack on local development environments.
XiaoHongShu Content Migration
An automated solution for scraping XiaoHongShu notes and cross-posting them to Facebook Meta Business Suite and WordPress via REST API.
Commitment Engine
A robust state-machine framework that converts conversational promises into persistent, trackable, and auto-executing files.
Featured*
