A high-performance full-text search engine for Markdown documentation archives powered by SQLite FTS5.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install md-docs-search
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 md-docs-search 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 md-docs-search?
md-docs-search is a specialized utility designed to manage and query large-scale Markdown documentation repositories. By leveraging SQLite's FTS5 engine and BM25 relevance ranking, it allows developers and researchers to perform lightning-fast searches across thousands of documents. This skill is a core component of Openclaw Skills, providing a robust solution for knowledge base exploration and technical specification lookups.
The tool is particularly effective for documentation sets that use standard delimiters and source URL patterns. It transforms static Markdown files into a dynamic, searchable database, ensuring that critical information is always accessible within seconds. Whether you are performing deep technical research or looking for specific configuration details, this skill streamlines the discovery process.
md-docs-search Use Cases
- Searching through extensive documentation archives for specific features or technical capabilities.
- Identifying official source URLs for accurate citations in technical reports and papers.
- Extracting technical specifications, configuration details, or limitations from complex docsets.
- Performing multi-source research across different vendors or project documentation simultaneously.
How md-docs-search Works
- The indexing process scans a designated directory containing Markdown files separated by triple-dash delimiters.
- It extracts metadata, including titles and source URLs marked with the specific *Source: pattern.
- Data is populated into a SQLite FTS5 virtual table, enabling advanced full-text search capabilities.
- Users execute search queries via the CLI, utilizing boolean operators, phrase matching, or prefix searches.
- The system returns BM25-ranked results, including context snippets and direct links to original sources.
md-docs-search Setup
To get started with this skill in your Openclaw Skills environment, follow these steps:
# 1. Index your documentation directory (one-time setup)
scripts/docs.py index ./docs
# 2. Verify the index status
scripts/docs.py status
# 3. Perform your first search
scripts/docs.py search "your query here"
md-docs-search Data Schema & Taxonomy
The skill organizes data using a structured SQLite database (docs.db) with the following schema characteristics:
| Component | Description |
|---|---|
| Document Delimiter | Articles must be separated by --- |
| Source Pattern | URLs should follow the *Source: <URL>* format |
| Indexing Engine | SQLite FTS5 with BM25 ranking |
| Metadata | Includes Title, Source URL, and Full Content |
Indexes can be localized within specific documentation folders for multi-source isolation.
md-docs-search Advanced Features
- Multi-source support allowing separate databases for different projects or vendors.
- Advanced FTS5 query syntax including boolean operators (AND, OR, NOT) and proximity searches.
- Customizable output formats including JSON and Markdown for easy piping to other tools.
- Title-only search mode for high-precision discovery.
- Automatic source URL extraction for automated citation workflows within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Tweet Processor Skill
Automatically extracts and categorizes high-value technical insights from X/Twitter links into structured Markdown notes.
CAPTCHAS Integration for OpenClaw
A specialized skill designed to bridge the CAPTCHAS Agent API with the OpenClaw ecosystem for advanced bot protection and identity verification.
Task Router
A distributed task queue and agent coordinator designed for complex multi-agent systems to manage routing, load balancing, and task lifecycles.
Solar Weather Monitor
A real-time space weather monitoring tool providing data on solar flares, geomagnetic storms, and aurora forecasts via NOAA.
Windsor.ai Analytics Connector
Empower your AI agents with the ability to analyze 325+ marketing and business data sources via Openclaw Skills and Windsor.ai.
Social Content Strategist
A comprehensive toolkit for AI agents to plan, create, and optimize high-performing social media content across all major platforms.
Featured*
