A high-performance local document retrieval engine that provides weighted keyword searching and incremental indexing without requiring a vector database.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doc-search-skill
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 doc-search-skill 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 Doc Search?
Doc Search is a specialized utility designed for developers and researchers who need to navigate large volumes of local documentation, code comments, and text files. As a core part of the Openclaw Skills ecosystem, it provides a multi-strategy search approach that ranks results by relevance, looking through filenames, headers, and body content. Unlike heavy semantic search engines, it remains lightweight and fast by utilizing traditional indexing techniques.
This skill is built to handle Markdown, plain text, and source code files with ease. By integrating Doc Search into your workflow, you gain the ability to pinpoint information across thousands of files instantly. It bridges the gap between basic grep commands and complex enterprise search solutions, making it an essential addition to any developer's toolkit using Openclaw Skills.
Doc Search Use Cases
- Rapidly locating technical specifications within large project documentation folders.
- Searching for specific code implementations or comments across a multi-repository codebase.
- Powering content retrieval for personal knowledge management (PKM) and note-taking systems.
- Extracting specific metadata from Markdown frontmatter across hundreds of files using Openclaw Skills.
- Navigating and auditing configuration files within complex project structures.
How Doc Search Works
- The tool scans designated directories based on user-defined file types and exclusion patterns.
- For large-scale projects, an indexing script parses file content and metadata to create a structured JSON index.
- When a query is executed, the engine applies a weighted scoring system (e.g., matching a filename ranks higher than matching body text).
- The system retrieves the matching lines along with a configurable number of surrounding context lines for better clarity.
- Results are returned in a structured format, allowing for easy integration with other tools in the Openclaw Skills suite.
Doc Search Setup
To get started with this search utility in the Openclaw Skills environment, follow these installation and configuration steps:
- Ensure you have the necessary Python scripts in your project directory.
- Perform a direct search without an index for immediate results:
python scripts/search.py "your_search_term" /path/to/docs --context 3
- For optimized performance on large datasets, build a local index:
python scripts/indexer.py /path/to/docs --output index.json
- Execute high-speed searches against the pre-built index:
python scripts/search.py "your_search_term" --index index.json
- (Optional) Create a
.docsearch.yamlin your root directory to define custom include/exclude rules.
Doc Search Data Schema & Taxonomy
The skill utilizes a structured weighting system to ensure the most relevant files appear first in search results. This data organization is a hallmark of Openclaw Skills.
| Priority | Match Type | Weight |
|---|---|---|
| 1 | Exact Filename Match | 100 |
| 2 | Filename Partial Match | 80 |
| 3 | Heading/H1 Match | 70 |
| 4 | Frontmatter Match | 60 |
| 5 | Body Content Match | 40 |
All results are output in a standardized JSON format containing the file path, relevance score, and match details including line numbers and context snippets.
Doc Search Advanced Features
- Incremental Indexing: Only updates the index for files that have been modified since the last scan, significantly reducing overhead.
- Multi-Strategy Ranking: Combines filename, metadata, and body content analysis for superior result accuracy.
- Context-Aware Results: Provides N lines of surrounding text to help users understand the match without opening the file.
- Configurable Filtering: Supports YAML-based configuration to ignore specific directories like node_modules or .git and focus on relevant file types.
- Developer API: Includes a Python API for programmatic access, allowing you to build custom search interfaces powered by Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
TradingView Signal Parser
A high-performance tool for converting TradingView text and chart links into structured trading data.
hexmem
A SQLite-powered persistent memory system that gives AI agents structured self-knowledge, identity continuity, and long-term fact retention.
Archon Decentralized Identity
Archon is a comprehensive decentralized identity system providing local node management, DID operations, and secure vault storage for AI agents.
Scryfall MTG Card Search
A high-performance Magic: The Gathering card data retrieval skill powered by the Scryfall API for AI agents.
Lyrical Fable AI Storyteller
An AI-powered creative engine for generating luminous, first-person philosophical fables inspired by legendary literary stylists.
DGR: Decision-Grade Reasoning
DGR is a reasoning governance protocol that produces machine-validated, auditable decision records for high-stakes AI outputs.
Featured*
