A zero-API key research tool that combines multi-engine search with intelligent fallback crawling to deliver structured data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-research
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 smart-research 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 Smart Research?
Smart Research is a comprehensive web investigation utility designed to provide AI agents with high-fidelity information retrieval capabilities. By utilizing Openclaw Skills, this tool bypasses the need for expensive search API keys by leveraging multiple public engines like Baidu, DuckDuckGo, and Bing. It is built for developers who need a reliable way to transform the vast web into clean, structured Markdown for LLM consumption.
The core value of this skill lies in its resilience. It doesn't just search; it employs a sophisticated multi-layer fallback system for fetching content, ensuring that even if one crawling method fails, others like crawl4ai, Jina, or Playwright are ready to step in. This makes it an essential part of any autonomous research workflow powered by Openclaw Skills.
Smart Research Use Cases
- Automated market research and competitor analysis using multiple search engines.
- Gathering the latest technical documentation or research papers for AI coding assistants.
- High-reliability web scraping for dynamic websites that require browser rendering.
- Creating comprehensive data snapshots for specific topics using the deep search functionality.
How Smart Research Works
- The skill receives an action request such as research, search, or fetch.
- In research mode, the Search Layer queries multiple engines with automatic fallback to find the most relevant URLs.
- The Fetch Layer processes these URLs through a prioritized chain of extraction services to ensure content is captured.
- The Fusion Layer standardizes the extracted data into a structured format, including scores and metadata.
- A final JSON object is returned containing the query results, source types, and clean Markdown content.
Smart Research Setup
To get started with this tool from the Openclaw Skills collection, ensure you have Python 3 and uv installed. Run the following commands to set up the environment:
# Install required dependencies
uv pip install requests baidusearch crawl4ai playwright
# Initialize Playwright for dynamic rendering
python3 -m playwright install
Smart Research Data Schema & Taxonomy
The skill organizes research data into a clear schema to allow for easy parsing by AI agents. All responses include a success flag and detailed metadata.
| Attribute | Description |
|---|---|
query |
The original search string used |
search_results |
A list of objects containing title, href, and snippet |
source_type |
The specific engine that provided the result (e.g., Bing) |
fetch_method |
The extraction tool used (e.g., crawl4ai, jina, playwright) |
content |
The full, cleaned Markdown content of the target page |
Smart Research Advanced Features
- Zero API Key architecture leveraging free and open-source web services.
- Intelligent multi-layer fallback chain (crawl4ai → Jina → markdown.new → defuddle → Playwright).
- Deep search mode for extended result counts and deeper crawling depth.
- Automated noise reduction and Markdown conversion for LLM-ready inputs.
- Unified Openclaw Skills interface for executing search, fetch, and research in one call.
SKILL.md
Loading
Related Openclaw Skills
Headphone Review
A high-fidelity AI agent skill designed to generate comprehensive, human-like reviews for headphones, IEMs, and TWS devices using multilingual web research.
Text to Markdown
A specialized text pre-processor that structures raw data to enable high-quality AI-driven Markdown generation.
Mermaid Canvas
A specialized rendering engine that transforms Mermaid code into high-quality PNG images using a browser-based canvas.
Wedding Planner Co-pilot
An AI-powered wedding planning co-pilot that manages budgets, vendors, and complex family dynamics entirely on your local machine.
kinthai-Self-Improving-User
A sophisticated self-improvement layer that enables AI agents to learn from individual user preferences, corrections, and mistakes in real-time.
North Face Brand Intelligence
A structured intelligence module for AI agents to query the history, business map, and market performance of the North Face brand.
Featured*
