A sophisticated multi-layered browsing engine designed for automated information gathering, data extraction, and real-time website monitoring.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install web-browser-toolkit
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 web-browser-toolkit 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 Web Browser Toolkit?
The Web Browser Toolkit is a comprehensive suite within the Openclaw Skills ecosystem designed for professional-grade web interaction. It utilizes a unique 3-layer architecture that automatically selects the most efficient browsing method based on the target site's complexity, ranging from lightweight curl fetches to full Playwright-based browser automation.
This toolkit is specifically engineered to handle both static and dynamic content, ensuring that users can extract structured data from modern SPA frameworks like React or Vue. It excels at transforming messy HTML into clean, structured JSON, making it an essential asset for developers and researchers who need reliable, automated web data pipelines.
Web Browser Toolkit Use Cases
- Automated research across multiple pages to generate consolidated reports.
- Real-time monitoring of regulatory websites (e.g., FAA, ICAO) for airworthiness directives or policy updates.
- Structured data extraction from e-commerce sites, news portals, and technical blogs.
- Simulating user interactions such as logins, form submissions, and infinite scrolling for deep-web scraping.
- Competitive intelligence gathering by tracking changes in competitor pricing or announcements.
How Web Browser Toolkit Works
- Protocol Selection: The system analyzes the target URL and determines the required depth (Layer 1: curl, Layer 2: Python BS4, or Layer 3: Playwright).
- Content Acquisition: The toolkit navigates to the site, handles JavaScript rendering if necessary, and captures the raw content.
- Data Extraction: Using predefined CSS selectors or automated content detection, it isolates relevant text, tables, and links.
- Structure & Tagging: Extracted data is passed through a structurizer that organizes information into a standardized JSON schema and applies automated tagging.
- Change Detection: For monitoring tasks, the toolkit compares the new snapshot against a stored baseline to identify and alert on differences.
Web Browser Toolkit Setup
To get started with this toolkit in the Openclaw Skills environment, ensure you have python3 and curl installed, then configure your environment:
# Install dependencies (BeautifulSoup4 and Playwright)
pip install beautifulsoup4 playwright
playwright install
# Basic fetch test
web_fetch https://example.com
# Start the browser engine for dynamic sites
openclaw browser start
Web Browser Toolkit Data Schema & Taxonomy
The toolkit organizes data into a consistent JSON format to ensure interoperability between Openclaw Skills.
| Field | Description |
|---|---|
metadata |
Includes collection_id, source_url, and method used. |
pages |
An array containing title, content, and extracted_data (tables/links). |
summary |
Statistics on success rates and total items gathered. |
tags |
Machine-generated labels based on content analysis. |
Web Browser Toolkit Advanced Features
- 3-Layer Fallback System: Automatically escalates from simple fetchers to full browsers if bot detection or JS-rendering issues occur.
- Aviation Industry Presets: Specialized configurations for ICAO and FAA data harvesting.
- Automated Monitoring & Diffs: Integrated cron support to track website changes and generate weekly delta reports.
- Sub-Skill Integration: Seamlessly works with the doc-recommender module to suggest official documentation based on scraped keywords.
- Interaction Scripting: Support for custom browser evaluations, screenshots, and PDF generation of live web states.
SKILL.md
Loading
Related Openclaw Skills
Bid Proposal Manager
An intelligent bid and proposal management system that parses multi-format announcements, vectorizes content for semantic search, and automates Notion project creation.
Entertainment 8
An AI-powered entertainment analysis tool that uncovers deep connections between celebrities, industry news, and the symbolic number 8.
Git Dirty Check
A specialized read-only tool for triaging uncommitted changes and identifying potential risks in a local git repository.
Browser Account Controller
A Python-based automation bridge for controlling multi-account browser profiles through a local HTTP API interface.
s-skill: Smart Code Assistant
An intelligent coding companion that provides deep code understanding, precise error diagnosis, refactoring suggestions, and automated documentation.
TestDino Playwright CI Intelligence
Connects your AI agent to TestDino for natural language insights into Playwright CI test runs, failure patterns, and project health.
Featured*
