A high-performance web extraction tool that leverages Microsoft Edge and Playwright to capture content from complex, dynamic web pages.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edge-browser
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 edge-browser 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 Edge Browser Controller?
The Edge Browser Controller is a specialized tool designed to provide AI agents with robust web browsing capabilities. By utilizing Microsoft Edge via the Playwright framework, this skill enables the fetching of web pages that require full JavaScript rendering, which traditional HTTP requests often fail to process. It is a critical component for Openclaw Skills when dealing with modern web applications or sites protected by advanced bot detection systems.
This skill ensures that your agent can see exactly what a human user would see, extracting both raw HTML and cleaned text content. It serves as a reliable alternative to standard Chrome-based tools, offering flexibility through fallback mechanisms and customizable execution parameters.
Edge Browser Controller Use Cases
- Accessing web pages that explicitly require Microsoft Edge for optimal compatibility.
- Scraping data from Single Page Applications (SPAs) where content is dynamically loaded via JavaScript.
- Overcoming anti-scraping barriers that block standard headless browsers or automated fetching scripts.
- Providing a reliable fallback when other browser-based Openclaw Skills fail due to environment or site-specific restrictions.
How Edge Browser Controller Works
- The AI agent triggers the skill by providing a target URL and optional parameters such as wait time.
- The system attempts to launch an instance of the Microsoft Edge browser using Playwright.
- If Microsoft Edge is not found in the default system paths, the script automatically falls back to a Chromium instance to ensure continuity.
- The browser navigates to the specified URL and waits for the page to reach a stable state or for a user-defined timeout.
- The controller extracts the page title, full HTML source, and a text-only representation of the content.
- The extracted data is returned as a structured JSON object or saved to a local file for further processing.
Edge Browser Controller Setup
To use this skill, ensure you have Playwright installed and the necessary browser binaries available:
pip install playwright
playwright install chromium
Basic usage command:
python ~/.openclaw/skills/edge-browser/scripts/fetch.py <URL> --wait 5 --output result.json
Edge Browser Controller Data Schema & Taxonomy
The skill returns and organizes data using a structured JSON format. Below are the primary fields generated during a fetch operation:
| Key | Type | Description |
|---|---|---|
| url | string | The final URL reached after any redirects. |
| title | string | The HTML document title of the fetched page. |
| content | string | The full, rendered HTML source code of the page. |
| text | string | The cleaned text content extracted from the body of the page. |
| status | string | The execution status indicator (e.g., "success"). |
Edge Browser Controller Advanced Features
- Intelligent Fallback: Automatically switches to Chromium if the Edge binary is unavailable in the host environment.
- Dynamic Loading Support: Includes a
--waitparameter to allow asynchronous content and JavaScript elements to fully render before extraction. - Anti-Detection Configuration: Uses a specific Edge User-Agent to better mimic legitimate user traffic and reduce the likelihood of being flagged by security filters.
- File-Based Persistence: Supports direct output to JSON files, facilitating easy integration within complex multi-step Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
Agent Father Skill
A comprehensive lifecycle management tool for creating, configuring, and onboarding AI agents and digital employees.
Hyperliquid Prime
A specialized prime broker layer for Hyperliquid that provides intelligent order routing and liquidity aggregation across native and HIP-3 perp markets.
YouTube Transcription Generator (VLM Run)
An automated tool to download YouTube content and generate high-quality transcriptions with optional timestamps using the VLM Run Orion visual AI.
Travel Destination Brochure & Video Generator
An automated tool that transforms a city name into a complete travel package including street-level imagery, landmark photos, AI-generated videos, and detailed itineraries.
Bright Data Web Scraping & Search
A high-performance scraping and search skill that bypasses bot detection to deliver markdown content and structured Google results.
Juicebox V5 Skills Collection
A comprehensive suite of Openclaw Skills for architecting, deploying, and managing complex treasury protocols, Revnets, and omnichain financial systems.
Featured*
