A lightweight Puppeteer-based tool for controlling existing Chrome instances via the Chrome DevTools Protocol.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install chrome-cdp-controller
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 chrome-cdp-controller 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 Chrome CDP Controller?
The Chrome CDP Controller is a developer-centric automation tool that leverages the Chrome DevTools Protocol (CDP) to interact with a running browser instance. Unlike traditional headless automation that spawns new browser processes, this Openclaw Skills integration connects to your existing environment, making it faster and less intrusive for local development workflows.
It allows developers to programmatically navigate pages, simulate user interactions, and extract data without disrupting their main browsing session. By utilizing puppeteer-core, it provides a powerful yet lightweight interface to automate complex web tasks while keeping your primary workspace open and active.
Chrome CDP Controller Use Cases
- Automated web scraping of dynamic platforms like Taobao or Amazon to extract real-time pricing data
- Interacting with AI web applications such as ChatGPT or Claude for automated prompting and data retrieval
- Monitoring and intercepting network traffic to debug API responses or capture data packets
- Performing automated UI testing on local web development projects to ensure frontend stability
- Generating programmatic screenshots for documentation or visual regression testing
How Chrome CDP Controller Works
- Launch Chrome with remote debugging enabled on a specific port to expose the CDP interface.
- Retrieve the unique WebSocket Debugger URL from the local JSON version endpoint provided by the browser.
- Connect the Puppeteer-based controller to the existing browser session using the retrieved WebSocket URL.
- Execute a sequence of JSON-defined commands or Node.js API calls to perform browser actions like clicking, filling forms, or navigating.
- Capture requested data or screenshots and automatically close the automation tab once the task lifecycle is complete.
Chrome CDP Controller Setup
First, ensure Chrome is running with remote debugging enabled:
# macOS example
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222 &
Install the required Openclaw Skills dependencies to get started with the controller:
cd chrome-cdp-controller
npm install
Retrieve your WebSocket URL to connect the agent:
curl -s http://localhost:9222/json/version | grep -o '"webSocketDebuggerUrl":"[^"]*"' | cut -d'"' -f4
Chrome CDP Controller Data Schema & Taxonomy
The skill processes automation workflows via a JSON command array and outputs structured results based on the interaction type.
| Command Type | Parameter | Description |
|---|---|---|
| navigate | url | The target web address to load |
| click | selector | CSS selector for the element to be clicked |
| fill | text | The content to input into a form field |
| evaluate | script | Custom JavaScript to run within the page context |
| screenshot | path | The local filesystem path where the image will be saved |
Chrome CDP Controller Advanced Features
- Real-time network response interception with custom URL pattern matching for API monitoring
- High-fidelity human interaction simulation including character-by-character typing and configurable delays
- Complex data extraction capabilities through direct JavaScript execution using the evaluate engine
- Support for multi-step workflow orchestration via external JSON configuration files
- Non-intrusive tab management that ensures the parent browser remains stable and unaffected by automation scripts
SKILL.md
Loading
Related Openclaw Skills
Gemini Deep Research CLI
Automate comprehensive multi-source inquiries and structured report generation using the Gemini CLI.
Dialogflow CX to CES Migration Tool
A production-grade utility for automating the migration of Dialogflow CX agents to the Google Customer Engagement Suite (CES) framework.
Stock OCR
A specialized tool for capturing K-line screenshots from financial terminals and extracting Moving Average (MA) values through high-precision OCR.
Polling Best Practices
A guidance-driven skill for automating long-running, asynchronous background tasks using a robust, cron-compatible polling pattern.
Agent Browser
A high-performance Rust-based headless browser CLI that empowers AI agents to interact with web pages through structured commands and element references.
PPTX Notes Editor
A specialized technical utility for AI agents to unpack, modify, and manage PowerPoint speaker notes through direct XML manipulation.
Featured*
