A natural language interface for automating browser actions, web navigation, and data extraction via CLI.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browser-pc
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 browser-pc 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 Browser Automation Skill?
The Browser Automation skill enables AI agents to interact with the web just like a human would, using the Stagehand CLI. By integrating this into your Openclaw Skills library, you allow your agent to navigate URLs, click buttons, fill out forms, and extract structured data using simple English commands rather than complex CSS selectors.
This skill is designed for flexibility, offering an automatic environment selection system. It can run locally using a standard Chrome installation for development or switch to remote environments like Browserbase for production-grade scraping, stealth requirements, and CAPTCHA solving without needing manual user intervention.
Browser Automation Skill Use Cases
- Automating complex web workflows like account creation or form filling
- Scraping structured data from modern, dynamic web applications
- Performing automated UI testing and capturing screenshots for visual verification
- Researching information across multiple websites using natural language queries
- Executing stealthy web operations through remote proxy environments
How Browser Automation Skill Works
- The skill detects the environment by checking for Browserbase API keys in the configuration.
- It initializes either a local Chrome instance or a remote browser session.
- The user or agent issues a navigation command to load a specific web address.
- Natural language instructions are processed to perform actions (click, type) or extract specific data points.
- Screenshots are generated to verify the success of the requested interactions.
- The session is closed to ensure clean resource management within the Openclaw Skills framework.
Browser Automation Skill Setup
First, ensure you have Node.js installed. Navigate to the skill directory and run the following commands:
npm install
npm link
To enable remote execution, add your credentials to the .env file:
BROWSERBASE_API_KEYBROWSERBASE_PROJECT_ID
If these keys are absent, the skill will default to using your local Chrome installation.
Browser Automation Skill Data Schema & Taxonomy
The skill utilizes a command-based schema to manage browser states and data retrieval:
| Command | Purpose | Input Type |
|---|---|---|
navigate |
Sets the current URL | String (URL) |
act |
Executes a UI interaction | String (Instruction) |
extract |
Retrieves data from page | String (Instruction) + Optional JSON Schema |
observe |
Lists interactable elements | String (Query) |
screenshot |
Captures current view | None |
close |
Ends the session | None |
Browser Automation Skill Advanced Features
- Intelligent environment switching between Local and Browserbase modes
- Natural language element discovery using the observe command
- Support for structured JSON schemas during data extraction tasks
- Stealth mode and proxy support for advanced web scraping scenarios
- Seamless integration with Openclaw Skills workflows via global CLI commands
SKILL.md
Loading
Related Openclaw Skills
Browser Automation
An AI-powered browser automation tool that executes natural language commands to navigate, interact with, and extract data from any website.
Browser Automation
A powerful CLI skill for automating web browser interactions and data extraction using natural language commands.
Tavily Search
An AI-optimized web search skill that delivers clean, relevant web data and deep research capabilities for Openclaw Skills agents.
OpenClaw IM Channel Integration
A unified configuration suite to connect OpenClaw AI agents with popular messaging platforms like Telegram, Slack, and Discord.
Browserbase Functions: Serverless Browser Automation
A comprehensive skill for deploying, managing, and invoking serverless browser automation using the Browserbase CLI and SDK.
Browser Automation
A natural language browser automation skill that enables AI agents to navigate web pages, extract data, and interact with web elements via the CLI.
Featured*
