browser-automation

by peytoncasper · View original on ClawHub

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

Module Automation v1.0.0 Audited 2026-02-07
80 Trust

Permissions

File Read Can read project files
File Write No file write access
Network Can access the network
Shell Can execute shell commands

Risk Assessment

Elevated Risk

This skill requests 3 of 4 possible permissions. Elevated scope — ensure each permission is justified. Consider running in a sandbox.

Shell access can execute arbitrary commands. Use a sandbox for extra safety.

SKILL.md

Automate browser interactions using Stagehand CLI with Claude.

First: Environment Selection (Local vs Remote)

The skill automatically selects between local and remote browser environments:

  • If Browserbase API keys exist (BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID in .env file): Uses remote Browserbase environment
  • If no Browserbase API keys: Falls back to local Chrome browser
  • No user prompting: The selection happens automatically based on available configuration

Setup (First Time Only)

Check setup.json in this directory. If setupComplete: false:

npm install    # Install dependencies
npm link       # Create global 'browser' command

Commands

All commands work identically in both modes:

browser navigate <url>                    # Go to URL
browser act "<action>"                    # Natural language action
browser extract "<instruction>" ['{}']    # Extract data (optional schema)
browser observe "<query>"                 # Discover elements
browser screenshot                        # Take screenshot
browser close                             # Close browser

Quick Example

browser navigate https://example.com
browser act "click the Sign In button"
browser extract "get the page title"
browser close

Mode Comparison

Feature Local Browserbase
Speed Faster Slightly slower
Setup Chrome required API key required
Stealth mode No Yes
Proxy/CAPTCHA No Yes
Best for Development Production/scraping

Best Practices

  1. Always navigate first before interacting
  2. View screenshots after each command to verify
  3. Be specific in action descriptions
  4. Close browser when done

Troubleshooting

  • Chrome not found: Install Chrome or use Browserbase mode
  • Action fails: Use browser observe to discover available elements
  • Browserbase fails: Verify API key and project ID are set

For detailed examples, see EXAMPLES.md. For API reference, see REFERENCE.md.

Back to Verified Skills Verify another skill

Related skills in Automation

Why You Need browser-automation

Web browsers are where most modern work happens — but automating browser interactions has traditionally required writing complex Selenium or Playwright scripts. Browser Automation lets you control a web browser using natural language through OpenClaw, making web scraping, form filling, testing, and data extraction as simple as describing what you want.

The skill uses Stagehand CLI with Claude to translate natural language commands into browser actions. It automatically selects between a local Chrome browser and Browserbase's cloud browser based on your configuration, so it works both for local development and headless server environments.

With 546 downloads and growing, this skill is the go-to choice for anyone who needs to automate web interactions without writing browser automation code from scratch.

Common Use Cases

  • Scrape data from websites using natural language descriptions
  • Fill forms, click buttons, and navigate web applications automatically
  • Take screenshots of web pages for documentation or testing
  • Test web applications by describing user flows in plain English
  • Extract structured data from web pages into usable formats

Frequently Asked Questions

Does it work without Browserbase?

Yes. If no Browserbase API keys are configured, it automatically falls back to using your local Chrome browser. Browserbase is optional for cloud/headless usage.

Why does it need shell access?

The skill needs shell access to launch and control the browser process through the Stagehand CLI. It also needs network access to interact with web pages.

Can it handle login-protected pages?

Yes. It can fill in login forms, handle authentication flows, and maintain session state across multiple page navigations.

Related Guides