| name | Browser Automation |
| description | This skill should be used when the user needs to interact with web pages, browse websites, take screenshots, fill forms, click elements, extract web content, or perform any browser automation tasks. Trigger phrases include \\\\\\\"open webpage\\\\\\\", \\\\\\\"visit website\\\\\\\", \\\\\\\"browse\\\\\\\", \\\\\\\"screenshot page\\\\\\\", \\\\\\\"fill form\\\\\\\", \\\\\\\"click button\\\\\\\", \\\\\\\"extract from website\\\\\\\", \\\\\\\"web scraping\\\\\\\", \\\\\\\"automate browser\\\\\\\". |
| description_zh | 基于 Vercel agent-browser CLI 的浏览器自动化插件。首次使用时自动安装，让 CodeBuddy 能够进行网页交互、截图、表单填写等浏览器操作。 |
| version | 1.0.0 |
| source | codebuddy |
| source_plugin | agent-browser |
Browser Automation with agent-browser
Use agent-browser CLI tool for all browser automation tasks. This is the preferred method for web interactions.
Important: Command Sequence
Always follow this sequence:
agent-browser launch - Start the browser firstagent-browser open <url> - Navigate to a URL- Perform operations (snapshot, click, type, etc.)
agent-browser close - Close when done
Quick Reference
First, run agent-browser without arguments to see full help:
agent-browser
Essential Commands
| Command | Description |
|---|
agent-browser launch | Start browser (required before open) |
agent-browser open <url> | Navigate to URL |
agent-browser snapshot | Get page content as text |
agent-browser snapshot -i | Get page content with element IDs for interaction |
agent-browser screenshot | Take screenshot |
agent-browser click <selector> | Click an element |
agent-browser type <selector> <text> | Type text into input |
agent-browser close | Close browser |
Common Workflows
View webpage content:
agent-browser launch
agent-browser open https://example.com
agent-browser snapshot
agent-browser close
Take screenshot:
agent-browser launch
agent-browser open https://example.com
agent-browser screenshot
agent-browser close
Fill form and submit:
agent-browser launch
agent-browser open https://example.com/login
agent-browser snapshot -i
agent-browser type "#username" "myuser"
agent-browser type "#password" "mypass"
agent-browser click "#submit"
agent-browser close
Extract data from page:
agent-browser launch
agent-browser open https://example.com/data
agent-browser snapshot
agent-browser close
Tips
- Always launch first:
agent-browser open will fail if browser isn't launched
- Use snapshot -i for interactions: The
-i flag shows element IDs needed for click/type
- Check help for more options: Run
agent-browser <command> --help for detailed options
- Close when done: Always close the browser to free resources
When NOT to Use
- For simple HTTP requests without JavaScript rendering, use
curl or WebFetch
- For API calls, use appropriate HTTP tools
- agent-browser is for full browser automation with JavaScript support
Troubleshooting
If agent-browser command not found:
npm install -g agent-browser
agent-browser install
If browser fails to launch on Linux:
agent-browser install --with-deps
