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.
Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.
What it does
Automate web browser interactions using natural language via CLI commands
When to use it
the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications
How agents load it
Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: Browser Automation; First: Environment Selection (Local vs Remote); Setup (First Time Only); Commands; Quick Example; Mode Comparison. It includes spec-recommended sections: input/output examples.
File analysis
File analysis: instruction-only skill (SKILL.md). The agent loads the full body when activated.
Browser AutomationFirst: Environment Selection (Local vs Remote)Setup (First Time Only)CommandsQuick ExampleMode ComparisonBest PracticesTroubleshooting
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.
allowed-tools
BashExperimental field; support depends on the client and does not grant permissions by itself.
DiscoverThe client exposes names and descriptions to the agent.
ActivateYour request or the task context selects the skill and loads its instructions.
Load resourcesReferenced scripts, documentation and assets are used when needed.
Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.
Ask your Agent to install
Copy these instructions to a compatible agent and confirm the target directory matches your client.
Install the agent skill "browser" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-1f9fc18ff8fae5c2-Browser.html
Save it as .cursor/skills/browser/SKILL.md or .claude/skills/browser/SKILL.md and keep the frontmatter name and description exactly as-is.
No unambiguous GitHub package URL is recorded. Follow the original source's installer instructions.
---
name: browser
description: 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.
allowed-tools: Bash
---
# Browser Automation
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`:
```bash
npm install # Install dependencies
npm link # Create global 'browser' command
```
## Commands
All commands work identically in both modes:
```bash
browser navigate # Go to URL
browser act "" # Natural language action
browser extract "" ['{}'] # Extract data (optional schema)
browser observe "" # Discover elements
browser screenshot # Take screenshot
browser close # Close browser
```
## Quick Example
```bash
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](EXAMPLES.md).
For API reference, see [REFERENCE.md](REFERENCE.md).