Notre avis

Automatise les interactions avec un navigateur web via des commandes CLI en langage naturel, avec bascule automatique entre environnement local et distant.

Points forts

Interface en langage naturel réduisant le besoin de scripts complexes
Sélection automatique de l'environnement (local ou Browserbase) sans intervention utilisateur
Fonctionnalités complètes : navigation, actions, extraction de données, capture d'écran, observation d'éléments

Limites

Configuration initiale requise (npm install, Chrome ou clé API Browserbase)
Peut rencontrer des difficultés avec des interactions complexes ou du contenu dynamique
Performances variables selon l'environnement (le mode distant est plus lent)

Quand l'utiliser

Quand vous devez interagir rapidement avec des pages web, extraire des données ou tester des applications sans écrire de code d'automatisation.

Quand l'éviter

Pour du scraping à grande échelle nécessitant des performances élevées ou des workflows multi-étapes avec logique conditionnelle complexe.

Exemples

Screenshot a page

Navigate to https://example.com and take a screenshot

Fill and submit a form

Go to https://example.com/login, fill in the username field with 'user' and password field with 'pass', then click the submit button

Extract search results

Search Google for 'climate change' and extract the titles and URLs of the first 10 results

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:

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

Always navigate first before interacting
View screenshots after each command to verify
Be specific in action descriptions
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.

Automatisation du navigateur

Recommandé pour