Does this skill require a local installation of Chrome?

Yes, this skill requires Google Chrome to be installed on your system to perform the browser interactions.

Can I use this for websites that require a login?

Yes, the browser maintains a persistent state (cookies and sessions) between commands, allowing you to log in and perform sequential actions.

How do I see what the browser is doing?

The skill automatically generates screenshots after major actions, which can be viewed to verify the state of the page.

What CLI tool does this skill use?

It utilizes the Stagehand CLI to translate Claude's natural language instructions into browser actions.

Browser Automation

Name: Browser Automation
Author: greyhaven-ai

bygreyhaven-ai

•

Browser Automation

Automates web browser interactions using natural language via CLI commands to navigate, interact, and extract data from any website.

About

This skill provides Claude Code with the ability to control a Chrome browser directly through the Stagehand CLI, enabling complex web-based tasks through natural language. It allows for seamless navigation, form filling, button clicks, and structured data extraction with optional JSON schemas. Designed for efficiency, it maintains a persistent browser instance to preserve session states and cookies while providing visual feedback through automated screenshots, making it ideal for web scraping, automated testing, and interacting with web applications that lack an API.

Key Features

Persistent browser sessions to maintain state and cookies between commands.
15 GitHub stars
Natural language command execution for browser navigation and interaction.
Structured data extraction from web pages using optional JSON schemas.
Element discovery and observation to understand complex page structures.
Automated visual verification via high-resolution screenshots.

Use Cases

Automating repetitive data collection and web scraping tasks.
Testing web application workflows and UI elements via CLI.
Interacting with websites and forms that do not provide public APIs.

About

Key Features

Persistent browser sessions to maintain state and cookies between commands.
15 GitHub stars
Natural language command execution for browser navigation and interaction.
Structured data extraction from web pages using optional JSON schemas.
Element discovery and observation to understand complex page structures.
Automated visual verification via high-resolution screenshots.

Use Cases

Automating repetitive data collection and web scraping tasks.
Testing web application workflows and UI elements via CLI.
Interacting with websites and forms that do not provide public APIs.