browser-use

Automate persistent browser interactions for testing, form filling, and data extraction.

2|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/citadelgrad/scott-cc --skill browser-use-citadelgrad
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/citadelgrad/scott-cc/tree/main/plugins/browser-automation/skills/browser-use
Command: npx skills add https://github.com/citadelgrad/scott-cc --skill browser-use-citadelgrad

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates persistent browser interactions for testing, form filling, and data extraction.

Core Features & Use Cases

  • Persistent sessions keep a browser open across commands for multi-step workflows.
  • Navigate, inspect, and interact using element indices to automate complex web tasks.
  • Screenshots and data capture to verify results or extract information from web pages.
  • Agent tasks (optional) leverage AI-assisted automation when an API key is configured.

Quick Start

browser-use open https://example.com browser-use state browser-use click 0 browser-use type "Hello" browser-use screenshot browser-use close

Frequently Asked Questions about browser-use

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks for web testing and data extraction?

Automate browser tasks by using a CLI to maintain persistent sessions for web testing and data extraction. You can navigate pages, inspect elements, interact by index, fill forms, and capture screenshots across multi-step workflows.

How do I fill out web forms automatically using browser commands?

Fill out web forms automatically by opening a target URL in a persistent browser session, selecting the input field by its element index, and typing the desired text string directly via the command line interface.

Can I take screenshots during automated web testing workflows?

You can take screenshots during automated web testing by executing a screenshot command within your persistent browser session. This captures the current page state to verify results or extract visual information from web pages.

Does browser automation support both headless and headed modes?

Browser automation supports headless, headed, real, and remote browser modes. This allows you to run automated testing and data extraction workflows either in the background or with a visible browser window.

What is the best way to inspect and interact with web elements by index?

The best way to inspect and interact with web elements by index is using a persistent browser session that keeps state across commands. You retrieve the page state and execute click or type actions targeting specific element indices.

Do I need an API key for AI-assisted browser automation?

You need an API key only for optional AI-assisted agent tasks. Standard browser automation for navigation, element interaction, and data extraction works without an API key by using the installed browser-use CLI.