browser-use

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

47|8|Updated Sep 13, 2025
One-click install
npx skills add https://github.com/lvndry/jazz --skill browser-use-lvndry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/lvndry/jazz/tree/main/skills/browser-use
Command: npx skills add https://github.com/lvndry/jazz --skill browser-use-lvndry

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions to perform web testing, form filling, data extraction, and screenshots. This Skill helps automate repetitive browser tasks, reduces manual clicks, and ensures consistent results across sessions.

Core Features & Use Cases

  • Automated navigation and interaction: Open pages, inspect elements, click, type, and capture screenshots.
  • Data extraction: Retrieve visible text and values for analysis or archival purposes.
  • Form automation and testing: Fill fields, submit forms, and verify responses across multi-step flows.
  • Multi-session support: Manage multiple browser sessions or profiles to test across different contexts.

Quick Start

Use the browser-use skill to open a site, inspect elements, and perform interactions. Example:

  • browser-use open https://example.com
  • browser-use state
  • browser-use click 0
  • browser-use type "Sample text"
  • browser-use screenshot

Frequently Asked Questions about browser-use

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

FAQPage Schema
How do I automate web testing and form filling across multiple pages?

Automating browser tasks involves using CLI commands to open pages, inspect element states, click, type, and capture screenshots. This handles multi-step flows end-to-end to ensure consistent results across sessions.

What is the best way to extract visible text and data from web pages?

Data extraction is performed by navigating to a target site and retrieving visible text and values via the browser state. This allows you to collect page content for analysis or archival purposes across diverse sites and APIs.

Do I need a specific browser environment to run browser automation tasks?

Yes, browser automation requires a compatible browser environment, which runs headless by default. It relies on the browser-use CLI to execute commands like open, state, click, type, and screenshot.

Can I use Python or JavaScript for browser interaction and web testing?

Yes, browser interaction supports optional integrations for Python or JavaScript. You can use these languages alongside the CLI to automate navigation, inspect elements, and collect results across diverse sites.

How do I capture screenshots during automated web testing?

You capture screenshots by issuing a screenshot command after navigating and interacting with the page. This records the visual state of the browser session during automated web testing flows.

How does multi-session support work for testing across different contexts?

Multi-session support allows you to manage multiple browser sessions or profiles simultaneously. This enables you to test web applications across different contexts and ensure consistent behavior.