browser-use

Automates browser navigation, form filling, screenshots, and data extraction via CLI.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/rub803030/examenprograma --skill browser-use-rub803030
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/rub803030/examenprograma/tree/main/EXAMEN_PROGRA_2-master/.agents/skills/browser-use
Command: npx skills add https://github.com/rub803030/examenprograma --skill browser-use-rub803030

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually testing websites, filling repetitive web forms, and scraping page data is slow and error-prone. This Skill provides persistent, scriptable browser automation so you can navigate pages, interact with elements, and extract data through simple CLI commands. ## Core Features & Use Cases - Persistent Browser Sessions: The browser stays open between commands, enabling multi-step workflows like login, navigate, fill form, and verify. - Multiple Browser Modes: Run headless Chromium, a real Chrome instance with your existing profiles and cookies, or a cloud-hosted remote browser. - Data Extraction & Screenshots: Capture page state, element text, HTML, cookies, and screenshots for testing or scraping tasks. - Cloud Agent Tasks: Launch autonomous browser agents in parallel, monitor task status, and manage cloud sessions and tunnels. - Use Case: Test a local dev server by starting it, exposing it through a tunnel, then driving a cloud browser to open the tunnel URL, fill a signup form, and screenshot the result. ## Quick Start Use the browser-use skill to open https://example.com, list the clickable elements on the page, and take a 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 browser interactions from the command line?▼

Use the browser-use CLI: run browser-use open <url> to navigate, browser-use state to list clickable elements with indices, then browser-use click or input to interact. The browser session persists between commands for multi-step workflows.

How to fill out a web form with browser automation?▼

First run browser-use state to get element indices, then use browser-use input <index> "text" for each field and browser-use click <index> to submit. Verify the result with browser-use state or a screenshot.

Can browser automation use my existing Chrome login sessions?▼

Yes. Run with --browser real --profile "Default" to use your local Chrome profile with existing cookies and logins. For cloud browsers, sync cookies from a local profile using browser-use profile sync --from "Default" --domain example.com.

Does browser-use support headless and cloud browsers?▼

Yes. The default chromium mode runs headless, --headed shows a visible window, and --browser remote uses a cloud-hosted browser with proxy support. Cloud sessions can run autonomous agent tasks in parallel.

Why is my browser automation element not found?▼

The element may be below the fold or not yet loaded. Run browser-use scroll down then browser-use state again, or use browser-use wait selector "h1" to wait for the element to appear before interacting.

What to do when a browser-use task gets stuck?▼

Check progress with browser-use task status <id>; if cost and duration stop increasing, the task is stuck. View the live URL with session get, then stop the task and start a new session instead of reusing the old one.