skills.rest
dominionism
dominionismCOMMUNITY
Explore all skills by this author โ†’
GitHub

browser-use

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

1|Updated Mar 13, 2026
Search Tags:#screenshots#cli#browser automation#web testing#web scraping#form filling#chromium
One-click install
npx skills add https://github.com/dominionism/Noesis --skill browser-use-dominionism
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/dominionism/Noesis/tree/main/assets/skills/browser-use
Command: npx skills add https://github.com/dominionism/Noesis --skill browser-use-dominionism

SYSTEM DOCUMENTATION & REQUIREMENTS

๐Ÿ’ก This Skill requires browser-use.

What problem does it solve? Manually testing web pages, filling forms, and scraping data from websites is repetitive and error-prone. This Skill gives an AI agent direct control of a persistent browser session so it can navigate sites, interact with page elements, capture screenshots, and extract information without writing custom automation scripts. ## Core Features & Use Cases - Persistent Browser Sessions: The browser stays open across commands, supporting multi-step workflows like login, navigation, form submission, and verification. - Multiple Browser Modes: Run headless Chromium, your real Chrome with existing logins, or a cloud-hosted remote browser with proxy and profile support. - Element-Level Interaction: Inspect pages with indexed element states, then click, type, select, hover, or execute JavaScript and persistent Python against the live page. - Cloud Subagents: Launch parallel remote agent tasks, monitor them with token-efficient status polling, and manage cloud sessions and profiles. - Use Case: Test a local dev server by tunneling it through Cloudflare, opening it in a cloud browser, filling the contact form, and capturing a full-page screenshot for verification. ## Quick Start Ask the agent to open a website with browser-use, list the clickable elements on the page, fill in a form, and take a screenshot to confirm the result.

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?โ–ผ

Install the browser-use CLI with uv or the install script, then run browser-use open to navigate, browser-use state to list indexed elements, and browser-use click or input to interact. The browser session persists across commands for multi-step workflows.

How do I fill out a web form with browser-use?โ–ผ

Open the page, run browser-use state to get element indices, then use browser-use input with each index and value, and browser-use click on the submit button. Verify the result with browser-use state or a screenshot.

Can browser-use use my logged-in Chrome sessions?โ–ผ

Yes, the --browser real mode launches your actual Chrome with existing cookies and logins. Use browser-use -b real profile list to pick a specific Chrome profile, since each profile has its own cookies and authenticated sessions.

Does browser-use require an API key?โ–ผ

Local Chromium and real browser modes work without a key. The remote cloud browser, AI agent tasks via browser-use run, and LLM-based extract command require BROWSER_USE_API_KEY set via flag, environment variable, or config file.

Why is my browser-use element not found?โ–ผ

The element may be below the fold or the page may not have finished loading. Run browser-use state to refresh the element list, scroll down and check again, or use browser-use wait with a selector to pause until the element appears.

How do I test a local dev server with a cloud browser?โ–ผ

Start your dev server, run browser-use tunnel with the port to get a public Cloudflare URL, then open that URL with browser-use --browser remote. The tunnel persists independently of browser sessions until stopped.

Related Skills

Explore More Software Engineering Skillsโ†’
vm0-aivm0-ai
1.1k

dev-server

Manage VM0 dev server lifecycle with start, stop, logs, auth, and tunnel operations.

Official
Advanced
semicolon-devteamsemicolon-devteam

iteration-tracker

Track test iterations and outcomes for GitHub issues via issue comments.

Official
Advanced
SeemSeamSeemSeam
17

browser-quality

Validate frontend quality with visual QA, responsive screenshots, accessibility, and performance metrics.

Community
Advanced
mercurjsmercurjs
1.7k

playwright-skill

Provides Playwright testing guidance for E2E, API, visual, accessibility, and CI/CD workflows.

Official
Advanced