skills.rest
matsumuratk
matsumuratkCOMMUNITY
Explore all skills by this author →
GitHub

browser-use

Automates browser navigation, interaction, and data extraction via a persistent CLI daemon.

1|Updated Jul 12, 2026
Search Tags:#screenshots#browser automation#web testing#web scraping#form filling#cdp#chromium
One-click install
npx skills add https://github.com/matsumuratk/elmo-aws --skill browser-use-matsumuratk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/matsumuratk/elmo-aws/tree/main/.claude/skills/browser-use
Command: npx skills add https://github.com/matsumuratk/elmo-aws --skill browser-use-matsumuratk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually testing websites, filling forms, and scraping page data is repetitive and slow. This Skill gives an AI agent direct control of a real browser through the browser-use CLI, so it can navigate pages, click elements, fill inputs, take screenshots, and extract content without writing custom automation scripts. ## Core Features & Use Cases - Persistent Browser Sessions: A background daemon keeps the browser open across commands with ~50ms latency, supporting headless, headed, Chrome profile, and CDP-connected modes. - Full Interaction & Extraction: Click, type, scroll, upload files, manage cookies, run JavaScript, and execute persistent Python snippets against the live page. - Cloud Browsers & Tunnels: Provision cloud browsers via the Browser Use API and expose local dev servers through Cloudflare tunnels. - Use Case: Ask the agent to log into a site using your Chrome profile, navigate to a dashboard, fill out a report form, and save a screenshot of the confirmation page. ## 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. A background daemon keeps the browser open between commands.

How do I automate a website that requires login?▼

Use Chrome profiles with browser-use --profile "Default" open <url> to reuse your existing logged-in sessions and cookies. Run browser-use profile list first to see available profiles, or connect to an already-running Chrome via --connect.

Can browser-use connect to an existing Chrome instance?▼

Yes, browser-use --connect auto-discovers a running Chrome with remote debugging enabled, probing ports 9222 and 9229. You can also pass an explicit endpoint with --cdp-url using an http:// or ws:// address.

How do I extract data from a web page with browser-use?▼

Run browser-use state to get element indices, then use browser-use get text <index>, get html, or get attributes to read content. You can also run browser-use eval with JavaScript or browser-use python for persistent scripted extraction.

Why does browser-use fail to find an element on the page?▼

The element may be off-screen or not yet loaded. Scroll with browser-use scroll down and re-run state, or wait explicitly with browser-use wait selector "css" or wait text before interacting.

Related Skills

Explore More Software Engineering Skills→
pixiesgeosunpixiesgeosun

opencli-operate

Automate web page interactions via command line with the OpenCLI Browser Bridge extension.

Community
Advanced
DyreanDyrean

agent-browser

Automate browser interactions for web testing and data extraction via Bash CLI.

Community
Advanced
AI-Foundry-CoreAI-Foundry-Core
4

e2e-testing-patterns

Automate end-to-end testing with Playwright and Cypress patterns.

Official
Advanced
LambdaTestLambdaTest
350

selenium-skill

Generate Selenium WebDriver automation scripts in Java, Python, JavaScript, C#, Ruby, or PHP.

Official
Advanced