skills.rest
serguei9090
serguei9090COMMUNITY
Explore all skills by this author →
GitHub

browser-use

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

Updated Mar 22, 2026
Search Tags:#screenshots#browser automation#web testing#web scraping#form filling#cdp#chrome
One-click install
npx skills add https://github.com/serguei9090/LogLensAi --skill browser-use-serguei9090
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/serguei9090/LogLensAi/tree/main/.agents/skills/browser-use
Command: npx skills add https://github.com/serguei9090/LogLensAi --skill browser-use-serguei9090

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manually testing web pages, filling forms, and scraping data from websites is repetitive and slow. This Skill gives an AI agent direct control of a real browser through a fast command-line interface, so web tasks can be automated end to end. ## Core Features & Use Cases - Browser Automation: Navigate pages, click elements, fill forms, scroll, and manage tabs using indexed elements returned by the state command. - Data Extraction: Capture screenshots, read page HTML and text, evaluate JavaScript, and manage cookies for authenticated sessions. - Flexible Browser Modes: Run headless Chromium, connect to the user's real Chrome with existing logins, use named profiles, or provision a cloud browser. - Use Case: Ask the agent to log into a web app with your Chrome profile, navigate to a dashboard, fill out a report form, and take a screenshot to confirm the submission. ## Quick Start Use the browser-use skill to open https://example.com, list the clickable elements, and take a screenshot of the homepage.

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?▼

Run browser-use open with a URL, then browser-use state to get indexed clickable elements. Use those indices with commands like click, input, and select to interact with the page, and screenshot or state to verify results.

How do I use my logged-in Chrome session for automation?▼

Run browser-use connect to attach to your running Chrome with remote debugging enabled, preserving cookies and logins. Alternatively, use browser-use --profile with a profile name to launch Chromium with your Chrome profile data.

Can I run multiple browser sessions at the same time?▼

Yes, pass --session NAME on every command to target an isolated browser instance with its own daemon and state. Use browser-use sessions to list active sessions and browser-use close --all to shut them down.

Why do browser-use commands fail or target the wrong browser?▼

Failures usually come from a broken session or a missing --session flag, which defaults to the default session. Run browser-use close to clear the broken session, then retry, and run browser-use doctor for diagnostics.

Does browser-use support cloud browsers and remote automation?▼

Yes, browser-use cloud connect provisions a cloud browser over CDP after logging in with an API key. The cloud v2 and v3 REST passthrough commands also allow creating tasks and custom browser configurations directly.

Related Skills

Explore More Software Engineering Skills→
llm011llm011
9

agent-browser

Automates browser interactions for command-line web workflows.

Official
Advanced
RoentekRoentek
4

playwright

Capture screenshots, scrape rendered text, extract links, and generate PDFs from URLs.

Official
Intermediate
mynthiomynthio

playwright-cli

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

Official
Advanced
milo0914milo0914

playwright-web-testing

Automate web browser interactions and end-to-end testing with Playwright.

Community
Advanced