skills.rest
t0lab
t0labOFFICIAL
Explore all skills by this author →
WebsiteGitHub

browser-use

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

2|Updated Apr 10, 2026
Search Tags:#screenshots#cdp#session-management#web-testing#browser-automation#form-filling#cloud-browsers
One-click install
npx skills add https://github.com/t0lab/harness-kit --skill browser-use-t0lab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/t0lab/harness-kit/tree/main/examples/basic-node/.agents/skills/browser-use
Command: npx skills add https://github.com/t0lab/harness-kit --skill browser-use-t0lab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates manual, error-prone web interactions by providing a CLI-driven, persistent browser automation interface that speeds up testing, form filling, screenshot capture, and data extraction across both local and cloud contexts.

Core Features & Use Cases

  • Fast, persistent sessions: A background daemon keeps browsers open across commands for low-latency interactions.
  • Element discovery and interaction: State inspection returns indexed clickable elements so agents can click, input, hover, and upload reliably.
  • Multiple modes and isolation: Support for headless/headed modes, connecting to the user's Chrome profile, cloud browsers, and isolated named sessions via --session.
  • Advanced control via CDP: A python CDP bridge exposes raw DevTools access for tab activation, network interception, emulation, and cookie management.
  • Tunneling and cloud APIs: Built-in tunnel tooling and cloud provisioning support scraping and exposing local dev servers securely.

Quick Start

Open a URL with the browser-use CLI, run state to discover interactive elements, use indexed interactions to complete tasks, 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 for web testing without losing the session state between commands?▼

Browser automation can maintain session state using a background daemon that keeps browsers open across CLI commands for low-latency interactions. This provides persistent, daemon-backed sessions so you can navigate websites and interact with page elements without restarting the browser context each time.

Can I run headless browser automation and connect to my existing Chrome profile for scraping?▼

Headless browser automation supports connecting to your existing Chrome profile for scraping tasks. The system allows running in both headed and headless modes, enabling you to leverage authenticated sessions and existing cookies for data extraction workflows.

How do I discover and interact with clickable elements on a web page during automated form filling?▼

Automated form filling relies on state inspection to return indexed clickable elements on the web page. Once elements are discovered, agents can reliably click, input text, hover, and upload files by referencing these indexed elements to complete complex form interactions.

Does browser automation work with cloud browsers and remote DevTools protocol access?▼

Browser automation supports cloud browsers and remote DevTools protocol access through built-in tunneling and cloud API provisioning. A Python CDP bridge exposes raw DevTools capabilities for tab activation, network interception, emulation, and cookie management across both local and cloud contexts.

What is the best way to manage multiple isolated browser sessions for parallel web testing?▼

Managing multiple isolated browser sessions is handled through named sessions using the --session flag. This provides session isolation, allowing you to run parallel web testing and scraping tasks concurrently without cross-interference between different browser automation contexts.

How do I capture screenshots and extract data from authenticated web pages using a CLI?▼

Screenshot capture and data extraction from authenticated web pages are executed via a CLI-driven interface. By opening a URL, inspecting the state for interactive elements, completing the authentication tasks, and issuing a screenshot command, you can reliably confirm and extract the resulting web data.

Related Skills

Explore More Software Engineering Skills→
crycriMcrycriM

browser-harness

Control Chrome browser automation through the Chrome DevTools Protocol using Python.

Community
Advanced
binggandatabinggandata
559

bggg-creator-image2ppt

Convert images, screenshots, HTML, or SVG files into editable PowerPoint presentations.

Community
Advanced
sourcegraphsourcegraph
16

web-browser

Automate Chromium-based browser navigation, element interaction, and data extraction via CDP.

Official
Advanced
brendadeeznuts1111brendadeeznuts1111

cloudflare-browser-rendering

Automate headless browser tasks with Puppeteer and Playwright on Cloudflare Workers.

Community
Advanced