browser-use

Automates browser tasks like clicking, inputting, and extracting data via a daemon.

Updated Jun 23, 2019
One-click install
npx skills add https://github.com/davafons/dotfiles --skill browser-use-davafons
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/davafons/dotfiles/tree/main/agents/.agents/skills/browser-use
Command: npx skills add https://github.com/davafons/dotfiles --skill browser-use-davafons

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction, eliminating repetitive manual steps.

Core Features & Use Cases

  • Persistent browser daemon that stays open across commands for fast, low-latency interactions.
  • Navigate pages, inspect elements, and perform actions like click, input, and screenshot.
  • Extract information from web pages and capture state to verify results across sessions.

Quick Start

Open a URL, run state to view elements, then interact with an element by its index.

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 across sessions?

Automate browser interactions across sessions by running a persistent browser daemon that stays open to process commands like open, state, click, input, and screenshot with low latency. This eliminates repetitive manual steps for web testing tasks.

Can I take screenshots and extract data during headless browser automation?

Yes, headless browser automation supports taking screenshots and extracting data. You can navigate pages, inspect elements, capture page state, and extract information by sending commands to the persistent browser daemon.

Do I need a running browser daemon to use browser automation for form filling?

Yes, browser automation for form filling requires a running browser daemon with CDP connections. You must open a URL, run state to view elements, then interact with elements by index or coordinates to input text across multiple profiles.

What's the best way to inspect elements and click by index in web testing?

The best way to inspect and click elements in web testing is to open a URL, run the state command to view available elements, then perform actions like click or input by referencing the specific element index or coordinates.

How does a persistent browser daemon handle multiple profiles for element interaction?

A persistent browser daemon handles multiple profiles by maintaining open CDP connections across commands. This allows you to navigate pages, interact with elements, input text, and capture state across different sessions without restarting the browser.