skills.rest
onblueroses
onbluerosesCOMMUNITY
Explore all skills by this author →
GitHub

browser-use

Automate browser navigation, interaction, and screenshotting with Chrome.

3|Updated Mar 1, 2026
Search Tags:#data extraction#browser automation#web scraping#screenshot#browser interaction
One-click install
npx skills add https://github.com/onblueroses/strata --skill browser-use-onblueroses
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/onblueroses/strata/tree/main/skills/browser-use
Command: npx skills add https://github.com/onblueroses/strata --skill browser-use-onblueroses

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires browser-use, python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines browser automation, enabling users to navigate, interact, and capture screenshots with ease, saving time and reducing manual effort.

Core Features & Use Cases

  • Browser Navigation: Navigate to URLs, scroll, and go back in history.
  • Page State & Screenshots: Retrieve page elements, take screenshots, and capture page titles and HTML.
  • Interactions: Click, type, send keyboard keys, and select dropdown options.
  • Waiting: Wait for specific elements or text to appear before proceeding.
  • Tab Management: Switch between tabs and close them.
  • JavaScript & Data: Execute JavaScript and extract data using LLM.
  • Cookies: Manage cookies, including getting, setting, clearing, exporting, and importing.
  • Session Management: List and close active sessions.
  • Use Cases: Automate web scraping, data entry, and visual validation tasks.

Quick Start

Use the browser-use skill to navigate to 'https://example.com' and click on the fifth element.

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 interaction and web scraping with Python?▼

To automate browser interaction and web scraping with Python, you can use this Skill to navigate URLs, click elements, type text, and extract data via an LLM. It supports both headless and real Chrome modes for flexible execution.

Do I need Python and browser-use CLI installed to run web automation tasks?▼

Yes, you need Python and the browser-use CLI installed to run web automation tasks. These dependencies are required to execute the scripts that handle browser navigation, page state retrieval, and dynamic page interactions.

Can I take screenshots and extract HTML during web scraping?▼

Yes, you can take screenshots and extract HTML during web scraping. The Skill captures page titles, HTML content, and visual screenshots, while also allowing you to wait for specific elements or text to appear before capturing data.

How do I manage login sessions and cookies for browser automation?▼

To manage login sessions and cookies for browser automation, the Skill provides built-in functions to get, set, clear, export, and import cookies. This allows you to maintain authenticated states across different browser sessions.

What is the best way to execute JavaScript and handle dynamic page structures?▼

The best way to execute JavaScript and handle dynamic page structures is by using the Skill's built-in command support. It allows direct JavaScript execution and uses an LLM to extract structured data from dynamically loaded page content.

Can I manage multiple tabs while automating web navigation?▼

Yes, you can manage multiple tabs while automating web navigation. The Skill supports tab management operations including switching between open tabs and closing them, alongside executing keyboard inputs and selecting dropdown options.

Related Skills

Explore More Software Engineering Skills→
browser-usebrowser-use
615

browser-use-terminal

Automate browser tasks via Python scripts and direct CDP control of Chrome.

Official
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
luisgustavooliveiraluisgustavooliveira

scrape

Extract text and structured data from web pages using Python libraries.

Community
Intermediate
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate