skills.rest
water1207
water1207COMMUNITY
Explore all skills by this author →
GitHub

browser-use

Automates browser interactions for web testing, form filling, screenshots, CLI-based scripted automation and data extraction.

1|Updated Feb 20, 2026
Search Tags:#cli#web-testing#data-extraction#web-scraping#browser-automation#form-filling
One-click install
npx skills add https://github.com/water1207/claw-bazzar --skill browser-use-water1207
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/water1207/claw-bazzar/tree/main/.agents/skills/browser-use
Command: npx skills add https://github.com/water1207/claw-bazzar --skill browser-use-water1207

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates repetitive and error-prone browser tasks, enabling you to control web pages without manual clicks.

Core Features & Use Cases

  • Open URLs and maintain persistent browser sessions
  • Inspect page state, interact with elements via indices, fill forms, take screenshots, and extract data
  • Use cases include web UI testing, form automation, data scraping, and monitoring

Quick Start

Open a URL, inspect the page state to obtain element indices, perform interactions using those indices, and capture a screenshot to verify results.

Frequently Asked Questions about browser-use

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping and form filling without manual clicks?▼

You can automate web scraping and form filling by using a CLI to open URLs, inspect page states for element indices, and issue commands to click, input text, and extract data across persistent browser sessions.

What is browser automation for end-to-end web testing?▼

Browser automation for web testing uses a CLI to navigate websites, interact with elements via indices, fill forms, capture screenshots, and extract data to validate UI behavior without manual intervention.

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

You take screenshots and extract data by opening a URL in a persistent browser session, inspecting the page state to identify elements, and executing dedicated screenshot and data extraction commands.

Can I maintain persistent browser sessions for scripted automation?▼

Yes, you can maintain persistent browser sessions for scripted automation, allowing sequential commands to execute within the same browsing context to preserve states like logins and page variables.

Does this browser automation tool support multiple browser modes?▼

Yes, the browser automation CLI supports multiple browser modes, enabling you to configure the browsing environment for different web testing, form filling, or data scraping scenarios.

What are the limitations of using element indices for web page interactions?▼

Using element indices requires inspecting the page state before every interaction, meaning dynamically loaded content or DOM changes may shift indices and require re-inspection to ensure accurate clicks and inputs.

Related Skills

Explore More Software Engineering Skills→
levanminhduclevanminhduc

chrome-devtools

Automate browser tasks and debugging workflows with Puppeteer CLI scripts.

Community
Advanced
Pans0020Pans0020

markdown-exporter

Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.

Community
Advanced
AllBeingsFutureAllBeingsFuture
9

browser-get-content

Extract page or element text from a webpage using an optional CSS selector.

Community
Basic
leroylim20leroylim20

agent-browser

Automate web browsing, form filling, and data extraction via headless browser navigation.

Community
Intermediate