skills.rest
KARENLHAO
KARENLHAOCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser testing, form filling, and data extraction using refs.

1|Updated Feb 2, 2026
Search Tags:#automation#screenshots#web-testing#browser#data-extraction#form-filling#element-refs
One-click install
npx skills add https://github.com/KARENLHAO/skills --skill agent-browser-karenlhao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/KARENLHAO/skills/tree/main/agent-browser
Command: npx skills add https://github.com/KARENLHAO/skills --skill agent-browser-karenlhao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browser automation streamlines repetitive web testing, form filling, and data extraction, reducing manual effort and human error.

Core Features & Use Cases

  • Navigate to URLs and snapshot interactive elements with refs
  • Interact using refs to simulate user actions (click, fill, type, hover)
  • Capture screenshots, read element text, and extract page data for validation
  • Support parallel sessions to test multiple sites simultaneously

Quick Start

Open a URL, snapshot interactive elements, and then interact using the captured refs to automate your web workflow.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser tasks for web testing and data extraction?▼

Browser automation is performed by navigating to URLs, snapshotting interactive elements with refs, and simulating user actions like clicks and form filling to extract page data and validate web apps.

What are refs in browser automation and how do they work?▼

Refs are semantic locators captured during a page snapshot to interact with web elements. You use refs to simulate user actions like clicking, typing, and hovering for stable browser automation.

Does browser automation work for filling out forms and capturing screenshots?▼

Yes, browser automation supports filling out forms by simulating typing and clicking, capturing screenshots of web pages, and reading element text to validate data across web applications.

Can I run parallel browser sessions to test multiple sites simultaneously?▼

Yes, this browser automation approach supports parallel sessions to test multiple sites simultaneously, streamlining repetitive web testing and data extraction across different web applications.

What do I need to handle errors and waits during web automation?▼

Stable web automation requires a scriptable browser driver that supports refs or semantic locators, waits, and error handling to navigate pages, click elements, and extract text reliably.

Related Skills

Explore More Software Engineering Skills→
jrollinjrollin
1

agent-browser

Automate browser interactions for UI testing and visual comparisons.

Community
Advanced
abhishekmmgnabhishekmmgn

scrape

Extract text, tables, and metadata from web pages via Bash.

Community
Advanced
matsuyoshi30matsuyoshi30

agent-browser

Automates browser interactions across multiple parallel sessions for form filling and testing.

Community
Intermediate
MaxStrootmannMaxStrootmann

agent-browser

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

Community
Advanced