skills.rest
george11642
george11642COMMUNITY
Explore all skills by this author →
GitHub

browser-agent

Automate Chrome browser interactions for UI testing and visual verification.

2|Updated Jan 30, 2026
Search Tags:#automation#devtools#chrome#web-testing#browser#screenshot#form-filling
One-click install
npx skills add https://github.com/george11642/george-plugins --skill browser-agent-george11642
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-agent
Source: https://github.com/george11642/george-plugins/tree/main/plugins/george-setup/skills/browser-agent
Command: npx skills add https://github.com/george11642/george-plugins --skill browser-agent-george11642

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates Chrome browser interactions to drive UI testing, form filling, and visual verification, reducing manual steps and errors during web automation.

Core Features & Use Cases

  • Navigate pages, click elements, type inputs, and capture screenshots across desktop and mobile contexts.
  • Perform DOM extraction and element inspection to validate UI and content integrity.
  • Support multi-tab workflows, OAuth/login flows, and dynamic form submission to verify end-to-end user journeys.

Quick Start

Run the browser-agent to automate a simple navigation and capture a screenshot of the homepage.

Frequently Asked Questions about browser-agent

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

FAQPage Schema
How do I automate Chrome UI tasks for web testing?▼

You can automate Chrome UI tasks by using the browser-agent to control the DevTools Protocol through the use_browser MCP tool. It enables you to navigate pages, click elements, type inputs, and capture screenshots to drive end-to-end UI workflows and visual verification.

Can I automate OAuth login flows and multi-tab workflows in Chrome?▼

Yes, browser automation supports multi-tab workflows, OAuth login flows, and dynamic form submission. It drives end-to-end user journeys by interacting with the browser via the DevTools Protocol to validate complex navigation sequences.

How do I capture screenshots across desktop and mobile contexts during browser automation?▼

Browser automation allows you to capture screenshots across desktop and mobile contexts by executing visual checks through the use_browser MCP tool. This visual verification helps validate UI integrity during end-to-end testing workflows.

Does browser automation work with the DevTools Protocol for DOM extraction?▼

Yes, browser automation works directly with the DevTools Protocol via the use_browser MCP tool to perform DOM extraction and element inspection. This allows you to validate UI and content integrity during automated web testing.

What is the best way to fill forms automatically in Chrome?▼

The best way to fill forms automatically in Chrome is using browser automation to drive dynamic form submission. It leverages the DevTools Protocol to type inputs, click elements, and verify end-to-end user journeys without manual steps.

Related Skills

Explore More Software Engineering Skills→
jmaglyjmagly
175

gate-evaluation

Validate phase-gate criteria and generate pass/fail gate reports.

Community
Advanced
ArkLabsHQArkLabsHQ
3

browser-testing

Automate browser interactions and capture screenshots with Playwright MCP.

Official
Intermediate
borealBytesborealBytes
7

browser-automation

Automate multi-step web flows and tab handling with the OpenClaw browser tool.

Community
Advanced
CleanExpoCleanExpo
1

playwright-browser

Automate headless browser tasks and end-to-end tests with Playwright.

Community
Advanced