browse

Drive a persistent headless browser to navigate URLs and verify page state.

Updated Sep 10, 2024
One-click install
npx skills add https://github.com/TioSavich/UMEDCTA --skill browse-tiosavich
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/TioSavich/UMEDCTA/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/TioSavich/UMEDCTA --skill browse-tiosavich

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser-based QA testing by driving a persistent headless browser to navigate URLs, interact with elements, verify page state, and capture annotated evidence.

Core Features & Use Cases

  • Persistent headless Chromium with deterministic commands for testing deployments.
  • Verify page state, diff before/after actions, take annotated screenshots, and test forms, uploads, and dialogs.
  • Use for feature validation, bug reproduction, and dogfooding user flows in CI or local development.

Quick Start

Launch a test by loading a URL and taking a screenshot to verify the UI.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate headless browser QA testing for feature validation?

Automate headless browser QA testing by driving a persistent Chromium instance to navigate URLs, interact with elements, verify page state, and capture annotated screenshots for feature validation.

Can I capture annotated screenshots during automated Playwright testing?

Yes, you can capture annotated screenshots during automated testing to serve as visual evidence, allowing you to verify UI state and diff before and after user interactions.

Does this headless browser tool support testing forms, uploads, and dialogs?

Yes, the headless browser tool supports end-to-end user-flow testing across forms, file uploads, dialogs, and responsive layouts using deterministic commands.

What is the best way to reproduce bugs using a headless browser?

The best way to reproduce bugs is by driving a persistent headless browser with deterministic commands to replicate exact user flows, safely navigate URLs, and report errors robustly.

How do I verify page state and diff before and after actions in automated testing?

Verify page state and diff before and after actions by executing strict commands in a persistent headless browser, which validates UI changes and captures annotated evidence of the results.

Are there limitations when using a headless browser for deployment dogfooding?

Limitations include relying on strict command handling and safe URL validation to keep AI agents informed, meaning unexpected navigation changes or complex non-deterministic UI behaviors may require robust error reporting to manage.