One-click install
npx skills add https://github.com/TumeloRamaphosa/StudEx-Valley-OS --skill browse-tumeloramaphosa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/TumeloRamaphosa/StudEx-Valley-OS/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/TumeloRamaphosa/StudEx-Valley-OS --skill browse-tumeloramaphosa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes guesswork in web QA by letting you reproduce user interactions in a real headless Chromium session and capture proof of what happened.

Core Features & Use Cases

  • Fast page interaction and verification: Navigate to any URL, click, fill, type, and assert element states to validate a user flow end-to-end.
  • State and behavior diffs: Take a baseline snapshot, perform actions, then diff before/after to show exactly what changed.
  • Evidence for bugs and deploy checks: Produce annotated screenshots, plain screenshots, and responsive layout captures to attach to bug reports.

Quick Start

Use browse to open a page, find all interactive elements, and verify that submitting a form updates the expected section.

Frequently Asked Questions about browse

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

FAQPage Schema
What is headless browser QA automation used for?

You can automate form validation by navigating to a URL, discovering all interactive elements, filling fields, and asserting element states after submission. The session captures screenshots and state diffs to verify the expected section updates correctly.

How do I capture screenshot evidence for bug reports during web testing?

You capture screenshot evidence by running automated web flows in a headless Chromium session that produces plain screenshots, annotated captures, and responsive layout outputs. These visual artifacts document the exact page state and user interactions for bug reports.

Can I test responsive layouts and file uploads with headless Chromium automation?

Yes, headless Chromium automation supports responsive layout checks, file uploads, and dialog handling across modern web UIs. It navigates to URLs and interacts with elements to validate these user flows end-to-end while capturing state snapshots.

Does browser testing automation work with cursor-interactive and popover elements?

Browser testing automation supports interactive element discovery including cursor-interactive and popover cases. It requires a persistent Chromium session and deterministic command execution to reliably interact with these dynamic elements and verify page state.

What is the best way to diff page state before and after web interactions?

The best way to diff page state is to take a baseline snapshot in a headless Chromium session, perform actions like clicking or typing, then generate before/after diffs. This shows exactly what changed during QA automation.

Do I need a persistent Chromium session for deterministic command execution in QA automation?

Yes, a persistent Chromium session is required to ensure deterministic command execution during QA automation. This environment supports reliable element discovery, state verification, and evidence outputs like snapshots and annotated screenshots.