browse

Automate web application testing via a persistent headless Chromium browser.

3|14|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/cegit27/moodle-proctor --skill browse-cegit27
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/cegit27/moodle-proctor/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/cegit27/moodle-proctor --skill browse-cegit27

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Testing web applications manually is slow and error-prone, especially when you need to capture visual evidence, track down console errors, or verify that a specific user flow works across deployments. This skill eliminates the friction by providing a persistent headless browser that you can control with simple text commands, making it fast to reproduce bugs and verify fixes.

Core Features & Use Cases

  • Persistent Browser State: The browser stays alive between commands, preserving cookies, login sessions, and open tabs so you can test multi-step flows without re-authenticating every time.
  • Visual Debugging & Evidence: Take plain or annotated screenshots, capture console logs and network requests, and generate before/after snapshot diffs to document exactly what changed after an action.
  • Form & Interaction Testing: Automate clicks, form fills, dropdown selections, file uploads, and dialog handling to validate user flows end-to-end, including responsive layout checks across mobile, tablet, and desktop viewports.

Quick Start

Use the browse skill to navigate to your application's staging URL, take an annotated screenshot of the main dashboard, and verify that the primary action button is visible and enabled.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate web application testing with a persistent headless browser?

Browser automation for web application testing uses a persistent headless Chromium instance controlled via CLI commands, preserving cookies and login sessions between actions so multi-step flows can be tested without re-authenticating.

Can I capture console logs and take annotated screenshots during QA testing?

Yes, QA testing workflows support capturing console logs, network requests, and taking plain or annotated screenshots to provide visual debugging evidence and document application behavior.

Do I need Playwright to run headless Chromium for bug investigation?

Yes, Playwright is required as the underlying framework for browser automation, enabling headless Chromium control for bug investigation, form interaction, and responsive layout checks.

What's the best way to generate before/after snapshot diffs for feature validation?

Before/after snapshot diffs for feature validation are generated by capturing application states before and after an action, highlighting visual changes to document exactly what was modified.

Does headless browser automation support multi-tab isolation and responsive viewport checks?

Headless browser automation supports multi-tab isolation for parallel testing and allows responsive layout checks across mobile, tablet, and desktop viewports to verify UI adaptability.

How does CDP-based CSS inspection work during web debugging?

CDP-based CSS inspection enables live style modification and DOM inspection during web debugging, allowing real-time CSS tweaks within the headless Chromium environment to isolate styling issues.