browse

Validate web pages and user flows in a live browser with screenshots.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/GenEducation/GenedUIProject --skill browse-geneducation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/GenEducation/GenedUIProject/tree/main/.gemini/skills/browse
Command: npx skills add https://github.com/GenEducation/GenedUIProject --skill browse-geneducation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, playwright-core, diff, bun:sqlite, and includes scripts (resource) components.

What problem does it solve?

Browse removes the manual grind of checking websites by hand. It lets you validate live pages, user flows, and browser behavior with fast, repeatable actions and clear evidence.

Core Features & Use Cases

  • Live navigation and interaction: Open URLs, click elements, fill forms, select options, type text, upload files, handle dialogs, and switch tabs.
  • Verification and debugging: Read page text, inspect HTML, check console and network activity, assert element state, and compare before-and-after changes.
  • Visual QA: Take screenshots, capture responsive layouts, crop to elements, and generate annotated snapshots for bug reports or deployment checks.
  • Practical use case: Use it to test a checkout flow, confirm a staging deploy, verify responsive behavior on mobile and desktop, or collect proof when a page breaks.

Quick Start

Use browse to open the target page, interact with the UI, and capture snapshots or screenshots to verify the flow.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate browser QA testing and capture screenshots of user flows?

Automate browser QA testing by driving headless navigation, DOM interaction, and state assertions to validate user flows, while capturing screenshots and annotated snapshots as visual evidence of page behavior.

Can I use Playwright to verify responsive layouts and handle forms during web debugging?

Playwright supports web debugging by handling form inputs, file uploads, and dialog management, while capturing responsive layouts across mobile and desktop viewports to verify UI behavior.

What is the best way to capture actionable evidence when reproducing bugs in a live browser?

The best way to capture actionable evidence for bug reproduction is executing live browser interactions, checking console and network activity, and generating visual diffs with privacy-safe command logging.

Does browser automation support deployment verification and network activity inspection?

Browser automation supports deployment verification by opening URLs, inspecting HTML, reading page text, and checking network activity to assert element state and confirm successful deployments.

How do I perform visual diffing to compare before-and-after changes on web pages?

Perform visual diffing by capturing before-and-after screenshots of web pages, cropping to specific elements, and comparing the snapshots to detect layout regressions and verify UI changes.

What are the limitations of using headless navigation for QA testing?

Headless navigation for QA testing requires browser dependencies like Playwright, executes without a visual interface, and relies on DOM interaction and state assertions rather than manual visual inspection.