browse

Drive a Playwright-backed headless browser to automate QA testing and bug reproduction.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/AndrewLi0420/BMW --skill browse-andrewli0420
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/AndrewLi0420/BMW/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/AndrewLi0420/BMW --skill browse-andrewli0420

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Browser-based QA tool helps teams automate repetitive website testing, capture evidence, and reproduce issues without manual, time-consuming clicks.

Core Features & Use Cases

  • Navigate any URL in a fast, headless browser and interact with elements to verify UI behavior.
  • Diff before/after actions, take annotated screenshots, and test responsive layouts, forms, and uploads.
  • Use case: as part of a deployment review, open the app URL, run a sequence of actions, and capture evidence for bug reports.

Quick Start

Open a URL and begin QA testing by issuing commands such as goto, snapshot, and screenshot.

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 testing for QA workflows?

Automate headless browser testing by driving a Playwright-backed browser context to navigate URLs, interact with elements, and verify UI behavior. This approach supports repeatable workflows for validating deployments and reproducing bugs without manual clicks.

Can I capture annotated screenshots during automated website testing?

Yes, you can capture annotated screenshots during automated website testing by issuing screenshot commands within the headless browser workflow. This allows you to generate visual evidence for bug reports and diff before/after actions.

Does this headless QA browser support testing responsive layouts and forms?

Yes, the headless QA browser supports testing responsive layouts, forms, dialogs, and uploads. It drives a browser context to interact with these page elements, allowing you to validate UI behavior across different deployment states.

Do I need Playwright to run automated browser interactions and snapshots?

Yes, you need a Playwright-backed browser context to run automated browser interactions and snapshots. The tool relies on this environment to expose a deterministic command surface for navigating pages and capturing element references.

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

The best way to reproduce bugs in a headless browser environment is to issue a deterministic sequence of navigation and interaction commands. This drives the browser to replicate user actions, take snapshots, and capture evidence for bug reports.

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

When using a headless browser for deployment validation, interactions are limited to the deterministic command surface provided. Testing focuses on navigating URLs, checking elements, and capturing visual diffs, requiring explicit commands for each step.