browse

Automate end-to-end QA browser testing with a persistent Playwright headless browser.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/zz8011/harnesstest --skill browse-zz8011
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/zz8011/harnesstest/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/zz8011/harnesstest --skill browse-zz8011

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates end-to-end QA browser testing by providing a persistent headless browser controlled via simple commands.

Core Features & Use Cases

  • Persistent headless browser powered by Playwright for QA automation, with state preserved across commands.
  • Navigate, interact, verify page state, diff before/after actions, take annotated screenshots, test responsive layouts, handle forms and uploads, and manage dialogs.
  • Use cases include feature verification, bug reproduction, and evidence collection during deployments or product dogfooding.

Quick Start

Launch the skill and drive a test page by issuing browse commands such as goto, text, 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 end-to-end QA testing with a headless browser?

You can automate end-to-end QA testing by launching a persistent headless browser and issuing simple commands for navigation, interaction, and element state checks. State is preserved across commands to drive complex test scenarios.

Can I take annotated screenshots during web automation testing?

Yes, you can take annotated screenshots during web automation testing to capture visual evidence. This supports feature verification, bug reproduction, and evidence collection during deployments or product dogfooding.

Does this Playwright automation tool support responsive testing and form uploads?

This Playwright automation tool supports responsive layout testing, form uploads, and dialog management. It enables comprehensive interaction testing across different viewport sizes and complex form scenarios.

What is the best way to verify page state and diff before and after actions?

The best way to verify page state is by using built-in diffing capabilities to compare before and after actions. This accurately identifies DOM changes and validates element states during feature verification.

How do I validate URLs safely during automated browser testing?

You validate URLs safely during automated browser testing by issuing commands designed for safe URL validation. This ensures navigation targets are correct and prevents accessing invalid or insecure endpoints.

Why does the headless browser maintain state across multiple testing commands?

The headless browser maintains state across multiple testing commands to provide a persistent environment for complex workflows. This allows sequential interactions, form submissions, and verifications without reinitializing the browser session.