browse

Drive a persistent Playwright browser for automated web QA and evidence capture.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/Ulanxx/mzstack --skill browse-ulanxx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/Ulanxx/mzstack/tree/main/browse
Command: npx skills add https://github.com/Ulanxx/mzstack --skill browse-ulanxx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a persistent, scriptable headless browser for automated QA and AI-driven testing of web applications, enabling teams to validate deployments, reproduce bugs, and gather evidence without manual browsing.

Core Features & Use Cases

  • Navigate to URLs, interact with page elements, verify state, and diff before/after actions.
  • Take annotated screenshots, test responsive layouts, validate forms and uploads, handle dialogs, and assert element states.
  • Use in CI pipelines, bug reproduction workflows, and AI-driven QA scenarios where reproducible browser sessions are essential.

Quick Start

Install mzstack, then start a browse session and issue commands to navigate URLs, interact with elements, and capture evidence.

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 QA testing for web deployments?

To automate headless browser QA testing, this Skill provides a persistent, scriptable browser integrated with Playwright to deterministically run actions, verify state, and capture evidence across deployments without manual browsing.

What is the best way to capture annotated screenshots during automated web testing?

The best way to capture annotated screenshots during automated web testing is using a scriptable headless browser to take screenshots, interact with page elements, and validate responsive layouts within a reproducible session.

Can I use Playwright to reproduce bugs and diff page states in CI pipelines?

Yes, you can use Playwright to reproduce bugs and diff page states in CI pipelines by issuing server-driven commands to navigate URLs, interact with elements, and verify state before and after actions.

Does this approach support validating forms, uploads, and dialogs in headless mode?

Yes, this headless browser approach supports validating forms and uploads, handling dialogs, asserting element states, and testing responsive layouts deterministically within automated workflows.

How do I start a session to interact with page elements using a command interface?

To start a session and interact with page elements, you install the required environment, launch a browse session, and issue lightweight server-driven commands to navigate URLs and capture evidence.