gstack

Automate QA testing of web apps with a headless browser and diff evidence.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mmunro3318/3d-render-pipeline --skill gstack-mmunro3318
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/mmunro3318/3d-render-pipeline/tree/main/.claude/skills/gstack
Command: npx skills add https://github.com/mmunro3318/3d-render-pipeline --skill gstack-mmunro3318

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

gstack accelerates QA and dogfooding by giving Claude Code a persistent headless browser and a structured workflow to test web apps with repeatable actions, evidence, and diffing.

Core Features & Use Cases

  • Persistent browser daemon with Playwright-backed interactions for repeatable QA tests.
  • Snapshot-based element refs, diffs, and annotated screenshots for evidence.
  • Per-repo isolation to keep test state separate across projects.
  • Built-in support for cookies, forms, dialogs, and uploads for end-to-end tests.
  • Cross-workspace testing and auto-diff reporting to spot regressions.

Quick Start

Run the browse command and issue /qa on a live site to start testing.

Frequently Asked Questions about gstack

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

FAQPage Schema
How do I automate QA testing with a headless browser in Claude Code?▼

Automate QA testing by running the browse command and issuing /qa on a live site. The Skill provides a persistent, Playwright-backed headless browser to navigate, interact, and verify web app state repeatable.

Can I capture screenshots and diffs during automated browser testing?▼

Yes, automated browser testing captures evidence through annotated screenshots and snapshot-based element diffs. This allows you to visually verify state and spot regressions across different test runs.

How does headless QA testing handle isolation across multiple project workspaces?▼

Headless QA testing enforces per-repo isolation to keep test state separate across projects. This ensures reproducible tests and prevents cross-workspace interference when dogfooding deployments.

Does this Playwright browser automation support forms, cookies, and uploads?▼

Yes, the Playwright browser automation supports built-in handling of cookies, forms, dialogs, and uploads. This enables comprehensive end-to-end testing of complex user workflows.

What is the best way to detect UI regressions during web app deployments?▼

Detect UI regressions by using auto-diff reporting and snapshot-based element comparisons. The persistent browser daemon runs repeatable actions to dogfood deployments and automatically spot visual or state regressions.