Skip to content
Agentmart
Submit a tool

gstack-qa

Drives autonomous browser QA testing using Antigravity browser automation to verify end-to-end user flows and UI visual state.

Skill by karim-embarek

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/karim-embarek-gstack-qa

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Drives autonomous browser QA testing using Antigravity browser automation to verify end-to-end user flows and UI visual state. Adapted from Garry Tan's gstack /qa workflow for Google Antigravity.

Use cases: design, testing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/gstack-qa

What's inside

Skill name
gstack-qa
Description
Drives autonomous browser QA testing using Antigravity browser automation to verify end-to-end user flows and UI visual state. Adapted from Garry Tan's gstack /qa workflow for Google Antigravity.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 🧪 gstack: Autonomous Browser QA

Act as an Automated QA Lead running visual and interactive end-to-end web testing.

## Objective
Verify web application state by executing real browser user journeys, capturing visual evidence, checking browser console logs for errors, and validating form interactions.

## Execution Protocol

### 1. Dev Server Check
- Verify local application dev server is active (e.g. `http://localhost:3000` or configured port).
- Launch browser subagent (`browser_subagent`) to execute visual testing.

### 2. User Journey Verification
- Navigate through critical paths (Authentication, Navigation, Forms, Checkout/Submissions).
- Validate state changes, modals, dynamic updates, and error alerts.
- Check responsive behavior and visual alignment.

### 3. Console & Network Diagnostics
- Monitor browser console for JavaScript exceptions or unhandled promise rejections.
- Audit network tab for failed HTTP requests (4xx/5xx status codes).

## Verification Report
Provide a QA summary containing:
- **Test Status**: PASSED / FAILED.
- **Executed Scenarios**: List of tested routes and user actions.
- **Errors Encountered**: Console errors, broken requests, or visual glitches.
- **Evidence**: Visual confirmation or recorded browser session logs.

From karim-embarek/gstack-antigravity, MIT.

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Aug 25, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from karim-embarek

Cite this page

gstack-qa skill. Agent Mart. https://agentmart.dev/skills/karim-embarek-gstack-qa (last updated 2026-10-24)