gstack

Automate browser QA workflows with a persistent Chromium daemon via Playwright.

Updated Aug 23, 2026

Search Tags:#automation #qa #diff #playwright #browser #headless #screenshot

Ready to run

npx skills add https://github.com/caraseli02/MoldovaDirect --skill gstack-caraseli02

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/caraseli02/MoldovaDirect/tree/main/.claude/skills/gstack
Command: npx skills add https://github.com/caraseli02/MoldovaDirect --skill gstack-caraseli02

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fast headless browser for QA testing & site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

Core Features & Use Cases

Persistent headless browser for automated QA across web apps and internal tools.
Command surface includes goto, text, snapshot, click, fill, hover, type, perf, screenshot, diff, annotate, and more.
Stateful sessions across commands to enable repeatable tests and production dogfooding locally.

Quick Start

Launch a browse session and perform a simple test flow by navigating to a URL, taking a snapshot, and verifying content.

Frequently Asked Questions about gstack

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

FAQPage Schema

How do I automate headless browser QA testing for web apps?▼

Headless browser QA testing is automated using a persistent Chromium daemon running Playwright via Bun, enabling navigation, interaction, content verification, and visual evidence collection across web apps with roughly 100ms per command.

What's the best way to capture annotated screenshots during Playwright automation?▼

Capture annotated screenshots during Playwright automation using a stateful Chromium daemon that exposes screenshot, diff, and annotate commands, enabling visual evidence collection for bug filing and deployment verification.

Can I use headless browser automation to verify deployments and dogfood internal tools?▼

Headless browser automation supports deployment verification and internal tool dogfooding through repeatable navigation and interaction flows, targeting developers and QA engineers needing production dogfooding across web apps with stateful sessions.

How do I diff before and after states during headless browser testing?▼

Diff before and after states during headless browser testing by executing sequential snapshot and diff commands within a persistent Chromium session, verifying page state changes after interactions like clicks, form fills, and hovers.

Does headless QA testing work without restarting the browser for each command?▼

Headless QA testing works without restarting the browser by maintaining a persistent Chromium daemon that preserves state across commands, minimizing warm-up time and maximizing reliability for sequential interactions.

Why use a persistent Chromium daemon for browser automation instead of launching new instances?▼

A persistent Chromium daemon is used for browser automation to maintain state across commands and minimize warm-up time, achieving roughly 100ms per command unlike launching new browser instances for each test.