gstack

Automates QA testing with a persistent Chromium headless browser and workflow commands.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill gstack-jm199seo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/jm199seo/lostark-accessory-viewer/tree/main/.claude/skills/gstack
Command: npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill gstack-jm199seo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a fast, persistent headless browser along with a suite of AI-driven workflow skills to accelerate QA testing, browser-based reviews, and developer workflows. It enables developers to test pages, capture evidence, and reason about design and process within a single, repeatable toolchain.

Core Features & Use Cases

  • Persistent Chromium daemon with a CLI to drive navigation, content extraction, visual diffs, annotated screenshots, and cookie management.
  • Reusable snapshot system using accessibility refs to locate elements with stable selectors for interactions and validations.
  • E2E testing, QA workflows, ship/review/document-release pipelines, canary monitoring, and safety hooks to guard destructive actions.
  • Cross-workspace isolation, session telemetry, and a robust design-doc workflow that feeds downstream skills for planning and shipping.

Quick Start

Install Bun, build the skill, and run the browse CLI to start interacting with the headless browser.

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 with Playwright?

Automate headless browser QA testing by using a persistent Chromium daemon with Playwright APIs to script navigation, extract content, capture annotated screenshots, and manage cookies. This approach provides a long-lived browser environment for repeatable end-to-end test execution.

What is a persistent headless browser and when do I need it for E2E testing?

A persistent headless browser is a long-lived Chromium daemon that maintains state across multiple test runs. You need it for E2E testing when executing continuous QA workflows, canary monitoring, or production dogfooding that requires multi-workload isolation and session telemetry.

How do I capture visual diffs and evidence during browser automation?

Capture visual diffs and evidence during browser automation by utilizing workflow commands that drive the headless browser to navigate pages, take annotated screenshots, and extract content. A reusable snapshot system using accessibility refs locates elements with stable selectors for accurate validations.

Do I need Bun to run headless browser workflows?

Yes, you need Bun installed to build the skill and run the browse CLI that starts the persistent Chromium daemon. This lightweight stateful server manages the Playwright APIs, cross-workspace isolation, and safe command execution required for your workflows.

Can I use this headless browser for production dogfooding and canary monitoring?

Yes, you can use this headless browser for production dogfooding and canary monitoring. It supports scripted navigation, content extraction, and evidence capture across multiple workspaces, with safety hooks designed to guard against destructive actions during continuous monitoring sessions.

Why use a persistent Chromium daemon instead of standard Playwright test runners?

Use a persistent Chromium daemon instead of standard runners to achieve cross-workspace isolation, maintain session telemetry, and execute safe commands across multi-workload environments. The long-lived daemon state enables faster repetitive navigation and content extraction for continuous QA workflows.