gstack

Automate browser-based QA with a persistent Chromium daemon via CLI.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/ligianehua/Gstack --skill gstack-ligianehua
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/ligianehua/Gstack/tree/main
Command: npx skills add https://github.com/ligianehua/Gstack --skill gstack-ligianehua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, puppeteer-core, bun, and includes scripts (resource) components.

What problem does it solve?

gstack browse eliminates the friction of browser-based QA by providing a persistent headless Chromium daemon that Claude Code can drive via a lightweight CLI surface. This lets teams reproduce bugs, verify deployments, and collect visual evidence without manually managing browser instances.

Core Features & Use Cases

  • Persistent browser daemon for isolated QA sessions across workspaces.
  • Commands like goto, click, text, snapshot, diff, and screenshot to automate end-to-end flows.
  • Evidence collection with annotated screenshots and diffs for PRs and bug reports.
  • Use cases include regression testing, design validation, and live-site QA dogfooding.

Quick Start

Install gstack and run a browse command to start testing a site.

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 Claude Code?

Automate headless browser QA by running a persistent Chromium daemon via a CLI, letting Claude Code execute end-to-end test flows and collect visual evidence without manual browser management.

What is a persistent Chromium daemon for isolated QA sessions?

A persistent Chromium daemon maintains browser state, cookies, and tabs across parallel workspaces, enabling isolated QA sessions for regression testing and live-site dogfooding without restarting instances.

Can I use Playwright to capture screenshots and visual diffs for bug reports?

Yes, Playwright drives commands like screenshot and diff to capture annotated visual evidence of deployments, enabling automated collection of visual diffs for PRs and bug reports.

Does headless browser automation require Bun and local environment setup?

Yes, headless browser automation relies on Bun, Playwright, and puppeteer-core within a local environment to manage the persistent Chromium daemon, browser state, and parallel workspace isolation.

How do I reproduce bugs and verify deployments using end-to-end test flows?

Reproduce bugs and verify deployments by driving the headless browser with CLI commands like goto, click, and text to automate end-to-end test flows across live sites and extract data.

When should I not use a persistent browser daemon for testing?

Avoid a persistent browser daemon if your testing requires ephemeral browser instances per test run, as this daemon maintains state, cookies, and tabs persistently across isolated parallel workspaces.