gstack

Coordinate persistent browser QA workflows with Playwright and Bun.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/FxHollow/100000mrr-landing --skill gstack-fxhollow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/FxHollow/100000mrr-landing/tree/main/.agents/skills/gstack
Command: npx skills add https://github.com/FxHollow/100000mrr-landing --skill gstack-fxhollow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, diff, and includes scripts (resource) components.

What problem does it solve?

gstack provides a fast, AI-assisted browser workflow for QA testing and product dogfooding, unifying an AI agent with a persistent browser to streamline testing workflows.

Core Features & Use Cases

  • Persistent headless Chromium daemon for sub-second interactions and stateful testing.
  • Snapshot-based element references and Playwright-backed interactions (goto, click, fill, text, etc.) with robust error handling.
  • Observability and logging of console, network, and dialogs for post-mortem debugging.
  • End-to-end QA workflow with tests, diffs, and annotated evidence for PRs and bug reports.
  • Use cases include QA automation, regression testing, design-review facilitation, and live-browser dogfooding.

Quick Start

Install Bun, install dependencies, and run the browse CLI to start the headless browser and begin QA sessions.

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 using Claude Code?

You can automate QA testing by bridging Claude Code prompts with a persistent headless Chromium daemon, enabling sub-second interactions, stateful navigation, and evidence capture across live sites.

Do I need Bun and Playwright to run AI-assisted browser workflows?

Yes, Bun and Playwright are required runtime dependencies to execute the localized command codebase, manage the persistent browser daemon, and perform snapshot-backed interactions.

How does snapshot-based element reference work for browser interactions?

Snapshot-based element references map Playwright-backed interactions like goto, click, and fill to specific page states, providing robust error handling and precise state verification during automated testing.

Can I capture console logs and network traffic for post-mortem debugging?

Yes, the workflow integrates observability features that log console messages, network requests, and dialog events, supplying complete records for post-mortem debugging and bug reports.

What's the best way to generate annotated evidence for PRs from regression testing?

Running end-to-end QA workflows captures tests, diffs, and annotated evidence directly from live browser sessions, streamlining regression testing, design review, and bug report generation.

Why does my browser automation test fail to maintain state between interactions?

Browser automation tests fail to maintain state when not using a persistent daemon; this Skill solves that by keeping a headless Chromium instance alive for continuous, stateful testing sessions.