skills.rest
SeaLion-hub
SeaLion-hubCOMMUNITY
Explore all skills by this author →
GitHub

gstack

Run a persistent headless browser daemon for Claude Code tests.

Updated Feb 16, 2026
Search Tags:#qa#evidence#diff#playwright#browser#claude-code#snapshot
One-click install
npx skills add https://github.com/SeaLion-hub/DICEE --skill gstack-sealion-hub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/SeaLion-hub/DICEE/tree/main/.agents/skills/gstack
Command: npx skills add https://github.com/SeaLion-hub/DICEE --skill gstack-sealion-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gstack provides a fast, persistent headless browser daemon to empower Claude Code tests and dogfooding. It enables AI agents to navigate pages, interact with UI, extract content, take snapshots, and generate verifiable evidence without leaving the Claude Code environment.

Core Features & Use Cases

  • Persistent browsing sessions: keep cookies, tabs, and state across commands for reliable end-to-end testing.
  • Deterministic actions with snapshots: diff, annotate, and verify page changes after interactions.
  • QA/testing workflows: validate deployments, gather bug evidence, and demonstrate issues with reproducible artifacts.

Quick Start

Run the gstack CLI to start a browse daemon, connect Claude Code to a local headless browser, and execute a simple flow like navigating to a page, taking a snapshot, and extracting text.

Frequently Asked Questions about gstack

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

FAQPage Schema
How do I capture QA evidence and snapshot diffs using a headless browser in Claude Code?▼

You can capture QA evidence and snapshot diffs by running a persistent headless browser daemon that enables deterministic navigation, interaction, and content extraction across real web pages directly within Claude Code workflows.

Can I keep browser cookies and tabs persistent across multiple Playwright test commands?▼

Yes, persistent browsing sessions keep cookies, tabs, and state across commands for reliable end-to-end testing, supporting multi-workspace isolation with per-project state preservation.

Does gstack require Playwright to run deterministic browser interactions for AI agents?▼

Yes, the skill requires Playwright to power its fast, persistent headless browser daemon for deterministic navigation, interaction, and content extraction during AI agent testing and dogfooding.

What is the best way to validate deployments and gather bug evidence without leaving the Claude Code environment?▼

The best way to validate deployments and gather bug evidence is using a persistent headless browser daemon that generates verifiable artifacts and reproducible snapshots without leaving the Claude Code environment.

How do I verify page changes after UI interactions during end-to-end testing?▼

You verify page changes by taking deterministic snapshots after UI interactions, enabling you to diff, annotate, and verify page changes across real web pages for QA and debugging workflows.

Related Skills

Explore More Software Engineering Skills→
zhifengzhang-szzhifengzhang-sz

gstack

Run a persistent headless browser daemon for QA testing and evidence capture.

Community
Advanced
clawpod-appclawpod-app
46

bug-report

Generate structured bug reports with reproduction steps and severity assessments.

Community
Intermediate
krzemienskikrzemienski
2

ios-validation-runner

Automate end-to-end iOS validation journeys with video, logs, and artifacts.

Community
Advanced
betaTridentbetaTrident

browser-qa

Automate visual regression testing and UI interaction verification for web applications.

Community
Advanced