gstack

Automate persistent headless browser testing and QA for Claude Code agents using Bun and Playwright.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/Jaykaijack/openclaw-backup --skill gstack-jaykaijack
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/Jaykaijack/openclaw-backup/tree/main/skills/gstack
Command: npx skills add https://github.com/Jaykaijack/openclaw-backup --skill gstack-jaykaijack

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persistently run a headless browser to enable AI agents to test, dogfood, and debug web apps with reliable, verifiable evidence.

Core Features & Use Cases

  • Persistent browser daemon with session and cookie management for repeatable tests.
  • Accessibility-driven snapshot with element refs (@e, @c), diffing, and annotated screenshots for verification.
  • End-to-end QA workflows: navigation, reading, interacting, and validation across pages, forms, and dialogs.

Quick Start

To get started, run /browse to launch the headless browser and begin testing.

Frequently Asked Questions about gstack

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

FAQPage Schema
How do I automate persistent headless browser testing for AI agents?

Automate persistent headless browser testing by running a long-running browser daemon that preserves cookies, logs, and session state. This approach enables AI agents to execute fast, deterministic commands for repeatable UI interactions and regression verification.

Can I use Playwright with Bun to drive end-to-end QA workflows?

Yes, you can use Playwright with Bun to drive end-to-end QA workflows. This combination powers a persistent browser daemon that handles navigation, reading, interacting, and validation across pages, forms, and dialogs in production-like environments.

How do I verify UI interactions and extract data using a headless browser?

Verify UI interactions and extract data using accessibility-driven snapshots with element references, diffing, and annotated screenshots. This mechanism targets repeated interactions across pages and dialogs to provide reliable, verifiable evidence for debugging.

What's the best way to maintain session state and cookies during browser automation?

Maintain session state and cookies during browser automation by relying on a persistent headless browser daemon. It preserves logs and session data across commands, ensuring repeatable tests and fast deterministic interactions without resetting context.

How do I launch a headless browser to start testing web apps?

Launch the headless browser to start testing web apps by running the browse command. This initiates the persistent daemon, enabling you to begin navigating, reading, interacting with, and validating web pages and forms immediately.

Why does my browser automation lose session state between repeated UI tests?

Browser automation loses session state between repeated UI tests when it uses ephemeral browser instances instead of a persistent daemon. Running a long-running headless browser daemon preserves cookies, logs, and session state for continuous, deterministic testing.