gstack

Drive a headless browser to run QA tests and capture screenshots.

5|1|Updated Feb 12, 2026

Search Tags:#automation #testing #qa #ai-agent #browser #state-persistence

Ready to run

npx skills add https://github.com/drt0927/tw-overlay --skill gstack-drt0927

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/drt0927/tw-overlay/tree/main/.gemini/skills/gstack
Command: npx skills add https://github.com/drt0927/tw-overlay --skill gstack-drt0927

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Headless browser control for QA and design verification enables teams to test pages, assert behavior, and capture evidence without manual clicks.

Core Features & Use Cases

Real-time QA interactions: navigate, click, fill forms, and extract content to verify user flows.
Diff-based validation: compare before/after states and produce annotated screenshots to prove changes.
Evidence capture & automation: generate structured outputs (screenshots, logs) for bug reports and design reviews.

Quick Start

Run the gstack browse skill to start a headless browser session for testing.

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?▼

Automate QA testing by launching a headless browser session to navigate pages, fill forms, click elements, and extract content for verification. It handles real-time interactions and captures structured outputs like screenshots and logs as evidence for bug reports.

Can I use browser automation to compare before and after page states?▼

Yes, you can compare before and after page states using diff-based validation. The browser captures annotated screenshots to prove visual changes, enabling teams to verify design updates and user flows without manual clicks.

What is the best way to capture evidence for bug reports during design verification?▼

The best way to capture evidence for bug reports is to drive a headless browser through user flows and generate structured outputs. It produces annotated screenshots and execution logs that document failures and prove design review issues.

Does headless browser testing support session persistence across multiple interactions?▼

Yes, headless browser testing supports session persistence across multiple interactions. It enforces safe defaults and maintains state, allowing continuous navigation, form filling, and extraction without losing context during extended QA workflows.

How do I handle error paths when automated browser tests fail?▼

Handle error paths when automated browser tests fail using the skill's clear error path for failures. It provides structured reporting and captures screenshot evidence, ensuring you can quickly identify and debug issues encountered during navigation or interaction.