gstack

Controls a persistent headless Chromium browser for QA testing, screenshots, and deployment verification.

Updated Sep 3, 2026
One-click install
npx skills add https://github.com/xzedm/clipplic-landing --skill gstack-xzedm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gstack
Source: https://github.com/xzedm/clipplic-landing/tree/main/.agents/skills/gstack
Command: npx skills add https://github.com/xzedm/clipplic-landing --skill gstack-xzedm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun.

What problem does it solve? Manually clicking through a site to verify a deployment or reproduce a bug is slow and hard to document. This Skill drives a persistent headless Chromium browser so an AI agent can navigate pages, fill forms, click elements, capture annotated screenshots, and collect bug evidence automatically. ## Core Features & Use Cases - Interactive QA flows: Navigate to any URL, snapshot interactive elements, fill forms, click buttons, and diff page state before and after each action. - Visual evidence capture: Take full-page, element-level, region-cropped, and annotated screenshots, plus responsive layout captures at mobile, tablet, and desktop viewports. - Deployment verification: Check page text, console errors, failed network requests, and element visibility to confirm a production deploy works. - Use Case: After shipping a login feature, ask the agent to open the staging site, fill in test credentials, submit the form, verify the dashboard appears, and save an annotated screenshot as bug or success evidence. ## Quick Start Ask the agent to open your staging site in the gstack browser, walk through the login flow with test credentials, and screenshot the result.

Frequently Asked Questions about gstack

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

FAQPage Schema
How do I test a login flow with a headless browser?▼

Navigate to the login page with the goto command, run snapshot -i to list interactive elements, fill the email and password fields using their element refs, click submit, then use snapshot -D to diff the resulting page state and confirm the dashboard appeared.

How do I take annotated screenshots of a web page for bug reports?▼

Run snapshot with the -i -a -o flags to produce an annotated PNG labeling every interactive element on the page. You can also capture specific elements, regions, or full viewports, then read the PNG so the screenshot is visible in the conversation.

Can I test responsive layouts at mobile and desktop sizes?▼

Yes. The responsive command captures screenshots at mobile, tablet, and desktop widths in one step. You can also set an exact viewport such as 375x812 for iPhone or 1440x900 for desktop before taking individual screenshots.

Does the headless browser keep cookies and login sessions between commands?▼

Yes. The browser persists between calls, so cookies, login sessions, and open tabs carry over across commands. It auto-starts on first use and shuts down after 30 minutes of idle time.

Why does the browse command say NEEDS_SETUP on first run?▼

The browser binary must be compiled once before use, which takes about ten seconds via the setup script. It requires bun; if bun is missing, the skill installs it with a checksum-verified install script before building.