gstack-browse

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

Updated Jun 24, 2026
One-click install
npx skills add https://github.com/tayiorbeii/paperclip-factory-kit-hermes --skill gstack-browse-tayiorbeii
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gstack-browse
Source: https://github.com/tayiorbeii/paperclip-factory-kit-hermes/tree/main/skills/paperclip/gstack-browse
Command: npx skills add https://github.com/tayiorbeii/paperclip-factory-kit-hermes --skill gstack-browse-tayiorbeii

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun.

What problem does it solve? Manually verifying that a web page loads correctly, a form submits, or a deployment looks right is slow and error-prone. This Skill gives an AI agent a persistent headless Chromium browser so it can navigate URLs, interact with elements, capture screenshots, and assert page state as evidence for QA and dogfooding. ## Core Features & Use Cases - Interactive page control: Navigate URLs, fill forms, click elements, handle dialogs, upload files, and diff page snapshots before and after actions. - Visual evidence capture: Take plain or annotated screenshots, responsive layout captures across mobile/tablet/desktop, and retina-scale renders for bug reports. - State assertions and diagnostics: Check visibility, enabled/disabled state, console errors, and failed network requests, plus compare staging versus production environments. - Use Case: After deploying a login flow, ask the agent to open the site, fill in credentials, submit the form, diff the resulting page, and attach an annotated screenshot proving the dashboard rendered. ## Quick Start Ask the agent to open your staging site in the browser, test the signup flow, and take an annotated screenshot of the result.

Frequently Asked Questions about gstack-browse

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

FAQPage Schema
How do I test a website with a headless browser from the command line?▼

Run the browse binary with commands like goto, fill, click, and snapshot to navigate pages and interact with elements. State persists between calls, so cookies and login sessions carry across commands at roughly 100ms per command after startup.

How do I take an annotated screenshot of a web page for a bug report?▼

Run snapshot with the -i, -a, and -o flags to produce a screenshot with red overlay boxes labeling each interactive element. Combine it with the console and network commands to attach error logs as supporting evidence.

Can a headless browser handle CAPTCHAs or multi-factor login?▼

Headless automation cannot solve CAPTCHAs or MFA prompts directly. Use the handoff command to open a visible Chrome window at the current page, let the user complete the challenge, then resume with full browser state preserved.

Does headless browsing work on sites that block automation?▼

Yes, using the --headed flag for a visible Chromium window and --proxy for SOCKS5 or HTTP proxy routing. These modes mask the navigator.webdriver automation signal, and on Linux containers Xvfb is spawned automatically when no display exists.

How do I test responsive layouts across mobile and desktop viewports?▼

Use the responsive command to capture mobile, tablet, and desktop screenshots in one step, or set an exact size with the viewport command. Adding --scale 2 produces retina-resolution output at twice the pixel dimensions.