browse

Drive a real Chromium browser for end-to-end QA testing.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/tropeks/Vitali --skill browse-tropeks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/tropeks/Vitali/tree/main/.claude/skills/gstack-browse
Command: npx skills add https://github.com/tropeks/Vitali --skill browse-tropeks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA teams struggle with repetitive browser interactions during bug reproduction and deployment verification. gstack-browse provides a programmable, observable browser surface that can be driven by AI or scripts to reproduce user flows reliably.

Core Features & Use Cases

  • End-to-end browser automation in headless or headed modes for testing, dogfooding, and bug reproduction.
  • Rich command surface including navigation, content extraction, interaction, visuals, snapshots, and session handoff.
  • Works with AI workflows via CLI commands and plan-mode telemetry to capture evidence and improve QA cycles.

Quick Start

Launch the browser and start issuing a few commands to load pages, take screenshots, and compare diffs.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate headless browser QA testing for bug reproduction?

Automate headless browser QA testing by driving a real Chromium browser with a persistent context and a cohesive CLI command surface. You compose test flows using Read, Write, and Meta commands to interact with pages, capture visuals, and generate actionable outputs.

Can I take screenshots and capture page diffs during end-to-end testing?

Yes, you can take screenshots and capture page diffs during end-to-end testing. The tool supports visual captures and page diffs, allowing you to generate telemetry-friendly evidence for reproducible QA cycles.

Does this browser automation tool support SPA handling and form interactions?

Yes, the browser automation tool supports SPA handling and form interactions. It provides a rich command surface including content extraction and interaction commands to drive complex user flows within single-page applications.

What is the best way to run Playwright-style browser automation in an AI workflow?

Run browser automation in an AI workflow by using a cohesive CLI with Read, Write, and Meta commands to compose test flows. The tool features a plan mode that captures telemetry-friendly evidence for AI-assisted QA cycles.

Are there limitations when using a headless browser for deployment verification?

A limitation of using a headless browser for deployment verification is the lack of visual rendering on screen, though the tool mitigates this by supporting headed modes and visual captures for reproducible evidence.