browse

Drive a headless browser to automate QA tasks and capture annotated screenshots.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/fray-cloud/coin --skill browse-fray-cloud
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/fray-cloud/coin/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/fray-cloud/coin --skill browse-fray-cloud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA teams waste time manually testing deployments and monitoring dynamic sites. browse provides a fast headless browser for QA testing and site dogfooding, letting you navigate any URL, interact with elements, verify page state, and capture evidence.

Core Features & Use Cases

  • Deterministic browser actions: navigate, click, fill, test dialogs, diff before/after, and annotate screenshots.
  • Visual diffs and responsive checks: verify layouts across breakpoints and compare page states.
  • Dogfooding and bug repro: reproduce user flows, collect reliable evidence, and speed up bug reports.

Quick Start

Load a URL with browse goto <url>, then inspect content, interact with elements, and capture evidence with further browse commands.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate QA testing with a headless browser?

You can automate QA testing with a headless browser by driving deterministic actions like navigating pages, clicking elements, filling forms, and capturing annotated screenshots as visual evidence.

How do I capture visual diffs for responsive UI checks?

Capture visual diffs for responsive checks by navigating to a URL with a headless browser, verifying layouts across breakpoints, and comparing page states to validate behavior.

Can I reproduce user flows and capture bug repro evidence automatically?

Yes, you can reproduce user flows and collect bug repro evidence automatically by navigating dynamic sites, testing dialogs, asserting page state, and generating annotated screenshots.

Does headless QA testing work for validating forms and dialogs?

Headless QA testing works for validating forms and dialogs by executing deterministic browser actions to fill inputs, interact with UI elements, and assert state across deployments.

What is the best way to navigate pages and verify UI behavior without a display?

The best way to verify UI behavior without a display is using a fast headless browser to run commands, inspect content, interact with elements, and capture test evidence.