browse

Navigate and interact with web pages using a headless browser to verify UI state and behavior.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/chriswestt/claude-skills --skill browse-chriswestt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/chriswestt/claude-skills/tree/main/gstack/browse
Command: npx skills add https://github.com/chriswestt/claude-skills --skill browse-chriswestt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates end-to-end QA flows using a headless browser to navigate pages, interact with elements, and assert state.

Core Features & Use Cases

  • Navigate to URLs and interact with page elements in a deterministic, scriptable way.
  • Take screenshots, diff before/after states, and verify responsive layouts across breakpoints.
  • Dogfood features like form handling, dialogs, and dynamic content including portals and popovers.

Quick Start

Use the browse skill to run a simple QA flow against a URL, verifying key page state and capturing artifacts.

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 feature verification?

Automate headless browser QA testing by navigating to URLs, interacting with page elements, and asserting UI state to verify feature behavior. This approach supports bug reproduction, feature testing, and visual regression across responsive layouts.

Can I capture screenshots and diff visual regressions across responsive breakpoints?

Yes, you can capture screenshots and diff before and after visual states across responsive breakpoints. This visual regression capability helps verify layout consistency and detect UI changes across different device sizes.

What is the best way to reproduce UI bugs in dynamic content like dialogs and portals?

Reproduce UI bugs in dynamic content by orchestrating a headless browser to interact with dialogs, portals, and popovers. This deterministic, scriptable navigation allows you to trigger and verify complex dynamic UI states.

Does headless browser automation work for testing form handling and popovers?

Headless browser automation works for dogfooding features like form handling, popovers, and dialogs. It orchestrates end-to-end element actions to verify dynamic content interactions and capture testing artifacts.

How do I run an end-to-end QA flow against a specific URL?

Run an end-to-end QA flow against a URL by using a headless browser to navigate the page, perform element actions, verify key page state, and capture artifacts. This provides deterministic, scriptable test execution.