browse

Drive a headless browser to navigate, interact, and capture screenshots for QA testing.

1|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/alexandervashurin/semaphore --skill browse-alexandervashurin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/alexandervashurin/semaphore/tree/main/.claude/skills/browse
Command: npx skills add https://github.com/alexandervashurin/semaphore --skill browse-alexandervashurin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun, perl, and includes scripts (resource) components.

What problem does it solve?

Automates browser-based QA tasks by providing a persistent, headless browser that can navigate pages, interact with elements, capture evidence, and compare states across runs.

Core Features & Use Cases

  • Navigate to URLs, click, fill, and verify UI states.
  • Take screenshots, diff diffs, and capture logs (console, network, dialogs) for bug reports.
  • Use cases include regression testing, feature verification, and bug reproduction with visual evidence.

Quick Start

Point the browser at a URL and perform a simple test, such as capturing a screenshot.

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 to capture screenshots and logs?

Headless browser QA testing automates navigation, interaction, and visual capture across web pages, returning test artifacts like screenshots and logs for regression checks and feature verification.

How do I compare UI state across multiple test runs for regression checks?

Comparing UI state for regression checks requires a headless browser to snapshot page states across different runs and generate diffs, highlighting visual or structural changes between executions.

Do I need bun and perl installed to run automated browser testing scripts?

Yes, the automated browser testing scripts depend on bun and perl, requiring both runtime environments to be installed locally to execute the headless browser lifecycle and interaction commands.

Can I use Playwright to capture network and console logs for bug reports?

Playwright can capture network and console logs during headless browser sessions, intercepting dialog outputs and network traffic to provide concrete evidence for bug reproduction and release verification.

What is the best way to reproduce a UI bug with visual evidence in automated testing?

Reproducing a UI bug with visual evidence in automated testing requires a headless browser to navigate to the specific URL, trigger the interaction, and capture screenshots alongside console and network logs.