browse

Automate headless Chromium interactions and capture screenshots for visual regression testing.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/BaGyun0107/harness-starterkit --skill browse-bagyun0107
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/BaGyun0107/harness-starterkit/tree/main/.agents/skills/gstack-browse
Command: npx skills add https://github.com/BaGyun0107/harness-starterkit --skill browse-bagyun0107

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides an automated, scriptable headless browser environment for testing website functionality, visual verification, and bug hunting, reducing manual testing effort.

Core Features & Use Cases

  • Navigate and Load Pages: Open URLs and load web content for validation.
  • Interact and Assert: Perform clicks, fill forms, and verify element visibility or states.
  • Visual Testing: Capture screenshots, compare layouts across devices, and generate annotated visuals.
  • Use Case: Automatically test that a new deployment loads correctly, with key elements visible and no console errors, then snapshot the results for bug reporting.

Quick Start

Command the browser to load your site, perform interactions like clicking buttons or filling forms, and take screenshots for verification.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate visual regression testing for web deployments?

Automate visual regression testing by loading web pages in a headless Chromium environment, simulating user interactions, and capturing screenshots to compare layouts across multiple devices. This generates visual evidence and verifies UI elements before deployment.

Can I use Puppeteer API to reproduce website bugs in a headless browser?

Yes, you can use the Puppeteer API within this headless Chromium environment to script user actions, verify element states, and capture console errors to reproduce website bugs. This enables automated bug hunting and site inspection.

Do I need Puppeteer API knowledge to perform automated QA testing here?

Yes, Puppeteer API knowledge is required to programmatically control the headless browser. You need this scripting capability to simulate user actions, fill forms, and verify website functionality for automated QA testing.

What is the best way to verify UI elements and capture annotated visuals automatically?

The best way to verify UI elements is by running automated scripts in a headless browser to perform clicks and form fills, then capturing annotated screenshots. This simulates real user behavior and generates visual evidence for validation.

Are there limitations when simulating user actions across multiple devices for web quality checks?

When simulating user actions across multiple devices, limitations include the need for explicit scripting for each scenario and reliance on the headless Chromium environment. Visual diffs and layout comparisons are constrained by the configured device profiles.