browse

Automate headless Chromium browser interactions and capture annotated screenshots.

1|Updated May 5, 2026
One-click install
npx skills add https://github.com/yashs33244/my-mac-claude --skill browse-yashs33244
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/yashs33244/my-mac-claude/tree/main/skills/gstack/browse
Command: npx skills add https://github.com/yashs33244/my-mac-claude --skill browse-yashs33244

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork of whether a web page is broken by letting you load any URL, interact with UI elements, verify resulting state, and capture evidence quickly.

Core Features & Use Cases

  • Fast page QA and dogfooding: Navigate, click, fill, select, hover, and wait for UI changes in a persistent headless Chromium session.
  • Reliable interaction discovery: Use snapshot views with interactive element refs, including non-ARIA cursor-interactive dropdown and popover items.
  • Verification with diffs and screenshots: Produce unified diffs between snapshots and annotate screenshots to generate bug-quality evidence.
  • Use Case: Verify a deployment by reproducing a user flow on staging, confirming expected UI state, and capturing screenshots and diffs for a clear bug report.

Quick Start

Ask the Skill to open the target URL, run a snapshot for interactive elements, perform the required actions, then take an annotated screenshot showing the observed results.

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 testing for web UI flows?

Headless browser testing automates web UI verification by navigating URLs in a persistent Chromium session, interacting with elements, and capturing page state. It produces annotated screenshots and unified diffs as bug-quality evidence.

Can I capture visual regression diffs during UI automation?

Visual regression diffs are captured by comparing interactive snapshots before and after UI actions. The resulting unified diffs verify expected page state changes and generate clear evidence for bug reports.

How do I discover interactive elements for form filling in a headless session?

Interactive element discovery uses snapshot views with stable element refs, including non-ARIA cursor-interactive items like dropdowns and popovers. This ensures reliable form filling, clicking, and selecting during automated QA testing.

Does headless browser automation maintain session state across multiple page actions?

Headless browser automation maintains session state across multiple page actions within a persistent Chromium session. This allows you to reproduce real user flows like logging in, navigating, and submitting forms sequentially.

What is the best way to verify a staging deployment without manual UI checks?

Verifying a staging deployment is best done by reproducing a user flow headlessly, confirming expected UI state through interactive snapshots, and capturing annotated screenshots. This removes manual guesswork and provides deterministic verification of web page behaviors.