meow:browse

Provides a persistent headless Chromium browser for QA testing and site dogfooding with navigation, interaction, state verification, visual diffing, and reporting across sessions.

14|2|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/ngocsangyem/MeowKit --skill meow-browse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meow:browse
Source: https://github.com/ngocsangyem/MeowKit/tree/main/.claude/skills/meow%3Abrowse
Command: npx skills add https://github.com/ngocsangyem/MeowKit --skill meow-browse

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Persistent headless Chromium browser for QA testing and site dogfooding. State persists between calls (cookies, tabs, login sessions). First call auto-starts (~3s), then ~100ms per command.

Core Features & Use Cases

  • Persistent state across commands to simulate real user sessions.
  • Auto-start on first use and fast ~100ms command execution.
  • Navigate and interact with pages (goto, click, fill, snapshot, diff).
  • Visual verification with annotated screenshots and responsive checks.
  • Reference QA patterns and command references for structured testing.

Quick Start

Install and initialize the browse skill, then start issuing $B commands to navigate pages, interact with elements, and capture evidence.

Frequently Asked Questions about meow:browse

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

FAQPage Schema
How do I run headless browser testing for QA without losing session state?

Headless browser testing for QA can persist session state like cookies and login sessions across calls using a dedicated headless Chromium instance. State persists between commands to simulate real user sessions for end-to-end validation.

Can I use headless screenshots and visual diffs for site dogfooding?

Headless screenshots and visual diffs for site dogfooding are supported through annotated screenshots and diff rendering. You can navigate pages, interact with elements, and capture visual evidence to verify deployments and reproduce bugs.

What is the best way to automate end-to-end validation of deployments with a headless browser?

Automating end-to-end validation of deployments with a headless browser is best handled through command-based navigation like goto, click, fill, and snapshot. The browser auto-starts on first use, then executes subsequent commands in around 100ms.

How do I perform responsive checks and verify page state in headless Chromium?

Responsive checks and page state verification in headless Chromium are performed through built-in snapshot and interaction commands. You can execute navigation, fill forms, capture annotated screenshots, and verify state across persistent sessions.

Do I need to install external dependencies to start a persistent headless QA browser?

You do not need to install external dependencies to start the persistent headless QA browser. It requires no dependencies, auto-starts on the first call in about three seconds, and provides reference patterns for structured testing.

Why does my headless browser testing session reset between commands?

Headless browser testing sessions reset between commands if you are not using a persistent state solution. This skill maintains cookies, tabs, and login sessions persistently across calls to prevent state loss during end-to-end validation.