browse

Drive Playwright-based headless browser QA for navigation, interaction, and state verification.

Updated May 11, 2026
One-click install
npx skills add https://github.com/wodeh/gstack-kimi --skill browse-wodeh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/wodeh/gstack-kimi/tree/main/browse
Command: npx skills add https://github.com/wodeh/gstack-kimi --skill browse-wodeh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate browser QA and dogfooding tasks by driving a headless or headed Playwright instance to navigate pages, interact with elements, verify page state, diff outcomes, and capture evidence.

Core Features & Use Cases

  • Navigate and interact with pages in headless mode, including clicking, typing, and form submissions.
  • Diff before/after states, take annotated screenshots, test responsive layouts, and verify dialogs and uploads.
  • Use cases include validating deployments, exploring user flows, and producing evidence for bug reports.

Quick Start

Open a URL, run a simple interaction flow, and review the test 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 QA for web app deployments?

Automate headless browser QA by driving a Playwright-based browser to navigate pages, interact with elements, and verify page state. This skill operates within a project-wide automation pipeline to validate deployments and document issues deterministically.

Can I capture screenshots and diff page states during browser automation?

Yes, you can diff before/after states and take annotated screenshots during browser automation. The skill drives a Playwright instance to capture evidence, test responsive layouts, and verify dialogs for bug reports.

How do I test responsive layouts and user flows in a headless browser?

Test responsive layouts and user flows by running a headless Playwright instance to navigate pages, interact with elements like forms, and verify outcomes. It provides a safe command surface for exploring user interactions.

Does this browser testing skill require specific dependencies to run?

No external dependencies are required to run this browser testing skill. It handles navigation, element interaction, and state verification internally using a Playwright-based browser with frontmatter validation.

What is the best way to coordinate automated browser dogfooding tasks?

Coordinate automated browser dogfooding tasks by using a deterministic, safe command surface that drives a Playwright-based browser. It handles navigation, interactions, and state verification to explore user flows and validate deployments.