testing

Orchestrate end-to-end UI tests for web apps with a Playwright-based subagent.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/YSheldon/Prompt-Log --skill testing-ysheldon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: testing
Source: https://github.com/YSheldon/Prompt-Log/tree/main/.local/skills/testing
Command: npx skills add https://github.com/YSheldon/Prompt-Log --skill testing-ysheldon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

End-to-end UI validation for web applications by automatically driving real browser sessions with a Playwright-based subagent, capturing regressions before release.

Core Features & Use Cases

  • End-to-end UI tests with a Playwright-based subagent that interacts with the app in a real browser.
  • Logs analysis for browser and backend issues, plus diagnostics and screenshots.
  • Support for Clerk and Replit authentication to test authenticated flows.
  • Returns structured feedback including test status, results, and observations.

Quick Start

Describe your test scenario in a testPlan and pass it to runTest to execute end-to-end UI tests automatically.

Frequently Asked Questions about testing

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

FAQPage Schema
How do I run end-to-end UI tests for a web app using Playwright?

To run end-to-end UI tests, describe your test scenario in a testPlan and pass it to the runTest function. This automatically orchestrates a Playwright-based subagent to execute browser interactions, analyze logs, and validate feature correctness.

Can I use this to test authenticated web app flows with Clerk or Replit?

Yes, you can test authenticated web app flows because this testing process supports Clerk and Replit authentication. It orchestrates real browser sessions through these providers to validate features behind login walls.

What kind of feedback and diagnostics do these end-to-end UI tests return?

End-to-end UI tests return structured feedback including test status, results, and observations. Diagnostics also feature browser and backend log analysis, plus screenshots, to help capture regressions before release.

How does automated UI validation capture regressions before a web app release?

Automated UI validation captures regressions by driving real browser sessions with a Playwright-based subagent. It executes your testPlan, analyzes browser and backend logs, and returns structured diagnostics to verify feature correctness.

Do I need to manually script browser interactions for my test scenarios?

No, you do not need to manually script browser interactions because the Playwright-based subagent orchestrates them automatically. You simply describe your test scenario in a testPlan and pass it to runTest for execution.