單元測試

Complete development setup: scaffolding, TypeScript, testing, CI/CD, Docker, deployment, and best practices

Run TUnit tests with Playwright. Use when user asks to run tests, execute tests, or check if tests pass.

Extract and capture screenshots of specific UI elements mentioned in QA test procedures. Use when creating visual references for test steps to show exactly what buttons, fields, and components look like.

Guide experienced developers on test structure, patterns, assertions, and test doubles for effective test-driven development

Apply ZyntroTest brand guidelines and design system to all UI components. Use this skill when building, modifying, or reviewing any HTML/CSS components, pages, or features for ZyntroTest.com to ensure brand consistency, proper styling, and adherence to the established design system. This skill should be proactively applied whenever creating or editing visual elements, forms, buttons, cards, layouts, or any user-facing components.

Create responsive, mobile-first layouts that adapt gracefully across all device sizes and screen resolutions. When creating or modifying UI layouts, breakpoints, media queries, or viewport-dependent styles. When working on files that implement responsive design for mobile, tablet, and desktop views. When building fluid layouts, setting breakpoints, or using responsive CSS utilities. When ensuring touch-friendly interfaces, optimizing for mobile performance, or testing across different screen sizes. When implementing responsive typography, images, or grid systems.

Systematic PRD-driven software development workflow for Claude Code. Use when the user wants to (1) Import/parse feature bundles into draft PRDs with dependency analysis, (2) Create comprehensive Product Requirements Documents from feature descriptions, (2b) Extend existing PRDs with new requirements (version increment), (3) Break down PRDs into structured task lists with dependencies and test plans, (4) Systematically execute task lists with quality gates and verification protocols, (5) Audit test coverage and correctness against specifications, (6) Generate comprehensive PRD status reports showing completion states and progress tracking, or build complete applications from requirements through to tested implementation following enterprise-grade practices.

Get the latest screenshot from ShareX and display it in the conversation

Define comprehensive testing strategies, write tests with proper naming conventions, organize tests by type, and implement mocking strategies. Use when creating tests, refactoring test suites, or improving test coverage.

Use Lockplane for safe database schema management - define schemas in .lp.sql files, validate, and apply with shadow DB testing

Generates initial view components with mandatory unit tests. Creates HomeView.vue, PageNotFoundView.vue, and their .spec.ts test files (4 files total).

Master metrics definition, KPI tracking, dashboarding, A/B testing, and data-driven decision making. Use data to guide product decisions.

Creates a battle-tested ChatGPT-style chatbot widget that solves real-world production issues. Features infinite re-render protection, text selection "Ask AI", RAG backend integration, streaming SSE, and comprehensive performance monitoring.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Workflows for the Loopwish web app (Next.js 14 App Router): run dev server, implement pages/components, and validate with lint/format/tests/build.

Help with Rails testing including unit tests, integration tests, fixtures, and debugging test failures. Use when working on tests or debugging test issues.

Modern Python development with uv, FastAPI, Pydantic, and clean architecture. Use for Python project setup, LLM app development, API design, testing strategy, and architecture decisions. Ideal for TypeScript developers transitioning to Python.

AI-powered unified development orchestrator combining debugging, refactoring, performance optimization, code review, testing integration, and profiling into comprehensive development workflows with Context7 integration, TRUST 5 validation, and enterprise-grade automation

Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.

Chaos engineering for Kubernetes with Chaos Mesh and LitmusChaos. Pod deletion, network chaos, resource chaos, blast radius control, and validation patterns for reliability testing.