單元測試

Writes minimal code to make tests pass during implement phase

Manually verify code changes work as expected. Use after implementing a feature or bug fix, after making visual/UI changes, after modifying API endpoints, or before considering work "done". All functional changes must be manually verified, even small changes. This is in addition to automated tests.

Implements product analytics with PostHog including event tracking, feature flags, and session replay. Use when adding analytics, A/B testing, or user behavior tracking to React and Next.js applications.

Help write and organize tests for Python projects. Use PROACTIVELY when new code is written. Keywords: test, testing, pytest, テスト

Autonomous agent creation skill that generates specialized agent definitions from templates. Use when you need to create new Claude Code agents for specific tasks like code review, deployment automation, testing, documentation, security analysis, or general-purpose research. This skill automates the creation of agent definition files (.md) with proper structure, workflow instructions, and tool access patterns following Miyabi framework standards.

Enterprise testing framework with pytest 8.4.x, Vitest 4.x, Playwright 1.48.x, Testing Library 15.x, httpx 0.28.x, k6 load testing, and accessibility testing

Generate Cypress E2E test files and configuration for web application testing. Triggers on "create cypress test", "generate cypress config", "e2e test for", "cypress setup".

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Docker ignore configuration template and validation logic for optimizing Docker build contexts. Includes 5 required standards (build artifacts, development files, CI/CD and testing, logs and temporary files, root-only placement). Use when creating or auditing .dockerignore files to reduce build context size, improve performance, and ensure security.

Next.js fullstack development guidelines for React 19 and Next.js 15+. Use when building Next.js applications with Feature-Sliced Design, TailwindCSS v4, ShadCN, Jotai, React Query, and Supabase integration. Covers file naming, component architecture, testing with Vitest/Playwright, UI/UX design patterns, and Toss frontend principles.

Orchestrates comprehensive audits across multiple specialized auditors for Claude Code customizations and provides guidance on naming, organization, best practices, and troubleshooting. Use when: (1) Auditing - wants complete evaluation, multi-faceted analysis, coordinated audit reports, thorough validation, or asks to audit multiple components; (2) Guidance - asks "what should I name...", "how should I organize...", "best practices for...", troubleshooting issues, understanding evaluation criteria, or needs pre-deployment validation. Automatically determines which auditors to invoke (agent-audit, skill-audit, hook-audit, command-audit, output-style-audit, evaluator, test-runner) based on target type and compiles unified reports with consolidated recommendations.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Guide through REFACTOR phase of TDD cycle - improving code while tests pass

Provides quick reference for all Sagebase CLI commands and Docker operations. Activates when user asks how to run application, test, format code, manage database, or execute any Sagebase operation. Includes just commands, unified CLI, testing, formatting, and database management.

Production-grade accessibility skill for WCAG 2.2 AA compliance. Covers auditing, remediation, component authoring, and validation workflows. Auto-invoked for UI implementation, a11y fixes, and accessibility testing.

This skill should be used when creating new test lanes for the XML test data generator. A test lane consists of an XSD schema file paired with a meta.yaml configuration file. This skill guides the process of creating both files with proper semantic type mappings, distribution settings, and field overrides. Use when users request new test lanes, want to generate test data configurations, or need help setting up XSD + meta.yaml pairs for the testgen CLI tool.

Creates CI/CD pipeline configurations for automated testing and deployment

Automated Google Tag Manager debugging with visual monitoring, screenshot annotation, and MCP integration. Use when testing GTM configurations, verifying tag firing, debugging dataLayer events, validating consent mode, checking tracking implementations, or automating GTM container builds with Stape/GTM MCP servers. Triggers on "debug GTM", "test GTM tags", "GTM preview", "verify tag firing", "check dataLayer", "monitor tags", "validate consent", "did my GTM fix work", "validate tracking", "annotate screenshot", "GTM QA", or when verifying configuration changes via browser automation.

Patterns for writing effective, maintainable tests

CI/CD pipeline failure resolution with autonomous iteration loops. Local validation → branch & PR creation → CI monitoring → iteration until green. Proven patterns for GitHub Actions, includes role-specific adaptations. Use when CI pipeline failures occur, GitHub Actions errors detected, autonomous error resolution needed, PR creation for fixes required. Triggers on ci pipeline failures, github actions errors, autonomous ci resolution, ci iteration, pr creation for errors, pipeline validation, test failures in ci, build failures in ci, continuous integration debugging.