單元測試

Generates and updates the latest app changelog based on git history since the last version tag.

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

Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'.

Specialized testing for React applications using TanStack ecosystem (Query, Router, Table, Form) with Vite and Vitest. Use when testing React + TanStack apps, mocking server state, testing router, or validating query behavior. Triggers: 'TanStack testing', 'React Query testing', 'test TanStack', 'mock query', 'router test'.

Validate methodology effectiveness using historical data without live deployment. Use when rich historical data exists (100+ instances), methodology targets observable patterns (error prevention, test strategy, performance optimization), pattern matching is feasible with clear detection rules, and live deployment has high friction (CI/CD integration effort, user study time, deployment risk). Enables 40-60% time reduction vs prospective validation, 60-80% cost reduction. Confidence calculation model provides statistical rigor. Validated in error recovery (1,336 errors, 23.7% prevention, 0.79 confidence).

Comprehensive CI/CD pipeline methodology with quality gates, release automation, smoke testing, observability, and performance tracking. Use when setting up CI/CD from scratch, build time over 5 minutes, no automated quality gates, manual release process, lack of pipeline observability, or broken releases reaching production. Provides 5 quality gate categories (coverage threshold 75-80%, lint blocking, CHANGELOG validation, build verification, test pass rate), release automation with conventional commits and automatic CHANGELOG generation, 25 smoke tests across execution/consistency/structure categories, CI observability with metrics tracking and regression detection, performance optimization including native-only testing for Go cross-compilation. Validated in meta-cc with 91.7% pattern validation rate (11/12 patterns), 2.5-3.5x estimated speedup, GitHub Actions native with 70-80% transferability to GitLab CI and Jenkins.

Create and run unit tests following the project's architecture and guidelines (Robolectric, naming, location).

Python Test-Driven Development expertise with pytest, strict red-green-refactor methodology, FastAPI testing patterns, and Pydantic model testing. Use when implementing Python features with TDD, writing pytest tests, testing FastAPI endpoints, developing with test-first approach, or when user mentions 'Python TDD', 'pytest', 'FastAPI testing', 'red-green-refactor', 'Python unit tests', 'test-driven Python', or 'Python test coverage'.

Grey Haven's comprehensive testing strategy - Vitest unit/integration/e2e for TypeScript, pytest markers for Python, >80% coverage requirement, fixture patterns, and Doppler for test environments. Use when writing tests, setting up test infrastructure, running tests, debugging test failures, improving coverage, configuring CI/CD, or when user mentions 'test', 'testing', 'pytest', 'vitest', 'coverage', 'TDD', 'test-driven development', 'unit test', 'integration test', 'e2e', 'end-to-end', 'test fixtures', 'mocking', 'test setup', 'CI testing'.

Systematic testing methodology for Go projects using TDD, coverage-driven gap closure, fixture patterns, and CLI testing. Use when establishing test strategy from scratch, improving test coverage from 60-75% to 80%+, creating test infrastructure with mocks and fixtures, building CLI test suites, or systematizing ad-hoc testing. Provides 8 documented patterns (table-driven, golden file, fixture, mocking, CLI testing, integration, helper utilities, coverage-driven gap closure), 3 automation tools (coverage analyzer 186x speedup, test generator 200x speedup, methodology guide 7.5x speedup). Validated across 3 project archetypes with 3.1x average speedup, 5.8% adaptation effort, 89% transferability to Python/Rust/TypeScript.

Use when testing Rails applications - TDD, Minitest, fixtures, model testing, mocking, test helpers

Use when sending emails - ActionMailer with async delivery via SolidQueue, templates, previews, and testing

Creates comprehensive implementation plans with bite-sized tasks before touching code. USE WHEN user wants detailed implementation plan OR has spec/requirements for multi-step task OR needs to break down complex feature OR before starting significant coding work. Documents file paths, code examples, testing, and verification steps assuming engineer has minimal codebase context.

Analyze WebAssembly test (WAST) files to debug compilation issues and create regression tests. Use when the user asks to debug or analyze WAST test failures, investigate compilation bugs in wasmoon, or when encountering test failures in spec/*.wast files. Triggers include "analyze wast", "debug wast", "wast bug", or references to specific .wast test files.

Comprehensive Chrome DevTools automation for performance testing, Core Web Vitals measurement (INP, LCP, CLS), network monitoring, accessibility validation, responsive testing, and browser automation. Uses Chrome DevTools Protocol via MCP to provide professional-grade web application testing, debugging, and analysis capabilities including performance tracing, HAR export, device emulation, and multi-page workflows.

Emacs Lisp development with modern tooling and best practices. USE WHEN writing Emacs configuration, developing packages, testing, linting, publishing to MELPA/ELPA, or working with Emacs Lisp code.

Python development best practices and modern tooling with uv. USE WHEN writing Python code, managing dependencies, testing, type checking, or working with Python projects.

Disciplined TDD workflow enforcing red-green-refactor cycle and the "iron law" of no production code without failing tests first. USE WHEN user wants to write tests first OR implement new feature with TDD OR fix bugs with test coverage OR explicitly requests TDD approach. Enforces systematic test-first development with verification at each step.

Creates isolated git worktrees with smart directory selection and safety verification for parallel development. USE WHEN starting feature work that needs isolation from current workspace OR before executing implementation plans OR working on multiple branches simultaneously OR need clean test environment. Creates isolated workspaces sharing the same repository.

Multi-LLM orchestration implementing the 5-stage coding workflow: Example Analysis → Hypothesis → Implementation → Debug Loop → Recursive Improvement.Based on "Towards a Science of Scaling Agent Systems" (Kim et al., 2025): - Centralized Consult architecture (Claude orchestrates, others advise) - Measured coordination (avoid MAS overhead in tool-heavy stages) - Tests-first selection (Poetiq pattern, not voting)Use when: Debugging complex issues, analyzing unfamiliar code, refactoring, or any task that benefits from diverse LLM perspectives with verification.