Manages local web server lifecycle and enables web page development with Playwright MCP. Use when developing HTML/CSS/JS, building web pages, viewing web pages, testing UI interactions, verifying renders, debugging frontend issues, or iterating on web design. Covers build, startup, shutdown, and browser-based testing workflows.
Complete Behavior-Driven Development workflow coordinating SCENARIO → STEP DEFINITIONS → IMPLEMENT → REFACTOR cycle with Given/When/Then scenarios. Use when writing BDD tests or implementing features from user stories.
Validates API contracts by discovering consumers and ensuring responses match their expectations. Detects breaking changes.
基于NFR性能要求，生成性能测试场景和关键性能指标（KPI）。L3级别专用，当性能需求明确后使用。
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
You are the quality assurance architect ensuring Leavn's critical paths are protected by tests.
Execute Baldrick iterations on existing specs. Use when: run baldrick, execute specs, implement features, start working. Triggers on: baldrick run, run specs, implement, execute features.
Creating Storybook documentation with proper stories, argTypes, model instances, and variations
Writes comprehensive test cases following testing best practices. Use when writing tests, creating unit tests, or asking about test coverage.
Compares code implementation against specifications and requirements. Verifies functional requirements, non-functional requirements, acceptance criteria, and technical specifications are met. Returns structured reports of specification gaps and misalignments.
Use when developing tests or refactoring test suites - run tests in watch mode with focused file patterns to get instant feedback on specific test files without running the entire suite
Evaluate browser screenshots and page state for errors. Use when verifying features work correctly, detecting error conditions, or validating UI state during browser testing.
API integration testing with Supertest and Vitest. Use when testing API endpoints.
Use when implementing features/bugfixes to enforce strict TDD discipline - enforces RED (write failing test), GREEN (minimal code), REFACTOR cycle with no exceptions. Prevents "test after" trap, catches rationalizations. Activates when user says "implement", "let's code", "write this feature", mentions "TDD", or during spec-driven execution phase.
Python 3.13+ 개발 전문가로서 FastAPI, Django, async 패턴, 데이터 과학, pytest를 사용한 테스팅, 그리고 현대적 Python 기능을 다룸. Python API, 웹 애플리케이션, 데이터 파이프라인 개발 또는 테스트 작성 시 사용.
Guide for writing Go tests following this project's patterns including httptest, test organization, and coverage requirements.
Level 1 patterns - test-watch, integration-test, complexity, loc, duplicates, slowtests
Strict TDD state machine with Result types. 7-state workflow (PLANNING, RED, GREEN, REFACTOR, VERIFY, BLOCKED, VIOLATION). Every message MUST announce state. Integrates with fn(args, deps), vitest-mock-extended, and typed error handling.
Use when designing or refactoring automated tests to make them high-signal, reliable, and maintainable across unit, integration, and end-to-end suites.
Use when the user asks to run performance tests, check for performance regressions, validate performance, or stress test event sourcing. Handles LOCAL mode (runs API locally) and REMOTE mode (targets deployed servidor API). Supports concurrent update tests, high-volume throughput tests, and combined stress tests. Delegates to the perf-test-runner sub-agent. Trigger phrases include "run perf test", "run remote perf test", "run concurrent perf tests", "run high-volume tests", "stress test event sourcing", "test concurrent updates", "validate throughput".
Cypress E2E testing standards including framework adaptations, test organization, and best practices
