單元測試

Automated test case generation specialist that creates comprehensive unit tests, integration tests, and test scenarios from code, requirements, or specifications across multiple testing frameworks

Generate and manage database seed data for development and testing. Use when developers need realistic test data, database migrations with initial data, or automated seeding for local environments. Supports PostgreSQL, MySQL, SQLite with Faker-based data generation and relationship management.

Frontend-backend integration patterns, CORS configuration, API contract validation, and build hygiene for full-stack TypeScript applications. Use when integrating separate services or debugging cross-origin issues.

Use this skill when performing QA reviews of the Planted website (Astro frontend at localhost:4321), Admin Dashboard V2 (localhost:5175), or production sites (planted.com, admin.planted.com). Orchestrates visual inspection, console/network error detection, accessibility auditing, Core Web Vitals measurement, and interactive testing using Chrome DevTools MCP.

QuantConnect walk-forward validation and Phase 5 robustness testing (project)

Expert knowledge in Flutter Riverpod state management (2025 best practices). Use when working with Riverpod, Flutter state management, AsyncNotifier, provider types, code generation with riverpod_generator, state synchronization, or when the user mentions data fetching, mutations, reactive state, performance optimization, or testing in Flutter apps. Covers AsyncNotifierProvider patterns, repository architecture, autoDispose, family providers, and common anti-patterns to avoid.

Overview of protected quality thresholds and quick reference for all quality tools. Use when you need to understand quality metrics, run comprehensive quality checks, or learn which specialized skill to use. For specific issues, use dedicated skills (deptrac-fixer for Deptrac, complexity-management for PHPInsights, testing-workflow for coverage).

Scaffold Next.js App Router routes for simple pages without forms or complex logic. Use when user needs "create a page", "add route", "add about/contact/terms page", "create API endpoint", "add layout", or mentions SSE/webhooks. Generates page, layout, loading, error, and not-found files with boilerplate. Best for static content, read-only pages, and API endpoints (REST, SSE, webhooks). Do NOT use for forms with validation (use worldcrafter-feature-builder), complete features with database (use worldcrafter-feature-builder), database-only changes (use worldcrafter-database-setup), or comprehensive testing (use worldcrafter-test-generator).

Run and verify frontend tests for the React/Vite application.

C17/C23 best practices with Unity test framework, cppcheck, and Make/CMake build systems.

Automatically applies when working with database migrations. Ensures proper Alembic patterns, upgrade/downgrade scripts, data migrations, rollback safety, and migration testing.

Multi-agent collaborative decision-making for complex problems. USE WHEN you need multiple specialist perspectives on high-stakes decisions (architecture, prioritization, security, compliance). Orchestrates conversation between custom agent rosters, synthesizes perspectives into actionable decisions. Finds 2-3x more issues than solo agent mode.

Design and implement REST API integrations with proper error handling, authentication, rate limiting, and testing. Use when building API clients, integrating third-party services, or when users mention API, REST, webhooks, HTTP requests, or service integration.

Handles emergency hotfix process for critical bugs in ash_cookie_consent library including branch creation, minimal fixes, testing, and rapid release. Use when user asks to "create hotfix", "emergency fix", "patch critical bug", or "hotfix for version".

Deploy build artifacts (e.g., NRO files) to a Nintendo Switch using just deploy. Use when deploying built homebrew to the console for testing.

Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.

使用 Minion 框架生成智能测试用例

Guide experienced developers through GREEN phase of TDD cycle - writing minimal implementation to pass failing tests

Multi-step analytical reasoning with hypothesis testing for complex problems

Generates sonar-project.properties for SonarQube code quality analysis and coverage reporting. Auto-detects test framework (Jest/Vitest) and configures coverage paths.