後端開發

Design database models with proper naming, data types, constraints, and relationships. Use this skill when creating or modifying ORM models, database schemas, or entity definitions. When working on files like models.py, models/, entities/, schemas/, or any file defining database tables and their relationships. When adding timestamps, foreign keys, indexes, or validation constraints. When defining model relationships (one-to-many, many-to-many) or cascade behaviors.

Master software architecture patterns for scalable, maintainable systems. From monoliths to microservices, from MVC to hexagonal - choose the right structure for every challenge.

REST/GraphQL/tRPC API pattern library with validation, error handling, and documentation. Use when creating backend APIs.

Expert in Lighthouse Journey Timeline backend architecture, service patterns, testing, and API development using Express.js, TypeScript, and Drizzle ORM. Use when implementing backend services, APIs, controllers, database queries, authentication, permissions, error handling, testing server code, or writing migrations.

Enforce honest, evidence-bound answers. Use when the user asks to be honest/truthful, expresses frustration or urgency, or when confidence is low and errors are costly.

LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, and multi-model orchestration.

Coordinates backend development tasks (APIs, services, databases). Use when implementing REST APIs, business logic, data models, or service integrations. Applies backend-standard.md for quality gates.

Nodemon JSON configuration templates and validation logic for development server hot-reload. Includes 5 required standards (watch patterns, exec command, ignore patterns, development settings, required dependencies). Use when creating or auditing nodemon.json files to enable automatic server restart on file changes.

Search the internet using Perplexity API. Use for current information, news, or web research. Keywords: search, web, internet, perplexity, news, research.

Master-level fullstack software engineering with deep backend expertise. Use when building production-grade APIs, database architectures, authentication systems, microservices, or any backend-heavy application. Triggers on: (1) API design and implementation, (2) Database schema design and optimization, (3) Authentication/authorization systems, (4) System architecture decisions, (5) Performance optimization, (6) Error handling and logging, (7) Testing strategies, (8) DevOps and deployment, (9) Security hardening.

Handle errors consistently across frontend and backend. Use when implementing try/catch patterns, error boundaries, API error responses, or error reporting.

Express.js server best practices including middleware, error handling, and security.

ALWAYS use this skill proactively for Consumer Affairs Django repositories (located in ../ca/ directory) when ANY of these occur - (1) After writing or modifying ANY Python code files in CA repos (2) After tests pass and before telling user work is complete (3) User mentions linting, formatting, ruff, code style, or code quality (4) After using the ca-django-tests skill successfully (5) Before preparing to commit code. This skill runs 'ca exec ruff format' and 'ca exec ruff check --fix' to ensure code quality. CRITICAL - Always run this automatically after code changes and before declaring work complete.

Use when creating REST API clients, SDK wrappers, or HTTP service integrations. Generates type-safe client code with retry logic, error handling, rate limiting, and comprehensive tests. Triggered by requests to integrate external APIs, build SDK clients, or create service wrappers.

Configure rich popup content with text, fields, media, charts, attachments, and related records. Use for customizing feature popups with dynamic content, expressions, and interactive elements.

Use when implementing a new data source adapter for metapyle, before writing any source code

Interact with Docker containers running on a TrueNAS server via SSH. Use this skill when working with containers on the remote TrueNAS server, including querying databases, inspecting logs, executing commands, or managing container state. Particularly useful for complex operations requiring nested SSH and docker exec commands with special escape sequences.

Execute AI-powered command-line tasks with memory, replay, and resume capabilities using memex-cli. Use when (1) Running AI backend tasks (codex, claude, gemini), (2) Replaying recorded events from JSONL files, (3) Resuming interrupted runs by run_id, (4) Executing prompts with streaming output in jsonl or text format.

Convert structured markdown hierarchies into professional SVG taxonomy diagrams with nested card support, trunk-and-branch arrow routing, and color-coded categories.

Anthropic Claude API development patterns, tool use, Agent SDK, prompt engineering, and best practices.