Patterns for creating design systems with personality and distinctive aesthetics. Covers aesthetic documentation, color token architecture, typography systems, layered surfaces, and motion. Use when building design systems that go beyond generic templates. Triggers on design system, design tokens, aesthetic, color palette, typography, CSS variables, tailwind config.

Build beautiful native iOS/Android apps with Expo Router. Covers route structure, native tabs, animations, blur effects, liquid glass, SF Symbols, and platform patterns.

WHAT: Production-ready Node.js backend patterns - Express/Fastify setup, layered architecture, middleware, error handling, validation, database integration, authentication, and caching. WHEN: User is building REST APIs, setting up Node.js servers, implementing authentication, integrating databases, adding validation/caching, or structuring backend applications. KEYWORDS: nodejs, node, express, fastify, typescript, api, rest, middleware, authentication, jwt, validation, zod, postgres, mongodb, redis, caching, rate limiting, error handling

> 文档更新于2018/12/29，点击查看[更新日志](#更新日志)。

Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.

Every Expert automatically has access to `@perstack/base` — a built-in skill that provides file operations, runtime control, and other essential tools.

Analyze projects and recommend observability integration. Use when adding observability to projects Claude Code works on.

[Alexa](https://developer.amazon.com/alexa) is Amazon's cloud-based voice service. Most people are familiar with the service through using an [Amazon Echo or Echo dot](https://developer.amazon.com/alexa/echo) but the service can also be integrated in to custom internet-connected devices like this talking robotic fish:

Build flexible, maintainable React components using compound components, context providers, and explicit variants. Avoid boolean prop proliferation.

Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.

Minimize total codebase size through ruthless simplification. Measure success by final code amount, not effort. Bias toward deletion.

When the user asks about startup metrics, SaaS metrics, unit economics, or business performance tracking. Triggers on: "startup metrics", "SaaS metrics", "CAC and LTV", "unit economics", "burn multiple", "rule of 40", "magic number", "marketplace metrics", "churn rate", "MRR", "ARR", "net revenue retention", "runway", or requests for metrics dashboards and investor reporting.

Rate limiting algorithms, implementation strategies, HTTP conventions, tiered limits, distributed patterns, and client-side handling. Use when protecting APIs from abuse, implementing usage tiers, or configuring gateway-level throttling.

Create persona documentation for a product or codebase. Use when asked to create persona docs, document target users, define user journeys, document onboarding flows, or when starting a new product and needing to define its audience. Persona docs should be the first documentation created for any product.

Build production-ready component libraries with Tailwind CSS using CVA, compound components, design tokens, and theming.

Guided skill creation with quality criteria

Searchable UI/UX design databases: 50+ styles, 97 palettes, 57 font pairings, 99 UX rules, 25 chart types. CLI generates design systems from natural language. Data-driven complement to ui-design.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

Write specification documents for features using specification-driven development practices, including requirements with user stories, architecture design documents with correctness properties, and implementation plans with task breakdowns. Use when planning a new feature, designing system architecture, creating implementation roadmaps, or documenting technical specifications.

Error handling patterns across languages and layers — operational vs programmer errors, retry strategies, circuit breakers, error boundaries, HTTP responses, graceful degradation, and structured logging. Use when designing error strategies, building resilient APIs, or reviewing error management.