graphql-design
GraphQL schema design, resolver patterns, subscriptions, DataLoader for N+1 prevention, and error handling
GraphQL schema design, resolver patterns, subscriptions, DataLoader for N+1 prevention, and error handling
Modern frontend patterns for React Server Components, performance optimization, and Core Web Vitals
Mobile development patterns for React Native and Flutter including navigation, state management, and responsive design
Next.js 14+ App Router patterns including RSC, ISR, middleware, parallel routes, and data fetching
React 19 patterns including Server Components, Actions, Suspense, hooks, and component composition
Advanced TypeScript patterns including generics, conditional types, mapped types, template literals, and type guards
Core storytelling rules for AI video scripts: concrete metaphors instead of abstract jargon, the mute test (story reads without audio), visual contrast and closure, physically visible causes of failure or success, visualizing the “eureka” beat, camera motion tied to physics, in-scene transitions instead of black cuts, character consistency and multi-speaker action/lip sync timelines, and three-act pacing with Mandarin VO speed (~4.5 chars/s) and breathing room for action and SFX.
Pythonic code with modern type hints, dataclasses, async patterns, packaging, and testing
End-to-end guidance for AppRun apps in TypeScript using MVU including component patterns, event handling, state management (including async generators), routing/navigation with params and guards, and testing with vitest. Use when designing or reviewing AppRun components, wiring routes, managing state flows, or writing AppRun tests.
Implement StreamHub real-time indicators with O(1) performance. Use for ChainHub or QuoteProvider implementations. Covers provider selection, RollbackState patterns, performance anti-patterns, and comprehensive testing with StreamHubTestBase.
Implement BufferList incremental indicators with efficient state management. Use for IIncrementFromChain or IIncrementFromQuote implementations. Covers interface selection, constructor patterns, and BufferListTestBase testing requirements.
Design and implement consistent, production-grade backend/backoffice interfaces using the @open-mercato/ui component library. Use this skill when building admin pages, CRUD interfaces, data tables, forms, detail pages, or any backoffice UI components. Ensures visual consistency and UX patterns across all application modules.
Scaffold a new module from scratch with all required files and conventions. Use when creating a new module, adding a new entity with CRUD, or bootstrapping module features (API routes, backend pages, DI, ACL, events, search). Triggers on "create module", "new module", "scaffold module", "add module", "bootstrap module", "generate module".
Implement a specification (or specific phases of a spec) using coordinated subagents. Handles multi-phase spec implementation with unit tests, integration tests, documentation, and code-review compliance. Use when the user says "implement spec", "implement the spec", "implement a dated spec file", "implement phases", "build from spec", or "code the spec". Tracks progress by updating the spec with implementation status.
Extend core modules using the Universal Module Extension System (UMES). Use when adding columns/fields/filters to existing tables/forms, enriching API responses, intercepting API routes, blocking/validating mutations, replacing UI components, injecting menu items, or reacting to domain events. Triggers on "extend", "add column to", "add field to", "inject into", "intercept", "enrich", "hook into", "customize", "override component", "add menu item", "react to event", "block mutation", "validate before save".
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Gauss Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.