← all publishers

MatthewTaormina

@matthewtaormina source repo

12 published skills

  1. System Design · matthewtaormina bundle
    Authoritative guide on system design, modular architecture, deep modules, and managing software complexity based on John Ousterhout's "A Philosophy of Software Design". Use when designing architectures, writing or refactoring modules, conducting code reviews, evaluating abstractions and interfaces, strategic programming, or eliminating dependencies, obscurity, classitis, and shallow wrappers.
    0 installs
  2. Cctv AI Systems · matthewtaormina bundle
    Authoritative guide for architecting, building, and deploying 24/7 SmartHub CCTV and Edge AI surveillance systems. Use when implementing RTSP/WebRTC/ONVIF camera ingestion, direct-to-disk recording pipelines, cascaded computer vision (SIMD motion gating, MOG2, YOLO, ByteTrack), storage retention and ring buffers, or polyglot CCTV architecture (Go, Node.js, Rust, C++).
    0 installs
  3. Hardware Aware Compute · matthewtaormina bundle
    Authoritative guide for hardware-aware software efficiency, compute reduction, and polyglot runtime orchestration across x86-64, ARM, and GPU platforms. Use when resolving overloaded CPU/GPU compute bottlenecks, designing zero-copy IPC and shared-memory pipelines, configuring media/CCTV AI streaming workloads, selecting optimal runtimes (Go, Node.js, Rust, C++, Python), or tuning adaptive hardware profiles.
    0 installs
  4. AI Routers · matthewtaormina bundle
    Official guide for developing with multi-model AI gateways and routers, specifically OpenRouter (global auto-routing and multi-provider failover) and EuroRouter / EUrouter (sovereign EU data residency and GDPR compliance). Use when implementing multi-model fallbacks, dynamic routing, or EU-sovereign LLM infrastructure using OpenAI-compatible SDKs.
    0 installs
  5. Cohere Sdk · matthewtaormina bundle
    Official guide for developing with the Cohere SDK (cohere-ai on npm v8+ / CohereClientV2, and cohere on PyPI) and Cohere Chat, Embed, and Rerank APIs. Use when implementing Command A+, Command A, Command R7B, Command A Reasoning/Vision/Translate, Embed v4, Rerank v4, or migrating from the legacy v1 CohereClient.
    0 installs
  6. Openai Sdk · matthewtaormina bundle
    Official guide for developing with the OpenAI SDK (openai npm package v7+ in Node.js/TypeScript and openai Python package v1+) and OpenAI APIs. Use when implementing, upgrading, or debugging OpenAI API calls, Responses API, Chat Completions, reasoning models (o1, o3, o4-mini), structured outputs, function calling/tools, streaming, vision, audio, or embeddings.
    0 installs
  7. Mistral Sdk · matthewtaormina bundle
    Official guide for developing with Mistral AI using the official SDKs (@mistralai/mistralai on npm and mistralai on PyPI) or OpenAI-compatible clients. Use when implementing Mistral Large 3, Mistral Medium 3.5, Mistral Small 4, Ministral 3, Codestral, native multimodal vision, Mistral OCR, structured outputs, function calling, or embeddings.
    0 installs
  8. AI Providers · matthewtaormina bundle
    Knowledgebase of current AI API providers and models (chat/agent, image, video, music/speech), documentation links, pricing, privacy/retention, and routers/gateways. Use when selecting models or vendors, comparing OpenAI, Anthropic, Google, Mistral, DeepSeek, xAI/SpaceXAI, Groq, Together, Fireworks, Vertex, Bedrock, Azure, OpenRouter, EUrouter, LiteLLM, Portkey, Sora, Veo, FLUX, Lyria, Kling, Runway, or when the user asks which model to use for chat, agents, image, video, or music.
    0 installs
  9. Deepseek Sdk · matthewtaormina bundle
    Official guide for developing with the DeepSeek API using the OpenAI-compatible SDK (openai npm / openai PyPI) at https://api.deepseek.com. Use when implementing deepseek-flash (V4.1-Flash), thinking mode, reasoning_effort, vision, tool calls, FIM, or migrating off retired deepseek-chat / deepseek-reasoner aliases.
    0 installs
  10. Google Genai · matthewtaormina bundle
    Official guide for developing with the Google Gen AI SDK (@google/genai in Node.js/TypeScript and google-genai in Python) and Gemini APIs. Use when implementing, upgrading, or debugging Gemini API calls, content generation, streaming, structured outputs, chat sessions, function calling/tools, multimodal processing (image, video, audio, PDF), thinkingConfig, context caching, or migrating from legacy @google/generative-ai.
    0 installs
  11. Accessibility · matthewtaormina
    Authoritative guide and standards for AODA (Accessibility for Ontarians with Disabilities Act) and WCAG 2.1/2.2 Level AA compliance across all UI components, dialogs, forms, and desktop application windows. Use when creating or modifying UI templates, CSS, interactive controls, keyboard navigation, and screen reader announcements.
    0 installs
  12. Anthropic Sdk · matthewtaormina bundle
    Official guide for developing with the Anthropic SDK (@anthropic-ai/sdk on npm and anthropic on PyPI) and Claude Messages API. Use when implementing, upgrading, or debugging Anthropic API calls, Claude 3.7 Sonnet, Claude 3.5 Sonnet/Haiku, prompt caching, extended thinking, streaming, tool use/function calling, token counting, message batches, or multimodal processing.
    0 installs