Design

Guides performance analysis and optimization for any application. Use when diagnosing slowness, optimizing code, improving load times, or when asked about performance.

Designs comprehensive testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, or when asked about testing approaches.

Create comprehensive implementation plans with detailed file-level changes and test strategies

Guides Git workflows, branching strategies, commit conventions, and collaboration patterns. Use when working with Git, creating PRs, managing branches, or when asked about version control.

Instructs AI agents on documentation standards for design docs, folder READMEs, source code interfaces, and test cases

Use when designing or architecting Elixir/Phoenix applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models with Ash Framework, structuring multi-app projects with path-based dependencies, or preparing handoff documentation for Director/Implementor AI collaboration

2025 UI design trends and patterns including glassmorphism, bento grids, micro-animations, and modern aesthetics. Essential for creating visually stunning, premium web interfaces.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Core game development principles applicable to all platforms. Game loop, design patterns, optimization, and AI fundamentals.

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

Mobile UX patterns for touch gestures, haptic feedback, accessibility, and platform-native interactions. Essential for building truly mobile-friendly apps.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

React/Tailwind component construction patterns for building reusable UI components.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Tailwind CSS principles. Responsive design, dark mode, utility patterns.