Development

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation

Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Performance profiling principles. Measurement, analysis, and optimization techniques.

Next.js App Router principles. Server Components, data fetching, routing patterns.

Native multi-agent orchestration using Claude Code's Agent Tool. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

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.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization