Content & Media

PC and console game development principles. Engine selection, platform features, optimization strategies.

Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

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.

MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.

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

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents. Use for creating new applications, scaffolding projects, or building features from scratch.

Vulnerability scanning principles. DAST, SAST, SCA selection and integration.

Build frameworks from scattered insights across all braindumps and notes

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

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.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

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.

Process file changes and update CLAUDE.md memory sections. Use when the memory-updater agent needs to analyze dirty files, update AUTO-MANAGED sections, verify content removal, or detect stale commands. Invoked after file edits to keep project memory in sync.

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.

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.