Performance skills

This skill helps you apply VR/AR development principles to optimize comfort, performance, and interaction across platforms.

This skill helps you design immersive game audio systems and adaptive music workflows that enhance player immersion and feedback.

This skill helps you apply core 3D game development principles to rendering, shaders, physics, and cameras for faster, higher quality prototypes.

This skill helps you design and implement clear 2D game systems, including sprites, tilemaps, physics, and camera, for polished gameplay.

This skill helps you make Node.js architecture decisions by applying context-aware principles for framework choice, async patterns, security, and testing.

This skill helps you build high-performance, memory-safe Rust services and libraries using async patterns, advanced types, and production-ready tooling.

This skill helps you design and optimize multiplayer architecture, synchronization, and security by applying proven principles for latency, fairness, and

This skill teaches safe production deployment thinking, verification, rollback, and post-deploy checks to minimize risk.

This skill helps you implement foundational SEO practices covering E-E-A-T, Core Web Vitals, technical and content optimization for better visibility.

This skill helps you design mobile games that respect battery, touch input, performance, and store requirements to maximize reach.

This skill guides enterprise RL training with miles for large MoE models, enabling FP8/INT4, train-inference alignment, and speculative RL for throughput.

This skill enables scalable pretraining of large language models using PyTorch Torchtitan 4D parallelism across GPUs, delivering faster training with efficient

This skill provides expert guidance for fast fine-tuning with Unsloth, enabling 2-5x training speed and reduced memory usage.

This skill helps you integrate PyTorch FSDP2 into training scripts with correct initialization, sharding, mixed precision, and DTensor-based checkpointing.

This skill helps you compress large language models to 4-bit precision with minimal accuracy loss, enabling faster inference and smaller memory footprints.

This skill enables memory-efficient fine-tuning of large language models using LoRA, QLoRA, and adapters to save GPU memory.

This skill orchestrates distributed training with Ray Train to scale PyTorch, TF, and HuggingFace across clusters, boosting efficiency and fault tolerance.

This skill speeds high-performance RLHF training for large models with Ray and vLLM acceleration, simplifying distributed PPO GRPO DPO workflows

This skill enforces runtime safety for LLMs with configurable jailbreaking, toxicity, PII, and fact-checking rails to improve reliability.

This skill enables fast billion-scale vector similarity with FAISS, guiding deployment, index selection, and GPU-accelerated search for high-performance

This skill provides expert guidance for distributed training with DeepSpeed, covering ZeRO, pipeline parallelism, FP16/BF16/FP8, and optimization best