Design

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

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Generate personalized news intelligence with verified sources (7-day freshness requirement)

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Mobile game development principles. Touch input, battery, performance, app stores.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

API security testing principles. OWASP API Top 10, authentication, authorization testing.

Web browser game development principles. Framework selection, WebGPU, optimization, PWA.

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination. Teaches thinking, not fixed patterns.

VR/AR development principles. Comfort, interaction, performance requirements.

Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets

Architectural reasoning framework: requirements analysis, trade-off evaluation, and ADR-based decision documentation. NOT a pattern catalog, but a thinking framework. Use when designing system architecture, choosing patterns, or making structural decisions.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

2D game development principles. Sprites, tilemaps, physics, camera.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Game design principles. GDD structure, balancing, player psychology, progression.

3D game development principles. Rendering, shaders, physics, cameras.