Research skills

This skill helps you choose web game frameworks, optimize WebGPU/WebGL usage, and apply browser-friendly performance and asset strategies.

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

This skill helps you design engaging games by applying core loop, GDD structure, player psychology, and balanced progression.

This skill guides reinforcement learning based training of large language models using verl across PPO, GRPO, and other RL algorithms.

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

This skill helps you perform vision-language tasks such as captioning, VQA, and multimodal chat using BLIP-2 with frozen encoders.

This skill helps you deploy and experiment with Mamba selective state-space models for efficient linear-time sequence processing on GPUs.

This skill automates end-to-end AI research projects by managing loops, literature search, experiments, and synthesis to guide direction and produce papers.

This skill helps you build complex AI systems with declarative LM programming, automatic prompt optimization and modular RAG pipelines for reliable outputs.

This skill helps researchers generate genuinely novel CS and AI ideas by applying cognitive science frameworks like combinatorial creativity and constraint

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 helps generate high-quality embeddings for semantic search and retrieval using sentence-transformers, enabling efficient RAG, clustering, and

This skill guides fine-tuning LLMs with TRL for instruction tuning, preference alignment, and reward-based optimization, aligning models to human feedback.

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

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

This skill helps you generate music or sounds from text descriptions using AudioCraft, enabling melody-conditioned and stereo audio output.

This skill fine-tunes and evaluates OpenVLA-OFT policies for robot action generation with LoRA and FiLM conditioning.

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 provides expert guidance for fine-tuning LLMs with Axolotl, including YAML configs, 100+ models, and multimodal support.

This skill helps you train and analyze Sparse Autoencoders with SAELens to extract interpretable, monosemantic features from neural activations.

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