ai-research-skills

Agent-Native Research Artifact (ARA) tooling: compile any research input (paper, repo, notes) into a structured artifact, record session provenance as a post-task epilogue, and run Seal Level 2 epistemic review. Use when ingesting research into a falsifiable, agent-traversable artifact, capturing how a research project actually evolved, or auditing an ARA for evidence-claim alignment.

98 skills

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

98 skills

Autonomous research orchestration using a two-loop architecture. Manages the full research lifecycle from literature survey to paper writing, routing to domain-specific skills for execution. Use when starting a research project, running autonomous experiments, or managing multi-hypothesis research.

98 skills

Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

98 skills

Multi-GPU and multi-node training including DeepSpeed, PyTorch FSDP, Accelerate, Megatron-Core, PyTorch Lightning, and Ray Train. Use when training large models across GPUs.

98 skills

Advanced ML techniques including MoE Training, Model Merging, Long Context, Speculative Decoding, Knowledge Distillation, and Model Pruning. Use when implementing cutting-edge optimization or architecture techniques.

98 skills

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

98 skills

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

98 skills

Research ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.

98 skills

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

98 skills

GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

98 skills

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

98 skills

ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

98 skills

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.

98 skills

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

98 skills

Vision, audio, and multimodal models including CLIP, Whisper, LLaVA, BLIP-2, Segment Anything, Stable Diffusion, AudioCraft, Cosmos Policy, OpenPI, and OpenVLA-OFT. Use when working with images, audio, multimodal tasks, or vision-language-action robot policies.

98 skills

LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.

98 skills

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

98 skills

RLHF and preference alignment including TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, and torchforge. Use when aligning models with human preferences, training reward models, or large-scale RL training.

98 skills

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

98 skills

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

98 skills

AI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

98 skills

Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.

98 skills