{ "name": "ai-research-skills", "owner": { "name": "Orchestra Research", "email": "zechen@orchestra-research.com" }, "metadata": { "description": "Comprehensive library of 98 AI research engineering skills enabling autonomous AI research from hypothesis to experimental verification", "version": "1.2.0" }, "plugins": [ { "name": "model-architecture", "description": "LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.", "source": "./", "strict": false, "skills": [ "./01-model-architecture/litgpt", "./01-model-architecture/mamba", "./01-model-architecture/nanogpt", "./01-model-architecture/rwkv", "./01-model-architecture/torchtitan" ] }, { "name": "tokenization", "description": "Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.", "source": "./", "strict": false, "skills": [ "./02-tokenization/huggingface-tokenizers", "./02-tokenization/sentencepiece" ] }, { "name": "fine-tuning", "description": "LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.", "source": "./", "strict": false, "skills": [ "./03-fine-tuning/axolotl", "./03-fine-tuning/llama-factory", "./03-fine-tuning/peft", "./03-fine-tuning/unsloth" ] }, { "name": "mechanistic-interpretability", "description": "Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.", "source": "./", "strict": false, "skills": [ "./04-mechanistic-interpretability/nnsight", "./04-mechanistic-interpretability/pyvene", "./04-mechanistic-interpretability/saelens", "./04-mechanistic-interpretability/transformer-lens" ] }, { "name": "data-processing", "description": "Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.", "source": "./", "strict": false, "skills": [ "./05-data-processing/nemo-curator", "./05-data-processing/ray-data" ] }, { "name": "post-training", "description": "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.", "source": "./", "strict": false, "skills": [ "./06-post-training/grpo-rl-training", "./06-post-training/miles", "./06-post-training/openrlhf", "./06-post-training/simpo", "./06-post-training/slime", "./06-post-training/torchforge", "./06-post-training/trl-fine-tuning", "./06-post-training/verl" ] }, { "name": "safety-alignment", "description": "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.", "source": "./", "strict": false, "skills": [ "./07-safety-alignment/constitutional-ai", "./07-safety-alignment/llamaguard", "./07-safety-alignment/nemo-guardrails", "./07-safety-alignment/prompt-guard" ] }, { "name": "distributed-training", "description": "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.", "source": "./", "strict": false, "skills": [ "./08-distributed-training/accelerate", "./08-distributed-training/deepspeed", "./08-distributed-training/megatron-core", "./08-distributed-training/pytorch-fsdp2", "./08-distributed-training/pytorch-lightning", "./08-distributed-training/ray-train" ] }, { "name": "infrastructure", "description": "GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.", "source": "./", "strict": false, "skills": [ "./09-infrastructure/lambda-labs", "./09-infrastructure/modal", "./09-infrastructure/skypilot" ] }, { "name": "optimization", "description": "Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.", "source": "./", "strict": false, "skills": [ "./10-optimization/awq", "./10-optimization/bitsandbytes", "./10-optimization/flash-attention", "./10-optimization/gguf", "./10-optimization/gptq", "./10-optimization/hqq", "./10-optimization/ml-training-recipes" ] }, { "name": "evaluation", "description": "LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.", "source": "./", "strict": false, "skills": [ "./11-evaluation/bigcode-evaluation-harness", "./11-evaluation/lm-evaluation-harness", "./11-evaluation/nemo-evaluator" ] }, { "name": "inference-serving", "description": "Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.", "source": "./", "strict": false, "skills": [ "./12-inference-serving/llama-cpp", "./12-inference-serving/sglang", "./12-inference-serving/tensorrt-llm", "./12-inference-serving/vllm" ] }, { "name": "mlops", "description": "ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.", "source": "./", "strict": false, "skills": [ "./13-mlops/mlflow", "./13-mlops/tensorboard", "./13-mlops/weights-and-biases" ] }, { "name": "agents", "description": "LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.", "source": "./", "strict": false, "skills": [ "./14-agents/autogpt", "./14-agents/crewai", "./14-agents/langchain", "./14-agents/llamaindex" ] }, { "name": "rag", "description": "Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.", "source": "./", "strict": false, "skills": [ "./15-rag/chroma", "./15-rag/faiss", "./15-rag/pinecone", "./15-rag/qdrant", "./15-rag/sentence-transformers" ] }, { "name": "prompt-engineering", "description": "Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.", "source": "./", "strict": false, "skills": [ "./16-prompt-engineering/dspy", "./16-prompt-engineering/guidance", "./16-prompt-engineering/instructor", "./16-prompt-engineering/outlines" ] }, { "name": "observability", "description": "LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.", "source": "./", "strict": false, "skills": [ "./17-observability/langsmith", "./17-observability/phoenix" ] }, { "name": "multimodal", "description": "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.", "source": "./", "strict": false, "skills": [ "./18-multimodal/audiocraft", "./18-multimodal/blip-2", "./18-multimodal/clip", "./18-multimodal/cosmos-policy", "./18-multimodal/llava", "./18-multimodal/openpi", "./18-multimodal/openvla-oft", "./18-multimodal/segment-anything", "./18-multimodal/stable-diffusion", "./18-multimodal/whisper" ] }, { "name": "emerging-techniques", "description": "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.", "source": "./", "strict": false, "skills": [ "./19-emerging-techniques/knowledge-distillation", "./19-emerging-techniques/long-context", "./19-emerging-techniques/model-merging", "./19-emerging-techniques/model-pruning", "./19-emerging-techniques/moe-training", "./19-emerging-techniques/speculative-decoding" ] }, { "name": "autoresearch", "description": "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.", "source": "./", "strict": false, "skills": [ "./0-autoresearch-skill" ] }, { "name": "ml-paper-writing", "description": "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.", "source": "./", "strict": false, "skills": [ "./20-ml-paper-writing/ml-paper-writing", "./20-ml-paper-writing/academic-plotting", "./20-ml-paper-writing/systems-paper-writing", "./20-ml-paper-writing/presenting-conference-talks" ] }, { "name": "ideation", "description": "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.", "source": "./", "strict": false, "skills": [ "./21-research-ideation/brainstorming-research-ideas", "./21-research-ideation/creative-thinking-for-research" ] }, { "name": "agent-native-research-artifact", "description": "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.", "source": "./", "strict": false, "skills": [ "./22-agent-native-research-artifact/compiler", "./22-agent-native-research-artifact/research-manager", "./22-agent-native-research-artifact/rigor-reviewer" ] } ] }