Orchestra-Research/AI-Research-SKILLs

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 5 skills · 378 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 2 skills · 153 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 219 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 215 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 2 skills · 153 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 8 skills · 432 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 258 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 6 skills · 372 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 3 skills · 140 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 7 skills · 518 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 3 skills · 229 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 298 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 3 skills · 104 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 249 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 5 skills · 305 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 164 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 2 skills · 92 tokens together

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

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 10 skills · 633 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 6 skills · 444 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 4 skills · 260 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 2 skills · 93 tokens together

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.

Orchestra-Research/AI-Research-SKILLs

Plugin Claude Code

Bundles 3 skills · 288 tokens together

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…