Orchestra-Research/AI-Research-SKILLs

Plugin marketplace

Comprehensive library of 98 AI research engineering skills enabling autonomous AI research from hypothesis to experimental verification

GitHub stars: 14.4K
plugins: 23
last updated: Nov 11, 2026

View on GitHub

Add marketplace

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs

Run it inside Claude Code, then install plugins from it with /plugin.

Plugins

1agent-native-research-artifactAgent-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.

2agentsLLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

3autoresearchAutonomous 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.

4data-processingData curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

5distributed-trainingMulti-GPU and multi-node training including DeepSpeed, PyTorch FSDP, Accelerate, Megatron-Core, PyTorch Lightning, and Ray Train. Use when training large models across GPUs.

6emerging-techniquesAdvanced 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.

7evaluationLLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

8fine-tuningLLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

9ideationResearch ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.

10inference-servingProduction LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

11infrastructureGPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

12mechanistic-interpretabilityNeural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

13ml-paper-writingWrite 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.

14mlopsML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

15model-architectureLLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

16multimodalVision, 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.

17observabilityLLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.

18optimizationModel optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

19post-trainingRLHF 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.

20prompt-engineeringStructured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

21ragRetrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

22safety-alignmentAI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

23tokenizationText tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.

Details

Repository: github.com/Orchestra-Research/AI-Research-SKILLs
Categories: community
Listed since: Jan 30, 2026