Orchestra-Research/AI-Research-SKILLs
6,242 stars22 plugins
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Add marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →#PluginVersion
1
agentsLLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.
—2
autoresearchAutonomous 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.
—3
data-processingData curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.
—4
distributed-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.
—5
emerging-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.
—6
evaluationLLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.
—7
fine-tuningLLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.
—8
ideationResearch ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.
—9
inference-servingProduction LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.
—10
infrastructureGPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.
—11
mechanistic-interpretabilityNeural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.
—12
ml-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, and writing best practices.
—13
mlopsML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.
—14
model-architectureLLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.
—15
multimodalVision, 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.
—16
observabilityLLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.
—17
optimizationModel optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.
—18
post-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.
—19
prompt-engineeringStructured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.
—20
ragRetrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.
—21
safety-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.
—22
tokenizationText tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.
—Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →