AI Research Engineering Skills Library

The most comprehensive open-source library of AI research engineering skills for AI agents

81 Skills Powering AI Research in 2026

| | | | |:---:|:---:|:---:| | Model Architecture (5) | Fine-Tuning (4) | Post-Training (8) | | Distributed Training (5) | Optimization (6) | Inference (4) | | Tokenization (2) | Data Processing (2) | Evaluation (3) | | Safety & Alignment (3) | Agents (4) | RAG (5) | | Multimodal (7) | Prompt Engineering (4) | MLOps (3) | | Observability (2) | Infrastructure (3) | Mech Interp (4) | | Emerging Techniques (6) | ML Paper Writing (1) | |

Table of Contents

• Our Mission
• Path Towards AI Research Agent
• Available AI Research Engineering Skills
• Demo
• Skill Structure
• Roadmap
• Repository Structure
• Use Cases

Our Mission

We provide the layer of Engineering Ability that enable your coding agent to write and conduct AI research experiments, including preparing datasets, executing training pipelines, deploying models, and building your AI agents.

Path Towards AI Research Agent

Modern AI research requires mastering dozens of specialized tools and frameworks. AI Researchers spend more time debugging infrastructure than testing hypotheses—slowing the pace of scientific discovery. We provide a comprehensive library of expert-level research engineering skills that enable AI agents to autonomously implement and execute different stages of AI research experiments—from data preparation and model training to evaluation and deployment.

• Specialized Expertise - Each skill provides deep, production-ready knowledge of a specific framework (Megatron-LM, vLLM, TRL, etc.)
• End-to-End Coverage - 81 skills spanning model architecture, tokenization, fine-tuning, mechanistic interpretability, data processing, post-training, distributed training, optimization, evaluation, inference, infrastructure, agents, RAG, multimodal, prompt engineering, MLOps, observability, emerging techniques, and ML paper writing
• Research-Grade Quality - Documentation sourced from official repos, real GitHub issues, and battle-tested production workflows

Available AI Research Engineering Skills

Quality over quantity: Each skill provides comprehensive, expert-level guidance with real code examples, troubleshooting guides, and production-ready workflows.

📦 Install from Claude Code Marketplace

Install skill categories directly using the Claude Code CLI:

# Add the marketplace
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs

# Install by category (20 categories available)
/plugin install fine-tuning@ai-research-skills        # Axolotl, LLaMA-Factory, PEFT, Unsloth
/plugin install post-training@ai-research-skills      # TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, torchforge
/plugin install inference-serving@ai-research-skills  # vLLM, TensorRT-LLM, llama.cpp, SGLang
/plugin install distributed-training@ai-research-skills
/plugin install optimization@ai-research-skills

All 20 Categories: | Category | Install Command | Skills Included | |----------|-----------------|-----------------| | Model Architecture | model-architecture@ai-research-skills | LitGPT, Mamba, NanoGPT, RWKV | | Tokenization | tokenization@ai-research-skills | HuggingFace Tokenizers, SentencePiece | | Fine-Tuning | fine-tuning@ai-research-skills | Axolotl, LLaMA-Factory, PEFT, Unsloth | | Mech Interp | mechanistic-interpretability@ai-research-skills | TransformerLens, SAELens, pyvene, nnsight | | Data Processing | data-processing@ai-research-skills | NeMo Curator, Ray Data | | Post-Training | post-training@ai-research-skills | TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, torchforge | | Safety | safety-alignment@ai-research-skills | Constitutional AI, LlamaGuard, NeMo Guardrails | | Distributed | distributed-training@ai-research-skills | DeepSpeed, FSDP, Accelerate, Megatron, Lightning, Ray Train | | Infrastructure | infrastructure@ai-research-skills | Modal, Lambda Labs, SkyPilot | | Optimization | optimization@ai-research-skills | Flash Attention, bitsandbytes, GPTQ, AWQ, HQQ, GGUF | | Evaluation | evaluation@ai-research-skills | lm-eval-harness, BigCode, NeMo Evaluator | | Inference | inference-serving@ai-research-skills | vLLM, TensorRT-LLM, llama.cpp, SGLang | | MLOps | mlops@ai-research-skills | W&B, MLflow, TensorBoard | | Agents | agents@ai-research-skills | LangChain, LlamaIndex, CrewAI, AutoGPT | | RAG | rag@ai-research-skills | Chroma, FAISS, Pinecone, Qdrant, Sentence Transformers | | Prompt Eng | prompt-engineering@ai-research-skills | DSPy, Instructor, Guidance, Outlines | | Observability | observability@ai-research-skills | LangSmith, Phoenix | | Multimodal | multimodal@ai-research-skills | CLIP, Whisper, LLaVA, BLIP-2, SAM, Stable Diffusion, AudioCraft | | Emerging | emerging-techniques@ai-research-skills | MoE, Model Merging, Long Context, Speculative Decoding, Distillation, Pruning | | ML Paper Writing | ml-paper-writing@ai-research-skills | ML Paper Writing (LaTeX templates, citation verification, writing guides) |

🏗️ Model Architecture (5 skills)

• LitGPT - Lightning AI's 20+ clean LLM implementations with production training recipes (462 lines + 4 refs)
• Mamba - State-space models with O(n) complexity, 5× faster than Transformers (253 lines + 3 refs)
• RWKV - RNN+Transformer hybrid, infinite context, Linux Foundation project (253 lines + 3 refs)
• NanoGPT - Educational GPT in ~300 lines by Karpathy (283 lines + 3 refs)

🔤 Tokenization (2 skills)

• HuggingFace Tokenizers - Rust-based, <20s/GB, BPE/WordPiece/Unigram algorithms (486 lines + 4 refs)
• SentencePiece - Language-independent, 50k sentences/sec, used by T5/ALBERT (228 lines + 2 refs)

🎯 Fine-Tuning (4 skills)

• Axolotl - YAML-based fine-tuning with 100+ models (156 lines + 4 refs)
• LLaMA-Factory - WebUI no-code fine-tuning (78 lines + 5 refs)
• Unsloth - 2x faster QLoRA fine-tuning (75 lines + 4 refs)
• PEFT - Parameter-efficient fine-tuning with LoRA, QLoRA, DoRA, 25+ methods (431 lines + 2 refs)

🔬 Mechanistic Interpretability (4 skills)

• TransformerLens - Neel Nanda's library for mech interp with HookPoints, activation caching (346 lines + 3 refs)
• SAELens - Sparse Autoencoder training and analysis for feature discovery (386 lines + 3 refs)
• pyvene - Stanford's causal intervention library with declarative configs (473 lines + 3 refs)
• nnsight - Remote interpretability via NDIF, run experiments on 70B+ models (436 lines + 3 refs)

📊 Data Processing (2 skills)

• Ray Data - Distributed ML data processing, streaming execution, GPU support (318 lines + 2 refs)
• NeMo Curator - GPU-accelerated data curation, 16× faster deduplication (375 lines + 2 refs)

🎓 Post-Training (8 skills)

• TRL Fine-Tuning - Transformer Reinforcement Learning (447 lines + 4 refs)
• GRPO-RL-Training (TRL) - Group Relative Policy Optimization with TRL (569 lines, gold standard)
• OpenRLHF - Full RLHF pipeline with Ray + vLLM (241 lines + 4 refs)
• SimPO - Simple Preference Optimization, no reference model needed (211 lines + 3 refs)
• verl - ByteDance's HybridFlow RL framework, FSDP/Megatron + vLLM/SGLang backends (389 lines + 2 refs)
• slime - THUDM's Megatron+SGLang framework powering GLM-4.x models (464 lines + 2 refs)
• miles - Enterprise fork of slime with FP8, INT4, speculative RL for MoE training (315 lines + 2 refs)
• torchforge - Meta's PyTorch-native RL with Monarch+TorchTitan+vLLM (380 lines + 2 refs)

🛡️ Safety & Alignment (3 skills)

• Constitutional AI - AI-driven self-improvement via principles (282 lines)
• LlamaGuard - Safety classifier for LLM inputs/outputs (329 lines)
• NeMo Guardrails - Programmable guardrails with Colang (289 lines)

⚡ Distributed Training (5 skills)

• Megatron-Core - NVIDIA's framework for training 2B-462B param models with 47% MFU on H100 (359 lines + 4 refs)
• **[