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.
AI Research SKILLs is a library of 98 modular skill files, organized across 23 categories, that instruct AI coding agents how to carry out the full lifecycle of machine learning research autonomously. The skills cover topics such as fine-tuning with Axolotl and LLaMA-Factory, post-training with TRL and GRPO, distributed training with Megatron-LM, inference with vLLM, mechanistic interpretability, safety and alignment, and paper writing. An `autoresearch` orchestration skill ties everything together using a two-loop architecture that routes tasks to the appropriate domain skill, taking an agent from literature survey and ideation through experiment execution to manuscript drafting. Installation via `npx @orchestra-research/ai-research-skills` auto-detects Claude Code, Gemini CLI, Cursor, and other agents, then places skill files in `~/.orchestra/skills/` with symlinks per agent. The library targets ML researchers and AI engineers who want an agent to handle infrastructure and framework debugging so they can focus on hypothesis testing rather than tooling.
- ✓Open-source license (MIT)
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/Orchestra-Research/AI-Research-SKILLs ~/.claude/skills/ai-research-skills24 items in this repository
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Skills overview
# AI Research `Skills` Library > **The most comprehensive open-source skills library enabling AI agents to autonomously conduct AI research — from idea to paper** <p align="center"> <img src="docs/assets/promo.gif" alt="AI Research Skills Demo" width="700"> </p> <p align="center"> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> <a href="https://www.npmjs.com/package/@orchestra-research/ai-research-skills"><img src="https://img.shields.io/npm/v/@orchestra-research/ai-research-skills.svg" alt="npm version"></a> <a href="https://www.orchestra-research.com/perspectives/ai-research-skills"><img src="https://img.shields.io/badge/Blog-Read%20More-orange.svg" alt="Blog Post"></a> <a href="https://join.slack.com/t/orchestrarese-efu1990/shared_invite/zt-3iu6gr8io-zJvpkZTPToEviQ9KFZvNSg"><img src="https://img.shields.io/badge/Slack-Join%20Community-4A154B.svg?logo=slack" alt="Slack"></a> <a href="https://x.com/orch_research"><img src="https://img.shields.io/badge/Twitter-Follow-1DA1F2.svg?logo=x" alt="Twitter"></a> <a href="https://www.linkedin.com/company/orchestra-research/"><img src="https://img.shields.io/badge/LinkedIn-Follow-0A66C2.svg?logo=linkedin" alt="LinkedIn"></a> </p> <div align="center"> ### **98 Skills Powering AI Research in 2026** </div> <details> <summary><b>View All 23 Categories</b></summary> <div align="center"> | | | | |:---:|:---:|:---:| | **Autoresearch** (1) | **Ideation** (2) | **ML Paper Writing** (2) | | **Model Architecture** (5) | **Fine-Tuning** (4) | **Post-Training** (8) | | **Distributed Training** (6) | **Optimization** (6) | **Inference** (4) | | **Tokenization** (2) | **Data Processing** (2) | **Evaluation** (3) | | **Safety & Alignment** (4) | **Agents** (4) | **RAG** (5) | | **Multimodal** (7) | **Prompt Engineering** (4) | **MLOps** (3) | | **Observability** (2) | **Infrastructure** (3) | **Mech Interp** (4) | | **Emerging Techniques** (6) | **Agent-Native Research Artifact** (3) | | </div> </details> --- ## Table of Contents - [Our Mission](#our-mission) - [Path Towards AI Research Agent](#path-towards-ai-research-agent) - [Available AI Research Engineering Skills](#available-ai-research-engineering-skills) - [Demos](#demos) - [Skill Structure](#skill-structure) - [Roadmap](#roadmap) - [Repository Structure](#repository-structure) - [Use Cases](#use-cases) - [Contributors](#contributors) - [Citation](#citation) - [Community](#community) ## Our Mission We enable AI agents to **autonomously conduct AI research** — from literature survey and idea generation through experiment execution to paper writing. The library provides both the **research orchestration layer** (autoresearch, ideation, paper writing) and the **engineering skills** (training, evaluation, deployment) needed at each stage. <p align="center"> <img src="docs/skills.png" alt="AI Research Agent System" width="50%"> <br> <em>System diagram of an AI research agent</em> </p> ## 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 skills library that enables AI agents to autonomously conduct the full research lifecycle — from brainstorming ideas to writing the paper. - Autonomous Research - The **autoresearch** skill orchestrates the entire research workflow using a two-loop architecture, routing to domain skills as needed - Specialized Expertise - Each domain skill provides deep, production-ready knowledge of a specific framework (Megatron-LM, vLLM, TRL, etc.) - End-to-End Coverage - 98 skills spanning the full AI research lifecycle, from ideation and literature survey to experiments and 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. ### 📦 Quick Install (Recommended) **For humans** — interactive installer with one command: ```bash npx @orchestra-research/ai-research-skills ``` **For AI agents** — point your agent to the welcome doc and it handles the rest: ``` Read https://www.orchestra-research.com/ai-research-skills/welcome.md and follow the instructions to install and use AI Research Skills. ``` This installs all 98 skills, loads the **autoresearch** orchestration layer, and starts autonomous research. <details> <summary><b>What the installer does</b></summary> - **Auto-detects** your installed coding agents (Claude Code, Hermes Agent, OpenCode, Cursor, Gemini CLI, etc.) - **Installs** skills to `~/.orchestra/skills/` with symlinks to each agent (falls back to copy on Windows) - **Offers** everything, quickstart bundle, by category, or individual skills - **Updates** installed skills with latest versions - **Uninstalls** all or selected skills </details> <details> <summary><b>CLI Commands</b></summary> ```bash # Interactive installer (recommended) npx @orchestra-research/ai-research-skills # Direct commands npx @orchestra-research/ai-research-skills list # View installed skills npx @orchestra-research/ai-research-skills update # Update installed skills ``` </details> <details> <summary><b>Claude Code Marketplace (Alternative)</b></summary> Install skill categories directly using the **Claude Code CLI**: ```bash # Add the marketplace /plugin marketplace add orchestra-research/AI-research-SKILLs # Install by category (23 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 ``` </details> ### All 23 Categories (98 Skills) | Category | Skills | Included | |----------|--------|----------| | **Autoresearch** | **1** | **Autonomous research orchestration — central layer that manages the full lifecycle and routes to all other skills** | | Ideation | 2 | Research Brainstorming, Creative Thinking | | ML Paper Writing | 2 | ML Paper Writing (LaTeX templates, citation verification), Academic Plotting | | Model Architecture | 5 | LitGPT, Mamba, NanoGPT, RWKV, TorchTitan | | Tokenization | 2 | HuggingFace Tokenizers, SentencePiece | | Fine-Tuning | 4 | Axolotl, LLaMA-Factory, PEFT, Unsloth | | Mech Interp | 4 | TransformerLens, SAELens, pyvene, nnsight | | Data Processing | 2 | NeMo Curator, Ray Data | | Post-Training | 8 | TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, torchforge | | Safety | 4 | Constitutional AI, LlamaGuard, NeMo Guardrails, Prompt Guard | | Distributed | 6 | DeepSpeed, FSDP, Accelerate, Megatron-Core, Lightning, Ray Train | | Infrastructure | 3 | Modal, Lambda Labs, SkyPilot | | Optimization | 6 | Flash Attention, bitsandbytes, GPTQ, AWQ, HQQ, GGUF | | Evaluation | 3 | lm-eval-harness, BigCode, NeMo Evaluator | | Inference | 4 | vLLM, TensorRT-LLM, llama.cpp, SGLang | | MLOps | 3 | W&B, MLflow, TensorBoard | | Agents | 4 | LangChain, LlamaIndex, CrewAI, AutoGPT | | RAG | 5 | Chroma, FAISS, Pinecone, Qdrant, Sentence Transformers | | Prompt Eng | 4 | DSPy, Instructor, Guidance, Outlines | | Observability | 2 | LangSmith, Phoenix | | Multimodal | 7 | CLIP, Whisper, LLaVA, BLIP-2, SAM, Stable Diffusion, AudioCraft | | Emerging | 6 | MoE, Model Merging, Long Context, Speculative Decoding, Distillation, Pruning | | Agent-Native Research Artifact | 3 | ARA Compiler, Research Manager, Rigor Reviewer | <details> <summary><b>View All 98 Skills in Details</b></summary> ### 🔬 Autoresearch (1 skill) — Central Orchestration Layer - **[Autoresearch](0-autoresearch-skill/)** - Autonomous research orchestration using a two-loop architecture (inner optimization + outer synthesis). Manages the full lifecycle from literature survey to paper writing, routing to all domain-specific skills. Supports Claude Code /loop and OpenClaw heartbeat for continuous operation (390 lines + 3 refs) ### 🏗️ Model Architecture (5 skills) - **[LitGPT](01-model-architecture/litgpt/)** - Lightning AI's 20+ clean LLM implementations with production training recipes (462 lines + 4 refs) - **[Mamba](01-model-architecture/mamba/)** - State-space models with O(n) complexity, 5× faster than Transformers (253 lines + 3 refs) - **[RWKV](01-model-architecture/rwkv/)** - RNN+Transformer hybrid, infinite context, Linux Foundation project (253 lines + 3 refs) - **[NanoGPT](01-model-architecture/nanogpt/)** - Educational GPT in ~300 lines by Karpathy (283 lines + 3 refs) - **[TorchTitan](01-model-architecture/torchtitan/)** - PyTorch-native distributed training for Llama 3.1 with 4D parallelism ### 🔤 Tokenization (2 skills) - **[HuggingFace Tokenizers](02-tokenization/huggingface-tokenizers/)** - Rust-based, <20s/GB, BPE/WordPiece/Unigram algorithms (486 lines + 4 refs) - **[SentencePiece](02-tokenization/sentencepiece/)** - Language-independent, 50k sentences/sec, used by T5/ALBERT (228 lines + 2 refs) ### 🎯 Fine-Tuning (4 skills) - **[Axolotl](03-fine-tuning/axolotl/)** - YAML-based fine-tuning with 100+ models (156 lines + 4 refs) - **[LLaMA-Factory](03-fine-tuning/llama-factory/)** - WebUI no-code fine-tuning (78 lines + 5 refs) - **[Unsloth](03-fine-tuning/unsloth/)** - 2x faster QLoRA fine-tuning (75 lines + 4 refs) - **[PEFT](03-fine-tuning/peft/)** - Parameter-efficient fine-tuning with LoRA, QLoRA, DoRA, 25+ methods (431 lines + 2 refs) ### 🔬 Mechanistic Interpretability (4 skills) - **[TransformerLens](04-mech
What people ask about AI-Research-SKILLs
What is Orchestra-Research/AI-Research-SKILLs?
+
Orchestra-Research/AI-Research-SKILLs is skills for the Claude AI ecosystem. 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. It has 9.6k GitHub stars and was last updated 1mo ago.
How do I install AI-Research-SKILLs?
+
You can install AI-Research-SKILLs by cloning the repository (https://github.com/Orchestra-Research/AI-Research-SKILLs) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Orchestra-Research/AI-Research-SKILLs safe to use?
+
Our security agent has analyzed Orchestra-Research/AI-Research-SKILLs and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains Orchestra-Research/AI-Research-SKILLs?
+
Orchestra-Research/AI-Research-SKILLs is maintained by Orchestra-Research. The last recorded GitHub activity is from 1mo ago, with 16 open issues.
Are there alternatives to AI-Research-SKILLs?
+
Yes. On ClaudeWave you can browse similar skills at /categories/skills, sorted by popularity or recent activity.
Deploy AI-Research-SKILLs to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/orchestra-research-ai-research-skills)<a href="https://claudewave.com/repo/orchestra-research-ai-research-skills"><img src="https://claudewave.com/api/badge/orchestra-research-ai-research-skills" alt="Featured on ClaudeWave: Orchestra-Research/AI-Research-SKILLs" width="320" height="64" /></a>More Skills
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Antigravity, and the open Agent Skills standard.
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
No description provided.