AI-Research-SKILLs
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
What is AI-Research-SKILLs?
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.
Overview of AI-Research-SKILLs
What it is
AI-Research-SKILLs is an open-source library of 98 skills for AI research and engineering, maintained by Orchestra Research. It is designed to enable AI agents (such as Claude Code, Codex, or Gemini) to autonomously conduct AI research — from literature survey and idea generation through experiment execution to paper writing. The library provides both a research orchestration layer (autoresearch, ideation, paper writing) and engineering skills (training, evaluation, deployment) needed at each stage. It is licensed under MIT and available for free.
Key features
- 98 skills across 23 categories covering the full AI research lifecycle, including Autoresearch, Fine-Tuning, Distributed Training, Evaluation, Inference, Safety, Multimodal, and more.
- Autoresearch orchestration layer uses a two-loop architecture (inner optimization + outer synthesis) to manage the full workflow from idea to paper.
- Production-ready, expert-level guidance — each skill includes documentation sourced from official repos, real GitHub issues, and battle-tested workflows, with code examples and troubleshooting guides.
- Quick install via a single npx command for humans, or by pointing an AI agent to a welcome document.
- Auto-detects coding agents (Claude Code, Hermes Agent, OpenCode, Qoder, Cursor, Gemini CLI, etc.) and installs skills with symlinks or copies.
Use cases
- Autonomous AI research agents that perform literature survey, generate hypotheses, run experiments, and write papers.
- AI-assisted model training and fine-tuning using skills for Axolotl, LLaMA-Factory, TRL, and other frameworks.
- Inference serving and optimization using skills for vLLM, TensorRT-LLM, llama.cpp, quantization libraries, and more.
- Evaluation and safety alignment with skills for lm-eval-harness, NeMo Guardrails, LlamaGuard, and other evaluation and safety frameworks.
- Multimodal and agent development leveraging skills for CLIP, Whisper, LLaVA, LangChain, and more.
Getting started
For humans — interactive installer:bashnpx @orchestra-research/ai-research-skillsFor AI agents — point your agent to the welcome document:Read https://www.orchestra-research.com/ai-research-skills/welcome.md and follow the instructions to install and use AI Research Skills.Additional CLI commands:bashnpx @orchestra-research/ai-research-skills list # View installed skillsnpx @orchestra-research/ai-research-skills update # Update installed skills
License and pricing
This project is licensed under the MIT License and is open-source. No pricing information is provided; it is available for free.
Based on the project's public README and repository metadata.