Claude AI Research Skills — AI skill for Claude Code

AI Research Engineering `Skills` Library

**The most comprehensive open-source library of AI research skills for AI models**

[](https://opensource.org/licenses/MIT) [](.) [](CONTRIBUTING.md) [](https://www.orchestra-research.com/perspectives/ai-research-skills)

Our Mission

**Enable AI agents to autonomously conduct AI research**—from hypothesis to experimental verification. We provide the foundational skills that empower **AI research agents** to conduct experiments, including preparing datasets, executing training pipelines, deploying models, and validating scientific hypotheses.

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 - 43/70 skills spanning model architecture, tokenization, fine-tuning, data processing, post-training, distributed training, optimization, inference, agents, RAG, and multimodal
• Research-Grade Quality - Documentation sourced from official repos, real GitHub issues, and battle-tested production workflows

📚 Available Skills (43/70 roadmap)

**Quality over quantity**: