Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
Orchestra-Research/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.
- Stars
- 14,726
- +7 days
- —
- Forks
- 1,012
- Language
- TeX
- License
- MIT
- Last push
- 11 Oct 2026
Summary
Summary written by AI from the README; it may be imprecise.This open-source collection provides 98 skills across 23 categories to support AI research and engineering workflows in Claude Code and other agent platforms. It includes documentation, code patterns, and reference guides for training, fine-tuning, inference, mechanistic interpretability, and academic paper writing. Developers can install the skills individually or as category bundles through an interactive CLI or the Claude Code plugin marketplace.
Use it when
- When orchestrating end-to-end AI research workflows from ideation to paper drafting in Claude Code
- When configuring distributed training, post-training, or quantization tools like DeepSpeed and vLLM
- When needing step-by-step guides and code patterns for model interpretability or evaluation
Install
/plugin marketplace add orchestra-research/AI-research-SKILLs/plugin install fine-tuning@ai-research-skills/plugin install post-training@ai-research-skillsCommands quoted from the repo's README. Read the README before running them.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.