#731 · Primary category: AI Agents & Automation

radiology-skills

Open-source Codex skills for radiology AI research: 27 expert workflows covering study design, statistics, multi-omics, and publication-ready reporting.

Project last updated:07/27/26

GitHub Stars

1.5K

Forks

17

Contributors

1

License

MIT

Why we included this project

radiology-skills packages the review standards of journals like Radiology and the Nature family into 27 specialist workflows that Claude or Codex agents can run. The rules come from real submissions and peer-review experience, so the agent audits a study the way a demanding reviewer would: it checks for data leakage, runs reporting checklists such as CLAIM and TRIPOD+AI, and flags missing external validation or calibration curves before a manuscript goes out. Teams sitting on CT, MRI, PET, or ultrasound data get concrete feasibility checks and sample-size reasoning instead of generic advice about whether their dataset can support a publishable project. The same skills carry through annotation protocols, statistical presentation, figure formatting, grant applications, and traceable responses to reviewer comments.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category