A discovery layer for scientific ML on Hugging Face. When you're working on protein design, genomics, climate modeling, or any of 17 other science domains, this pulls from a curated catalog at huggingscience.co instead of making you grep through thousands of generic Hub entries. It maps your task to the right topic, fetches markdown indexes of datasets and models, then walks you through using them with standard HF libraries. The real value is curation: someone already filtered for quality and openness, so you're not comparing ESM2 variants or weather datasets from scratch. Includes interactive Spaces like BoltzGen for binder design. If your ML is scientific, start here before raw Hub search.
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill hugging-science