
NVIDIA-verified agent skills for CUDA-X, RAG, and Physical AI
Pull an AlphaFold structure by UniProt ID and read its confidence, domains and disordered regions.
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
From Google DeepMind's science-skills pack. Given a UniProt accession, the agent fetches the AlphaFold predicted structure and reports pLDDT confidence, likely domain boundaries and disordered stretches. It asks for a UniProt ID first rather than guessing from a gene or protein name.
Used it? Write the first review.

NVIDIA-verified agent skills for CUDA-X, RAG, and Physical AI

166 scientific research skills that turn any agent into a co-scientist
Gather literature, benchmarks and prior art for an autonomous research task, with provenance notes.
Twelve research-advisor skills, from evaluating an idea to drafting a rebuttal.
Score and annotate genetic variants with AlphaGenome Variant Impact scores via the Atlas API.
Google DeepMind's pack of 40 science skills for genomics, protein structure, chemistry and literature search.