NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local NIM containers for confidential or proprietary sequences.
安装
npx skills add NVIDIA/skills --skill msa-structure-prediction-pipelinenpx skills add NVIDIA/skills --skill msa-structure-prediction-pipeline -a claude-code -gnpx skills add NVIDIA/skills --skill msa-structure-prediction-pipeline -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/bionemo-msa-structure-prediction-pipelinegh skill install NVIDIA/skills msa-structure-prediction-pipelinegit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/bionemo-msa-structure-prediction-pipeline ~/.claude/skills/msa-structure-prediction-pipeline # Claude Code
cp -R /tmp/NVIDIA__skills/skills/bionemo-msa-structure-prediction-pipeline ~/.agents/skills/msa-structure-prediction-pipeline # Codex, Cursor, Gemini CLI, Copilot, OpenCode