Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_gpi_channel*), attaching GPU memory to a GPI domain, the domain and channel attribute objects, and…
Install
npx skills add NVIDIA/skills --skill doca-gpinpx skills add NVIDIA/skills --skill doca-gpi -a claude-code -gnpx skills add NVIDIA/skills --skill doca-gpi -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/doca-gpigh skill install NVIDIA/skills doca-gpigit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/doca-gpi ~/.claude/skills/doca-gpi # Claude Code
cp -R /tmp/NVIDIA__skills/skills/doca-gpi ~/.agents/skills/doca-gpi # Codex, Cursor, Gemini CLI, Copilot, OpenCode