Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
Install
npx skills add NVIDIA/skills --skill dynamo-interconnect-checknpx skills add NVIDIA/skills --skill dynamo-interconnect-check -a claude-code -gnpx skills add NVIDIA/skills --skill dynamo-interconnect-check -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/dynamo-interconnect-checkgh skill install NVIDIA/skills dynamo-interconnect-checkgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/dynamo-interconnect-check ~/.claude/skills/dynamo-interconnect-check # Claude Code
cp -R /tmp/NVIDIA__skills/skills/dynamo-interconnect-check ~/.agents/skills/dynamo-interconnect-check # Codex, Cursor, Gemini CLI, Copilot, OpenCode