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.
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add nvidia/skills/dynamo-interconnect-checkCompatible with
Supported agents
| name | dynamo-interconnect-check |
| description | 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. |
| license | Apache-2.0 |
| metadata | author: Dan Gil <dagil@nvidia.com> tags: - dynamo - nixl - rdma - disagg - validation |
Confirm that the transport disaggregated serving depends on actually works. A deployment can pass an endpoint smoke test while disagg is silently wrong: if NIXL/UCX cannot reach the peer worker over RDMA or NVLink, KV transfer falls back to a slow or broken path. Catch that with read-only checks before trusting a disagg deployment or its benchmark numbers.
This skill is read-only. It never mutates the cluster and never prints secrets.
kubectl exec access to a worker pod in the target Dynamo deployment.recipes/<model>/<framework>/<mode>).ibstat, nvidia-smi, lsmod available in the worker pod image (missing tools are reported as skipped, not failures).dynamo-recipe-runner deploys a disagg or multi-node recipe.For diagnosing pods that are already crashing or unschedulable, use
dynamo-troubleshoot first.
python3 scripts/check_interconnect.py env recipes/<model>/<framework>/<mode>
Reports which NIXL/UCX/NCCL transport variables are set and flags
disagg-critical ones (e.g. UCX_TLS, UCX_NET_DEVICES, NCCL_IB_HCA) that are
absent. Missing here is only a warning — they may be baked into the image — so
confirm with the node and NIXL checks. See
references/interconnect-env-vars.md for what each variable does.
Locally on a GPU node, or inside a running worker pod:
python3 scripts/check_interconnect.py node \
--namespace "${NAMESPACE}" --pod <worker-pod>
Probes (read-only) for: InfiniBand devices and Active links, GPUDirect RDMA
(nvidia_peermem), GDRCopy, and NVLink in the GPU topology. Missing tools are
reported as skipped, not failures.
python3 scripts/check_interconnect.py nixl \
--namespace "${NAMESPACE}" --pod <worker-pod>
Looks for NIXL test tooling in the pod and surfaces the exact next step to run a pairwise prefill↔decode transfer test. A full cross-pod transfer test requires two scheduled GPU pods on the fabric.
| Script | Purpose | Arguments |
|---|---|---|
scripts/check_interconnect.py env | Inspect NIXL/UCX/NCCL env vars on a recipe | positional recipe path |
scripts/check_interconnect.py node | Probe InfiniBand, GPUDirect RDMA, GDRCopy, NVLink on a node or pod | --namespace, --pod |
scripts/check_interconnect.py nixl | Surface NIXL transfer-test readiness for a pod | --namespace, --pod |
Invoke via the agentskills.io run_script() protocol:
run_script("scripts/check_interconnect.py", args=["env", "recipes/qwen3-coder-480b/sglang/disagg"])
run_script("scripts/check_interconnect.py", args=["node", "--namespace", "dynamo-demo", "--pod", "qwen-worker-0"])
Verify a disagg recipe's transport env shape before deploy:
python3 scripts/check_interconnect.py env recipes/qwen3-coder-480b/sglang/disagg
After deploy, validate a worker pod's fabric:
python3 scripts/check_interconnect.py node \
--namespace dynamo-demo --pod qwen-worker-0
python3 scripts/check_interconnect.py nixl \
--namespace dynamo-demo --pod qwen-worker-0
Equivalent through the agent protocol:
run_script("scripts/check_interconnect.py", args=["nixl", "--namespace", "dynamo-demo", "--pod", "qwen-worker-0"])
Each check returns ok / warn / fail / skipped with a one-line detail,
plus a rolled-up verdict on disagg transport readiness. Report:
skipped results for missing tools (ibstat, nvidia-smi, lsmod) are inconclusive, not a pass.| Symptom | Likely cause | Next step |
|---|---|---|
env reports all critical vars missing | Vars baked into image or injected by operator | Run the node check inside the worker pod to verify actual env |
node reports no Active IB link | Fabric down or HCA not provisioned to the node | Contact cluster admin; verify kubectl describe node shows nvidia.com/gpu and IB labels |
nvidia_peermem missing | GPUDirect RDMA module not loaded | Ask cluster admin to load nvidia-peermem; without it, NIXL falls back to staged copies |
nixl finds no test tools | Worker image lacks NIXL test harness | Use a NIXL-enabled image or run the standalone transfer test from a debug pod |
See BENCHMARK.md for the NVCARPS-EVAL performance report (auto-generated by the NVSkills CI pipeline). To refresh, re-run /nvskills-ci on an upstream PR touching this skill.
references/interconnect-env-vars.md — NIXL/UCX/NCCL env var catalog and IB
capability checklist.scripts/check_interconnect.py for all read-only checks.AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiondynamo-interconnect-checkExecute the skills CLI command in your project's root directory to begin installation:
epx add nvidia/skills/dynamo-interconnect-checkFetches dynamo-interconnect-check from nvidia/skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/dynamo-interconnect-check
Restart Cursor to activate dynamo-interconnect-check. Access via /dynamo-interconnect-checkin your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
dynamo-recipe-runner
nvidia/skills · dynamo · same repo
rag-blueprint
nvidia/skills · rag · same repo
jetson-print-bsp-info
nvidia/skills · jetson · same repo
nemo-mbridge-perf-megatron-fsdp
nvidia/skills · nemo-mbridge · same repo
jetson-customize-mgbe
nvidia/skills · jetson · same repo
cuopt-routing-formulation
nvidia/skills · cuopt · same repo
dynamo-interconnect-check has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend dynamo-interconnect-check for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Keeps context tight: dynamo-interconnect-check is the kind of skill you can hand to a new teammate without a long onboarding doc.
dynamo-interconnect-check reduced setup friction for our internal harness; good balance of opinion and flexibility.
Registry listing for dynamo-interconnect-check matched our evaluation — installs cleanly and behaves as described in the markdown.
Solid pick for teams standardizing on skills: dynamo-interconnect-check is focused, and the summary matches what you get after install.
We added dynamo-interconnect-check from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
dynamo-interconnect-check fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in dynamo-interconnect-check — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend dynamo-interconnect-check for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 46