Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Dynamo Interconnect Check · nvidia | DecimalAI

devopsby nvidia

Dynamo Interconnect Check

nvidia/dynamo-interconnect-check

Source nvidia/skills ↗License Apache-2.0

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.

SkillScore77Maintained

Automatic

DevOps & SRE pack

Last verified 8/12/2026

What it changes

Passed 13 of 17 test cases with the skill, and 7 of 17 without it.

Without skill41%

With skill77%

Checks it passed that the model alone missed

States Python 3.10+ as the minimum requirement
Specifies running scripts/check_interconnect.py env recipes/deepseek-v3/vllm/disagg
Confirms the script is strictly read-only, does not mutate cluster state, and never prints secrets

and 6 more in the full report

9 fixed8 passed either way4 still failing1 broke

Pass-rate lift: +36 pp
Tokens: +23%
Agent turns: 0%
Response time: -65%

Model gemini-3.6-flashMeasured 8/12/2026v117 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/nvidia-dynamo-interconnect-check/SKILL.md https://app.decimal.ai/s/nvidia-dynamo-interconnect-check/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nvidia-dynamo-interconnect-check, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/nvidia-dynamo-interconnect-check/ and pins it in .decimal/skills.lock

decimalai skills add nvidia-dynamo-interconnect-check

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nvidia-dynamo-interconnect-check/SKILL.md https://app.decimal.ai/s/nvidia-dynamo-interconnect-check/SKILL.md

Raw file: /s/nvidia-dynamo-interconnect-check/SKILL.md ↗ · machine-readable summary at /s/nvidia-dynamo-interconnect-check.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

I want to invoke the NIXL reachability check via the `run_script` python function for pod `prefill-worker-0` in namespace `dynamo-test`. What is the exact function signature invocation?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses run_script with script path scripts/check_interconnect.py and args containing nixl, --namespace, dynamo-test, --pod, and prefill-worker-0	Missed	Passed

case-10 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md146 lines3 filesincludes scripts

Dynamo Interconnect Check

Purpose

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.

Prerequisites

Python 3.10+ on the operator machine.
kubectl exec access to a worker pod in the target Dynamo deployment.
Read access to the recipe directory (recipes/<model>/<framework>/<mode>).
For node-capability checks: tools like ibstat, nvidia-smi, lsmod available in the worker pod image (missing tools are reported as skipped, not failures).

When To Use

After dynamo-recipe-runner deploys a disagg or multi-node recipe.
Before reporting disagg throughput/latency, so numbers reflect the real transport.
When agg works but disagg is slow, hangs, or returns wrong output and you suspect the fabric rather than the model.

For diagnosing pods that are already crashing or unschedulable, use dynamo-troubleshoot first.

Instructions

1. Check Transport Env Vars On The Recipe

Track record

Benchmark

13 / 17

test cases passed, vs 7 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nvidia / skills

skills/dynamo-interconnect-check/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 2 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Dynamo Interconnect Check

Purpose

Prerequisites

When To Use

Instructions

1. Check Transport Env Vars On The Recipe

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills