dynamo-troubleshoot
Diagnose failed or unhealthy Dynamo deployments.
Connecting the steps of a workflow
What it does
Turn a Dynamo failure into a clear problem class, strongest signal, and next action. Start with read-only evidence, avoid secrets, and fix one layer at a time.
Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 1 script
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/collect_dynamo_debug_bundle.py.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
references/failure-decision-tree.md line 147: “curl http://127.0.0.1:8000/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"<model>","messages":[{"role":"user","con…”. Read 2026-10-04, commit 0e0d506.
references/failure-decision-tree.md, line 147 ↗No known risk pattern found
Launch7’s automated check read all 7 text files in this skill and matched none of its risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-04, commit 0e0d506 by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to NVIDIA/skills: 2026-10-02 (2 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 1 script beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
Worth knowing
- It can only read. Nothing it does changes anything on the other side.
More from NVIDIA
All from this publisher →- accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable…
- deepstream-generate-pipeline
Build DeepStream GStreamer pipelines interactively.
- deepstream-import-vision-model
When this skill is active, read the relevant reference document before starting each phase.
- deepstream-profile-pipeline
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement.
- deepstream-sop
DeepStream SOP Inference Microservice Skill
