How do I install the Dgx Station Diagnose skill?

Run npx skillmds@latest add nvidia/dgx-station-diagnose in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dgx Station Diagnose safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dgx Station Diagnose?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dgx Station Diagnose free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dgx Station Diagnose?

NVIDIA (@nvidia) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dgx Station Diagnose by nvidia — Agent Skill

Name: Dgx Station Diagnose
Author: NVIDIA

Dgx Station Diagnose

Run and interpret the complete read-only dgx-assist diagnostic suite for NVIDIA DGX Station GB300, correlate findings with pinned NVIDIA playbooks, export a redacted support bundle, and apply one separately approved allowlisted fix. Use when the user reports a Station, CUDA, GPU health, coherency, vsloshd, Docker, CDI, MIG, cache, port, or owned inference-service failure.

NVIDIA 34ea5b3 5 files · 5.5 KB Updated Sep 17, 2026 2.2k repo stars

File contents

DGX Station diagnostics

Diagnose first. Do not mutate as part of diagnosis.

Workflow

Run scripts/dgx-assist diagnose run --json.
Report the detected compatibility profile, then findings in severity order with their stable IDs and evidence. Preserve unknown states. On Software 1.0, do not reinterpret intentionally skipped Software 2.0 service checks as faults.
Search the pinned playbooks for each high or critical finding; cite the relevant URL, heading, lines, and commit.
If no passage overlaps, say so and avoid inventing a platform fix.
Offer diagnose bundle --report-id "<id>" when escalation is appropriate.
Offer at most one automatic fix at a time, and only when fix_id is present.
Preview with diagnose fix --report-id "<id>" --finding "<id>" --dry-run.
Explain exact actions, impact, privilege, and reboot state. Obtain explicit approval.
Repeat with --yes only after approval and report the action receipt.

Safety requirements

Keep diagnose run read-only.
Never install packages, rewrite Docker configuration, change power caps or driver parameters, kill workloads, or modify MIG through a diagnostic fix.
Never stop a service without current dgx-assist ownership evidence.
Never use Fabric Manager as a routine Station check or remediation.
Re-run diagnostics when finding evidence is stale.
Never reveal secrets or unredacted home paths in a bundle.
Do not execute an unregistered remediation.
Treat --yes only as approval already obtained.

Read references/findings.md before proposing a fix or support bundle. Read references/bringup.md when the problem concerns physical deployment, BMC or firmware verification, driver bring-up, power braking, or support escalation.

---name: dgx-station-diagnosedescription: Run and interpret the complete read-only dgx-assist diagnostic suite for NVIDIA DGX Station GB300, correlate findings with pinned NVIDIA playbooks, export a redacted support bundle, and apply one separately approved allowlisted fix. Use when the user reports a Station, CUDA, GPU health, coherency, vsloshd, Docker, CDI, MIG, cache, port, or owned inference-service failure.---# DGX Station diagnosticsDiagnose first. Do not mutate as part of diagnosis.## Workflow1. Run `scripts/dgx-assist diagnose run --json`.2. Report the detected compatibility profile, then findings in severity order with their stable IDs and evidence. Preserve `unknown` states. On Software 1.0, do not reinterpret intentionally skipped Software 2.0 service checks as faults.3. Search the pinned playbooks for each high or critical finding; cite the relevant URL, heading, lines, and commit.4. If no passage overlaps, say so and avoid inventing a platform fix.5. Offer `diagnose bundle --report-id "<id>"` when escalation is appropriate.6. Offer at most one automatic fix at a time, and only when `fix_id` is present.7. Preview with `diagnose fix --report-id "<id>" --finding "<id>" --dry-run`.8. Explain exact actions, impact, privilege, and reboot state. Obtain explicit approval.9. Repeat with `--yes` only after approval and report the action receipt.## Safety requirements- Keep `diagnose run` read-only.- Never install packages, rewrite Docker configuration, change power caps or driver parameters, kill workloads, or modify MIG through a diagnostic fix.- Never stop a service without current `dgx-assist` ownership evidence.- Never use Fabric Manager as a routine Station check or remediation.- Re-run diagnostics when finding evidence is stale.- Never reveal secrets or unredacted home paths in a bundle.- Do not execute an unregistered remediation.- Treat `--yes` only as approval already obtained.Read [references/findings.md](references/findings.md) before proposing a fix or support bundle. Read [references/bringup.md](references/bringup.md) when the problem concerns physical deployment, BMC or firmware verification, driver bring-up, power braking, or support escalation.

Frequently asked questions