Skip to main content
skill CX Codex

runai-get-workload-health-summary — Claude Code skill

runai-get-workload-health-summary is a Claude Code skill that summarizes Run:ai workload health for a scope or a single workload. Overview requests need a filter.

no license ★ 4,106 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add NVIDIA/skills --skill runai-get-workload-health-summary -a claude-code
Open on GitHub

What runai-get-workload-health-summary does

The skill reports health across a filtered group of Run:ai workloads or details for one workload. An overview needs at least one filter; if cluster_id is missing, the agent asks for it before querying.

This is a read-only workflow. It does not change workloads, pods, nodes, policies, or quotas. It requires MCP read access to workload listings and status, pods, metrics, submitted specs, and effective policies. Kubernetes access is optional, for additional pod details when MCP data cannot answer a required field. Root-cause diagnosis, cluster health, fleet utilization, and run history are outside its scope.

What it helps with

  • summarize workloads matching a filter
  • find failed or idle workloads
  • inspect the health of one workload
  • list workloads running on a named node

Example prompts for the agent

  • Show failed workloads in cluster cluster_id from the last 2 hours.
  • Find idle workloads in project finance-prod in cluster cluster_id.
  • Check the health of workload training-job-42 in cluster cluster_id.

How to install runai-get-workload-health-summary

1Skills CLI (Vercel)

npx skills add NVIDIA/skills --skill runai-get-workload-health-summary -a claude-code

2Manually: put the files in place

~/.claude/skills/runai-get-workload-health-summary/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/runai-get-workload-health-summary/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about runai-get-workload-health-summary

How do I install runai-get-workload-health-summary in Claude Code?

Run npx skills add NVIDIA/skills --skill runai-get-workload-health-summary -a claude-code. The skill file is placed at ~/.claude/skills/runai-get-workload-health-summary/SKILL.md.

What does runai-get-workload-health-summary do?

It reports health for a filtered set of Run:ai workloads or gives details about one workload. It only reads data and makes no changes.

What does runai-get-workload-health-summary need to run?

It requires MCP read access to workload, pod, metrics, spec, and policy data, plus a cluster_id. Overview requests also need a filter. Kubernetes access is optional.

Similar skills

All skills for DevOps and infrastructure →

From the same set312

The whole set →
tao-train-codetr The tao-train-codetr skill guides Co-DETR training, evaluation, and inference in TAO. Use it to run object detection with COCO data or an image folder. CX Codex +1 ★ 4,106repo stars isaac-mission-control-showcase isaac-mission-control-showcase launches a local Nova Carter simulation in Isaac Sim with Mission Control driving it. Use for demos, scenario testing, and small-warehouse integration diagnostics. CX Codex +1 ★ 4,106repo stars i4h-workflow-scene-edit i4h-workflow-scene-edit edits existing Isaac for Healthcare workflow scenes and task contracts in a live Isaac Sim session without modifying files until instructed to bake. CX Codex +1 ★ 4,106repo stars nvmolkit-usage The nvmolkit-usage skill guides Python work with nvMolKit for batched GPU operations on RDKit molecules. Use it to build or debug fingerprint, similarity, conformer, clustering, and search workflows. CX Codex +1 ★ 4,106repo stars tao-generate-anomalies tao-generate-anomalies orchestrates NVIDIA's PAIDF AnomalyGen pipeline to fine-tune defect models, generate synthetic anomaly images, and evaluate output quality. CX Codex +1 ★ 4,106repo stars portfolio-optimization portfolio-optimization is a Claude Code skill for stock portfolio analysis with Mean-CVaR and Mean-Variance methods using NVIDIA cuOpt. Calculate allocations, assess risk, or backtest. CX Codex +1 ★ 4,106repo stars warp-eval warp-eval is a Claude Code skill that checks whether a specific hot code path is suitable for NVIDIA Warp, presenting measurements and evidence rather than an adoption verdict. CX Codex +1 ★ 4,106repo stars tao-run-deft-aoi-cosmos3 tao-run-deft-aoi-cosmos3 executes iterative training workflows for Cosmos3 visual inspection models. Designed strictly for binary OK or NG verification. CX Codex +1 ★ 4,106repo stars

Project sponsors

Companies that keep this analytics open