What are the best Claude Code skills for Kubernetes?
gke-ai-troubleshooting-jobset-interruption from google/skills is the highest-scoring Claude Code skill for Kubernetes, at 89/100 (grade B) on the Suede Skill Check. The table below compares the top 15 of 69 listed Kubernetes skills from 6 repositories by score, publisher and license, using the October 22, 2026 snapshot of SuedeAI.directory.
- 69 listed Kubernetes skills
- 6 full pages scoring 80+
- 8 repositories
Compare 15 Claude Code skills for Kubernetes
Ranked by Suede Skill Check score. Linked names open the directory listing; scores come from the published rubric.
| Skill | Publisher | Suede Skill Check | License | What it does |
|---|---|---|---|---|
| gke-ai-troubleshooting-jobset-interruption | Google Official google/skills | 89/100 · B | Apache-2.0 | Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart… |
| gke-ai-troubleshooting-tpu-dynamic-slices-monitoring | Google Official google/skills | 89/100 · B | Apache-2.0 | Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice… |
| gke-ai-troubleshooting-tpu-metrics-monitoring | Google Official google/skills | 89/100 · B | Apache-2.0 | Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle… |
| tao-run-on-kubernetes | NVIDIA Official NVIDIA/skills | 87/100 · B | Apache-2.0 | Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for… |
| aks-troubleshooting | Microsoft Official microsoft/azure-skills | 85/100 · B | MIT | Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff… |
| kubernetes-specialist | jeffallan jeffallan/claude-skills | 84/100 · B | MIT | Guides deploying and managing Kubernetes workloads, including manifests, pod security, RBAC, network policies, Helm charts, debugging pod crashes, and right-sizing resources. |
| aks-gpu-inference | Microsoft Official microsoft/azure-skills | 84/100 · B | MIT | Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load… |
| devops-engineer | jeffallan jeffallan/claude-skills | 84/100 · B | MIT | Creates Dockerfiles, CI/CD pipelines, Kubernetes manifests, and Terraform or Pulumi templates, and handles deployment automation, GitOps configuration, and incident response runbooks. |
| mirrord-ci | metalbear-co metalbear-co/skills | 83/100 · B | MIT | Helps set up mirrord in CI pipelines to run end-to-end, integration, or automated tests against real staging or shared Kubernetes clusters. |
| mirrord-config | metalbear-co metalbear-co/skills | 83/100 · B | MIT | Generates, edits, and validates mirrord.json configuration files for connecting a local process to a Kubernetes environment, ensuring the output JSON is valid and schema-conformant. |
| dynamo-recipe-runner | NVIDIA Official NVIDIA/skills | 83/100 · B | Apache-2.0 | Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use… |
| aks-network-capture | Microsoft Official microsoft/azure-skills | 82/100 · B | MIT | Collects bounded packet captures from AKS nodes and Azure network configuration for wire-level evidence. WHEN: "capture packets on an AKS node"… |
| mirrord-quickstart | metalbear-co metalbear-co/skills | 80/100 · B | MIT | Guides new users through installing mirrord via CLI, VS Code, or IntelliJ, running a first session against a Kubernetes target, and verifying the connection. |
| qdrant-hybrid-cloud-setup | Qdrant Official qdrant/skills | 79/100 · C | Apache-2.0 | Guides installing and running Qdrant Hybrid Cloud on your own Kubernetes cluster, covering storage, backups, the agent and operator, cluster exposure, and secret rotation. |
| physical-ai-infrastructure-setup-and-resilient-scaling | NVIDIA Official NVIDIA/skills | 78/100 · C | Apache-2.0 | Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local… |
Questions and answers
Which Kubernetes skill has the highest Suede Skill Check score?
gke-ai-troubleshooting-jobset-interruption from google/skills scores 89/100, grade B, the highest of the 69 listed Kubernetes skills in the October 22, 2026 snapshot. It earns full points for structural checks, recent maintenance and instruction depth. gke-ai-troubleshooting-tpu-dynamic-slices-monitoring from google/skills follows at 89/100.
How do I install a Kubernetes skill in Claude Code?
Run npx skills add with the skill folder's GitHub URL from your project, or copy the folder into .claude/skills/ and Claude Code loads it when a request matches its description. For gke-ai-troubleshooting-jobset-interruption, run: npx skills add https://github.com/google/skills/tree/main/skills/cloud/gke-ai-troubleshooting-jobset-interruption. Each full skill page on SuedeAI.directory lists the same steps for Claude Code and Codex.
Are these Kubernetes skills free?
All 15 Kubernetes skills on this page are published in public GitHub repositories and cost nothing to download. Every one uses an open-source or open-content license, led by MIT (8) and Apache-2.0 (7), so you can use and adapt the files at no cost under those terms. One skill names credentials for an outside service; each full page lists them under Before you install.
Do these Kubernetes skills work with Codex and Cursor?
Yes. Each of the 15 Kubernetes skills on this page is a SKILL.md folder in the Agent Skills format, which Claude Code, Codex and Cursor all read. The skills CLI (npx skills add) installs every one of them into Claude Code, Codex, Cursor and other agents, and each full skill page adds a project-level copy into .claude/skills for Claude Code and .agents/skills for Codex. 2 of them declare compatibility in the SKILL.md frontmatter.
How does SuedeAI.directory rank Kubernetes skills?
By Suede Skill Check score from 0 to 99, which adds structure, description quality, instruction depth, bundled files, maintenance and curated-list citations, all read from each skill's published files. A skill joins this page when its name or summary matches the Kubernetes keyword map; each repository fills at most three rows, so the table compares publishers.
Which Kubernetes skills come from official publishers?
gke-ai-troubleshooting-jobset-interruption, gke-ai-troubleshooting-tpu-dynamic-slices-monitoring and gke-ai-troubleshooting-tpu-metrics-monitoring from Google, tao-run-on-kubernetes, dynamo-recipe-runner and physical-ai-infrastructure-setup-and-resilient-scaling from NVIDIA, aks-troubleshooting, aks-gpu-inference and aks-network-capture from Microsoft and qdrant-hybrid-cloud-setup from Qdrant are published by the company behind the tool, marked Official in the table.
Compare alternatives
More Claude Code skills by task
Presentations · Playwright and Browser Testing · Terraform · SEO · Code Review · Git and Pull Requests · MCP Servers · Data Analysis · AWS · Security Audits · Email · Video · iOS and Swift · Flutter and Dart · React and Next.js · RAG and Vector Search · LLM Evals · SQL and Databases · Technical Documentation · UI Design
Browse by category: DevOps and Cloud.