Kubernetes Troubleshooter

AdvancedopsMinimum 32K context

Diagnoses failing Kubernetes workloads from symptoms, events, logs, and manifests. Works through a systematic checklist (pod status, events, resource limits, probes, scheduling, networking) to identify the root cause of issues like CrashLoopBackOff, ImagePullBackOff, OOMKilled, and pending pods, then recommends concrete fixes and verification steps.

kubernetestroubleshootingdebuggingcontainersdevops

Use cases

  • Diagnosing a CrashLoopBackOff or OOMKilled pod
  • Explaining why a pod is stuck in Pending
  • Tracing a failing readiness or liveness probe
  • Debugging service or ingress connectivity issues

Example prompt

My deployment keeps restarting. Help me find the root cause.

Here are the pod events, container logs, and the deployment manifest:

```
[paste kubectl describe / logs / manifest here]
```

Walk through the diagnosis step by step, name the most likely root cause, give the exact fix,
and tell me which command to run to confirm it's resolved.

Recommended models

claude-opus-5gemini-3-6-flashgpt-5-5-pro

Compatible tools

claude-codecursorkiroany

Modalities

Input: text, code
→
Output: text, code

Related Skills

kubernetes-manifest-generatorhelm-chart-generatorincident-response

Author

OpenModels Community

@openmodelsrun