ALWAYS check before using kubectl commands. Guide for Kubernetes-related skills.
From workflowsnpx claudepluginhub eveld/claude --plugin workflowsThis skill uses the workspace's default tool permissions.
You have specialized Kubernetes debugging skills. Use these instead of raw kubectl commands for consistent, well-documented workflows.
Simple, single kubectl command query?
→ Use kubernetes skill
kubectl get pods commandsComplex investigation requiring multiple steps? → Use Task tool with K8s agents (conserves context)
k8s-locator - Find and list resources across namespacesk8s-analyzer - Diagnose pod/deployment issues, check logs/eventsk8s-pattern-finder - Find patterns across resources, detect infrastructure issuesSpecific pod crashing or failing?
→ Use k8s-debug skill
Just need to find resources broadly?
→ Use k8s-locator agent only
Investigating single pod/service issue?
→ Use k8s-locator + k8s-analyzer agents
Need to find patterns or cluster-wide issues?
→ Use all three: k8s-locator + k8s-analyzer + k8s-pattern-finder
| Type | Name | Purpose |
|---|---|---|
| Skill | kubernetes | Simple queries (single kubectl command) |
| Skill | k8s-debug | Launch ephemeral debug container |
| Agent | k8s-locator | Find and list resources across namespaces |
| Agent | k8s-analyzer | Diagnose pod/deployment issues |
| Agent | k8s-pattern-finder | Find patterns, cluster-wide issues |
Only use kubectl directly when:
For systematic Kubernetes work, use the specialized skills above.
Covered by skills:
kubectl get → Use kuberneteskubectl describe → Use kuberneteskubectl logs → Use kuberneteskubectl debug → Use k8s-debugNot covered yet (use directly):
kubectl apply, kubectl delete, kubectl edit (destructive operations)kubectl port-forward, kubectl exec (interactive operations)Check context before any kubectl operation:
kubectl config current-context
kubectl config view --minify