What problem does it solve?
This Skill eliminates unstructured, ad-hoc Kubernetes debugging and design reviews that waste time and miss critical issues. It provides a standardized, phased workflow to diagnose cluster problems, validate manifests, and audit workload or namespace health consistently across teams.
Core Features & Use Cases
- 5-phase structured troubleshooting: Guides users through context gathering, diagnosis, root-cause analysis, prioritized recommendations, and verification for any Kubernetes issue, from CrashLoopBackOff to networking and RBAC failures.
- Manifest design review: Validates Kubernetes YAML and Helm charts against best practices for resource sizing, security hardening, and reliability before deployment to production.
- Cluster health audits: Performs namespace or workload-level health checks to catch misconfigurations, resource pressure, and security gaps before they cause outages.
- Use Case: For example, if your e-commerce platform's payment pods are crashing in production, use this Skill to systematically gather cluster context, identify the root cause (e.g., missing environment variable or OOMKill), and get actionable, prioritized fixes with verification steps.
Quick Start
Use the kubernetes-specialist skill to investigate why the payment pods in the production namespace are crashing and get a prioritized list of fixes.