Back to Skills Marketplace
Skill pack

Kubernetes Triage Assistant

Diagnose Kubernetes workloads, pods, deployments, services, events, logs, rollout issues, and EKS operational risks.

v0.1.0 1 skill tools By Kendr kubernetesk8sekspodsdeploymentslogsdevops
Publisher docsHosted archive

How to use it

  1. Open Kendr Desktop.
  2. Go to Skills, then Marketplace.
  3. Search for Kubernetes Triage Assistant or kubernetes-triage-assistant.
  4. Install the pack, then enable the pack or individual skills you want available in agentic mode.

Kendr Desktop compares the installed version with the hosted catalog version and offers an update when this pack changes.

Install source

Use this hosted archive when installing or updating the pack from Kendr Desktop.

https://kendr.org/api/skills/packs/kubernetes-triage-assistant/archive

Kubernetes Triage Assistant

Diagnose Kubernetes and EKS workload failures with read-first inspection, logs, events, manifests, rollout state, and approval-gated changes.

Kubernetes Triage Assistant

Use this skill when the user asks about Kubernetes pods, deployments, services, ingress, events, logs, rollout failures, CrashLoopBackOff, ImagePullBackOff, EKS clusters, or containerized workloads.

Expected companion packs:

  • AWS Official MCP or an EKS MCP server for EKS cluster context.
  • Grafana Official MCP for cluster metrics, logs, and alert correlation.
  • Docker Operations for local image and container checks.
  • GitHub Official MCP for manifests, Helm charts, Kustomize overlays, and deployment commits.

Workflow:

  • Identify cluster, namespace, workload, pod, container, image tag, and recent deployment time.
  • Inspect current status, events, logs, restart counts, resource requests and limits, probes, image pull state, and rollout history before proposing changes.
  • Distinguish application failure, image issue, configuration issue, scheduling/resource pressure, network/DNS issue, RBAC issue, and cluster health issue.
  • For production incidents, correlate Kubernetes findings with Grafana alerts and recent GitHub deployments.

Actions:

  • Treat apply, patch, delete, rollout restart, scale, secret reads, and exec into containers as sensitive or side-effecting.
  • Use Kendr approval before side-effecting Kubernetes or EKS operations.
  • Do not print Kubernetes Secret values, tokens, kubeconfig contents, or private logs unrelated to the request.