googlecloudplatform/gke-mcp
25 skills · 623 total installs
$npx skills add googlecloudplatform/gke-mcpSkillInstalls
gke-app-onboardingWorkflows for containerizing and deploying applications to GKE for the first time.gke-reliabilityWorkflows for ensuring high availability and reliability of GKE workloads.gke-cluster-creatorGuides the user through creating GKE clusters using pre-defined templates (Standard, Autopilot, GPU/AI).gke-cost-analysisAnswer natural language questions about GKE-related costs by leveraging BigQuery export and cost allocation data.gke-multi-tenancyGuidance on implementing multi-tenancy and governance in Google Kubernetes Engine (GKE) clusters.gke-networking-edgeWorkflows for configuring edge networking, ingress, and security on GKE.gke-observabilityWorkflows for setting up and auditing observability (logging, monitoring, tracing) on GKE.gke-workload-scalingSpecific workflows for scaling GKE workloads using HPA and VPA, as well as best practices for autoscaling configuration.gke-workload-securityWorkflows for auditing and hardening the security of GKE workloads.custom-golden-image-discoveryExpert at discovering golden base images for GKE custom nodes using technical specs or context clues.gke-ai-troubleshooting-skill-creation-guideExpert instructions for building high-quality GKE troubleshooting skills.gke-ai-troubleshooting-tpu-connection-failure-vbar-oomDiagnose and prevent `vbar_control_agent` segfaults and OOMs caused by race conditions during TPU device resets and frequent metrics collection (e.g.gke-backup-drWorkflows for configuring Backup for GKE and disaster recovery.gke-cluster-lifecycleGuidance on managing the lifecycle and upgrades of Google Kubernetes Engine (GKE) clusters.gke-compute-class-creatorGuide for creating GKE ComputeClass resources. Use this skill when users want to define custom node configurations, autoscaling priorities, or hardware…gke-cost-optimizationGuidance on optimizing costs for Google Kubernetes Engine (GKE) clusters.gke-inference-quickstartDeploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ).gke-productionizeAssists in preparing applications and clusters on GKE for production.gke-storageGuidance on managing storage in Google Kubernetes Engine (GKE) clusters.gke-ai-troubleshooting-jobset-interruptionSystematically diagnose GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads.gke-skill-creatorDynamically generates specialized GKE skills for complex troubleshooting, operational workflows, architectural setup, or performance/cost optimization.gke-ai-troubleshooting-handle-disruption-gpu-tpuDiagnose and predict node disruption during Compute Engine host maintenance for GPU and TPU workloads.gke-tpu-metrics-monitoringMonitor and troubleshoot GKE TPU workloads using GKE system metrics and PromQL.gke-tpu-dynamic-slices-monitoringMonitor and manage GKE TPU Dynamic Slices custom resources. Use when checking slice lifecycle states, troubleshooting failed slice creations (e.g.verify_unusedVerifies if a GKE or Kubernetes cluster is unused (no active compute, external exposure, or persistent data) before allowing deletion.