Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plans, creates, and configures production-ready Google Kubernetes Engine (GKE) clusters using the golden path Autopilot configuration. Covers networking, security, observability, scaling, cost optimization, and AI/ML inference on GKE.
.claude/skills/davila7-gke-basics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 36% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 47% | 0% |
GKE is a managed Kubernetes platform on Google Cloud for deploying, scaling, and operating containerized applications. This skill defaults to the golden path Autopilot configuration — see gke-golden-path.md for defaults, rules, and guardrails.
bashgcloud services enable container.googleapis.com --quiet gcloud container clusters create-auto my-cluster --region=us-central1 --quiet gcloud container clusters get-credentials my-cluster --region=us-central1 --quiet kubectl create deployment hello-server \ --image=us-docker.pkg.dev/google-samples/containers/gke/hello-app:1.0
Load the relevant reference based on trigger keywords. Prefer the most specific match; if ambiguous, ask the user to clarify.
| Scenario | Trigger Keywords | Reference | |----------|-----------------|-----------| | Core Concepts | Autopilot vs Standard, architecture, pricing, what is GKE | core-concepts.md | | Golden Path & Defaults | golden path, Day-0 checklist, production defaults, cluster defaults | gke-golden-path.md | | Cluster Creation | create cluster, new cluster, provision GKE | gke-cluster-creation.md | | Networking | private cluster, VPC, subnet, Gateway API, DNS, ingress, egress, datapath | gke-networking.md | | Security & IAM | Workload Identity, Secret Manager, RBAC, Binary Auth, hardening, audit, gVisor, IAM roles | gke-security.md | | Scaling | HPA, VPA, autoscaler, autoscaling, NAP, scale pods, scale nodes | gke-scaling.md | | Compute Classes | ComputeClass, machine family, Spot fallback, GPU node pool, node selection | gke-compute-classes.md | | Cost | cost, savings, Spot VMs, rightsizing, CUD, optimize spend, budget | gke-cost.md | | AI/ML Inference | inference, model serving, LLM, GPU, TPU, GIQ, vLLM | gke-inference.md | | Upgrades | upgrade, maintenance window, release channel, patching, version | gke-upgrades.md | | Observability | monitoring, logging, Prometheus, Grafana, metrics, alerts, dashboards | gke-observability.md | | Multi-tenancy | multi-tenant, namespace isolation, team access, enterprise, RBAC planning | gke-multitenancy.md | | Batch & HPC | batch, HPC, job queue, high performance, MPI, parallel | gke-batch-hpc.md | | App Onboarding | containerize, deploy app, Dockerfile, onboard, migrate to GKE | gke-app-onboarding.md | | Backup & DR | backup, restore, disaster recovery, CMEK | gke-backup-dr.md | | Storage | storage, PVC, persistent volume, StorageClass, Filestore, GCS FUSE | gke-storage.md | | Reliability | PDB, health probe, liveness, readiness, topology spread, graceful shutdown | gke-reliability.md | | Client Libraries | client library, client-go, kubernetes python, kubernetes java, kubernetes SDK | client-library-usage.md | | Infrastructure as Code | Terraform, IaC, HCL, infrastructure as code | iac-usage.md | | MCP Server | MCP tools, MCP server, MCP setup | mcp-usage.md | | CLI / Tools | gcloud, kubectl, commands, how to | cli-reference.md | | Production Audit | production readiness, compliance, golden path check | gke-cluster-creation.md |
If you need product information not found in these references, use the Developer Knowledge MCP server search_documents tool.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,871 | 5,670 | -36% | 1 | 1 | 0% | 1,702 | 2,220 | +30% | 0 | 0 | — |
case-02 | fail→pass | 19,838 | 15,579 | -21% | 1 | 1 | 0% | 3,566 | 4,215 | +18% | 0 | 0 | — |
case-03 | pass→pass | 9,494 | 6,338 | -33% | 1 | 1 | 0% | 1,701 | 2,317 | +36% | 0 | 0 | — |
case-04 | pass→pass | 17,356 | 22,424 | +29% | 1 | 1 | 0% | 3,477 | 3,572 | +3% | 0 | 0 | — |
case-05 | pass→pass | 8,140 | 5,866 | -28% | 1 | 1 | 0% | 1,480 | 2,172 | +47% | 0 | 0 | — |
case-06 | pass→pass | 14,286 | 4,071 | -72% | 1 | 1 | 0% | 1,372 | 1,754 | +28% | 0 | 0 | — |
case-07 | pass→pass | 8,096 | 5,250 | -35% | 1 | 1 | 0% | 992 | 1,939 | +95% | 0 | 0 | — |
case-08 | pass→pass | 17,488 | 15,793 | -10% | 1 | 1 | 0% | 3,175 | 4,017 | +27% | 0 | 0 | — |
case-09 | pass→pass | 12,986 | 12,539 | -3% | 1 | 1 | 0% | 2,154 | 3,460 | +61% | 0 | 0 | — |
case-10 | pass→pass | 12,047 | 13,730 | +14% | 1 | 1 | 0% | 2,181 | 3,479 | +60% | 0 | 0 | — |
case-11 | pass→pass | 6,054 | 3,835 | -37% | 1 | 1 | 0% | 678 | 1,733 | +156% | 0 | 0 | — |
case-12 | pass→pass | 3,917 | 6,275 | +60% | 1 | 1 | 0% | 545 | 2,128 | +290% | 0 | 0 | — |
case-13 | pass→pass | 10,356 | 7,128 | -31% | 1 | 1 | 0% | 1,627 | 2,315 | +42% | 0 | 0 | — |
case-14 | pass→pass | 17,372 | 9,935 | -43% | 1 | 1 | 0% | 2,955 | 2,968 | +0% | 0 | 0 | — |
case-15 | pass→pass | 7,274 | 7,769 | +7% | 1 | 1 | 0% | 1,150 | 2,358 | +105% | 0 | 0 | — |
case-16 | pass→pass | 16,126 | 24,287 | +51% | 1 | 1 | 0% | 2,645 | 3,788 | +43% | 0 | 0 | — |
case-17 | pass→pass | 5,449 | 5,644 | +4% | 1 | 1 | 0% | 653 | 1,926 | +195% | 0 | 0 | — |
case-18 | pass→pass | 14,272 | 11,994 | -16% | 1 | 1 | 0% | 2,450 | 3,239 | +32% | 0 | 0 | — |
case-19 | pass→pass | 7,040 | 10,113 | +44% | 1 | 1 | 0% | 1,069 | 2,130 | +99% | 0 | 0 | — |
case-20 | pass→pass | 19,170 | 18,411 | -4% | 1 | 1 | 0% | 3,035 | 4,329 | +43% | 0 | 0 | — |
case-21 | pass→pass | 6,352 | 8,918 | +40% | 1 | 1 | 0% | 995 | 2,684 | +170% | 0 | 0 | — |
case-22 | pass→pass | 3,730 | 5,481 | +47% | 1 | 1 | 0% | 602 | 2,111 | +251% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.