Automation & Ops ✓ Google · Official google-cloudgkekubernetesgpu-inferencetpu-inferencellm-servingautoscaling

GKE AI Inference Deployment Assistant

Deploy, tune, and autoscale GPU/TPU AI inference services on GKE.

FollowSkills review · FSRS-2.0
Not recommended
46/ 100 5-point scale 2.3 / 5
Trust14 / 25 · 2.8/5

The document requires authenticated gcloud access and GPU/TPU quota, and notes that Hugging Face tokens should be stored in a Kubernetes Secret; however, it does not specify least-privilege IAM, data flows, sensitive-data handling, pre-deployment confirmation, rollback, or deletion procedures. Because kubectl apply can cause external infrastructure changes, points are deducted. No malware, credential theft, or covert exfiltration behavior is evident.

Reliability7 / 20 · 1.8/5

The workflow from model discovery through manifest generation, deployment, and monitoring is broadly coherent and the commands are concrete; however, it lacks version pinning, command-availability checks, diagnostic failure handling, and rollback guidance. The troubleshooting table and several tables also contain malformed Markdown. Under static calibration, no execution was performed, so reliability remains below 10.

Adaptability8 / 15 · 2.7/5

The audience, scenarios, and non-fit boundary for generic batch or HPC queues are reasonably clear, and the skill covers GPUs, TPUs, model servers, and autoscaling. Inputs and outputs, trigger precision, detailed non-fit cases, and environment compatibility are still underspecified, with no Chinese-language or mainland-China reachability discussion.

Convention8 / 15 · 2.7/5

The skill includes front matter, prerequisites, a staged workflow, examples, optimization guidance, and troubleshooting. Repository context supplies Apache-2.0 licensing, installation, contribution, and active-development information. However, the skill lacks its own version, changelog, named maintenance responsibility, update path, dependency versions, known limitations, and FAQ; information layering is basic.

Effectiveness6 / 15 · 2.0/5

For common GKE inference deployments, the commands, ComputeClass example, HPA example, and optimization tips provide useful directly adaptable material and cover the core task. Still, there are no committed representative outputs, execution results, or complete production configurations; users must fill in secrets, PVCs, monitoring, model storage, and failure handling. The score is therefore moderate and below the static ceiling.

Verifiability3 / 10 · 1.5/5

The skill contains inspectable commands, YAML, and troubleshooting content, providing limited auditability. It lacks a test suite, CI coverage, third-party execution evidence, versioned official citations, and cross-source corroboration. The assessment relies mainly on author-provided documentation, with no execution performed.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 513a7a51e85f
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The deployment examples modify external GKE/Kubernetes state without requiring explicit confirmation, permission review, or rollback; production users should review manifests, IAM, Secrets, PVCs, quotas, and costs first.
  • The gcloud AI Profiles commands, model/accelerator combinations, ComputeClass API, GPU metric name, and TPU/GPU availability may vary by version and region; versions and official verification links are not pinned.
  • Several tables are malformed and troubleshooting is incomplete; reachability of Hugging Face, model registries, and related Google services from mainland-China networks is not established.
Review evidence [1][2][3][4]
See the full review method →

What does this skill do, and when should you use it?

This skill supports teams running AI/ML inference workloads on Google Kubernetes Engine. It uses Google’s Inference Quickstart and LLM-serving practices to help select models, inference servers, and GPU or TPU accelerators, then generate Kubernetes manifests. It also covers ComputeClasses, GPU-metric autoscaling, and practical inference optimization. It is explicitly not intended for generic batch jobs or HPC task queues.

It uses gcloud container ai profiles to list supported models and valid model–accelerator–server combinations, then generates an inference.yaml Kubernetes manifest. The manifest can specify a model, vLLM/TGI/Triton/TensorRT-LLM server, GPU or TPU type, and an optional normalized time-per-output-token target. The skill provides a ComputeClass example, a GPU-metric HorizontalPodAutoscaler example, and guidance on quantization, batching, tensor parallelism, and vLLM KV-cache allocation. After generation, users can deploy with kubectl apply, inspect Pods and logs, and use the listed Kubernetes MCP tools to inspect resources, rollouts, and events.

  1. A platform engineer needs to deploy a Llama, Gemma, or Mistral model on GKE.
  2. An ML engineer needs to identify a valid accelerator and inference-server combination for a model.
  3. A cloud infrastructure team needs a GPU-targeting ComputeClass for inference on GKE Autopilot.
  4. An operations team needs to scale an LLM service using GPU utilization or request queue depth.
  5. A GKE user is troubleshooting an invalid combination, GPU quota exhaustion, GPU OOM, or slow model cold start.

What are this skill's strengths and limitations?

Pros
  • Covers model and hardware discovery, manifest generation, deployment, monitoring, and troubleshooting.
  • Names concrete server options including vLLM, TGI, Triton, and TensorRT-LLM.
  • Includes accelerator selection, ComputeClasses, autoscaling, and memory-optimization guidance.
  • Defines its boundary clearly by excluding generic batch and HPC workloads.
Limitations
  • Requires an existing GKE Autopilot cluster, authenticated gcloud CLI, and sufficient GPU or TPU quota.
  • Some operations are explicitly CLI-only and cannot rely solely on the listed MCP tools.
  • The source provides no test suite, platform-validation scope, or actual cost estimates.
  • Some models may require Hugging Face tokens, PVCs, or manifest customization.

How do you install this skill?

Install the repository’s skill collection with npx skills add google/skills. The README says the installer lets users select specific skills from the repository, but it does not document a separate command or destination directory for installing only gke-inference.

How do you use this skill?

With an authenticated gcloud environment and a GKE Autopilot cluster that supports GPU workloads, use a prompt such as: “Deploy Gemma 2 9B on GKE with vLLM and an NVIDIA L4, and generate the inference manifest.” The skill can run gcloud container ai profiles models list --quiet, query combinations with gcloud container ai profiles list --model=gemma-2-9b-it --quiet, and generate inference.yaml with the manifest command. Review placeholders such as Hugging Face tokens and PVCs, then deploy with kubectl apply -f inference.yaml and monitor the Pods.

How does this skill compare with similar options?

Compared with the repository’s gke-batch-hpc skill, this skill focuses on AI/ML inference, model serving, and LLM autoscaling on GKE; generic batch jobs and HPC task queues should use gke-batch-hpc.

FAQ

Does it create the GKE cluster for me?
That is not established by the provided content. An existing GKE Autopilot cluster supporting GPU workloads is a stated prerequisite.
What permissions or external resources are required?
You need an authenticated gcloud CLI, sufficient GPU or TPU quota in the target region, and a Kubernetes environment where deployment and monitoring commands can run.
Does it provide actual cloud pricing?
No. It provides only relative accelerator cost levels.
Which deployment failures does it address?
It covers unsupported model/accelerator combinations, GPU quota limits, GPU out-of-memory errors, and slow cold starts caused by model loading.

More skills from this repository

All from google/skills

Automation & Ops ✓ Google · Official

GKE Cluster Creation Advisor

Plan, provision, and audit GKE clusters against production best practices.

Automation & Ops ✓ Google · Official

AI Workload Migration to GKE Inference

Move existing AI inference workloads to self-hosted inference on Google Kubernetes Engine.

Automation & Ops ✓ Google · Official

GKE Production Golden Path

Set production-oriented GKE defaults, readiness checks, and decision guardrails for cluster design.

Automation & Ops ✓ Google · Official

GKE Basics Navigator

A focused entry point for discovering GKE cluster needs and routing each task to the right specialist skill.

Automation & Ops ✓ Google · Official

GKE ComputeClasses Advisor

Configure, optimize, and troubleshoot GKE ComputeClasses for cost, capacity, and workload placement.

Automation & Ops ✓ Google · Official

GKE Cluster Autoscaler Guide

Configure, optimize, and troubleshoot automatic GKE node scaling.

Automation & Ops ✓ Google · Official

GKE Enterprise RAG Search Architect

Designs and validates enterprise RAG search systems built on GKE and AlloyDB.

Automation & Ops ✓ Google · Official

Google Cloud Performance Advisor

Assess and improve workload performance using the Google Cloud WAF.

Automation & Ops ✓ Google · Official

GKE Workload Autoscaling

Configure manual scaling, HPA, and VPA for GKE workloads while improving resource requests from observed usage.

Automation & Ops ✓ Google · Official

GKE Cost Optimization

Reduce GKE spending through rightsizing, quotas, Spot VMs, and capacity planning.

Automation & Ops ✓ Google · Official

GKE Observability Configuration

Configure GKE logging, monitoring, and Prometheus metrics.

Dev & Engineering ✓ Google · Official

Google Agents CLI Agent Development Guide

Guides agents from specification through development, deployment, and monitoring.

Automation & Ops ✓ Google · Official

GKE Multi-Tenancy Planner

Plan isolation, quotas, access control, and cost attribution for teams sharing a GKE cluster.

Automation & Ops ✓ Google · Official

GKE Production Readiness Review

Assess whether GKE clusters and workloads are ready for production.

Automation & Ops ✓ Google · Official

GKE App Onboarding Assistant

Containerize and deploy an application to Google Kubernetes Engine for the first time.

Automation & Ops ✓ Google · Official

GKE Storage Manager

Configure persistent disks, Filestore, and GCS FUSE storage for GKE workloads.

Automation & Ops ✓ Google · Official

GKE Workload Reliability Guide

Reduce GKE workload disruption with high-availability configuration.

Automation & Ops ✓ Google · Official

GKE Backup & Disaster Recovery

Configure Backup for GKE policies and restore workflows for stateful workloads.

Automation & Ops ✓ Google · Official

GKE GPU/TPU Disruption Diagnosis

Diagnose and mitigate GKE GPU/TPU node disruptions caused by host maintenance.

Data & Analysis ✓ Google · Official

Google Cloud Agent Evaluation Flywheel

Improve model and agent quality through structured evaluation, failure analysis, and iteration.

Related skills