Automation & Ops ✓ Google · Official gkegputpunode-disruptioncloud-monitoringpromqlpoddisruptionbudget

GKE GPU/TPU Disruption Diagnosis

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

FollowSkills review · FSRS-2.0
Not recommended
50/ 100 5-point scale 2.5 / 5
Trust16 / 25 · 3.2/5

The workflow mainly recommends read-only inspection of node labels, PromQL, logs, and taints, with no destructive default actions; however, it does not explicitly require confirmation before running commands and does not document permissions, sensitive telemetry handling, data flows, rollback, or complete source attribution, so points are deducted.

Reliability7 / 20 · 1.8/5

The sequence and required inputs are reasonably clear and include a negative-result branch with interpretations; however, there are no scripts, tests, CI evidence, or robust abnormal-input handling, and statements such as a maintenance label guaranteeing disruption are overly absolute, so static evidence is limited.

Adaptability9 / 15 · 3.0/5

The name, target scenarios, optional parameters, and excluded scenarios are stated, covering GPU/TPU node-maintenance disruption diagnosis; however, boundaries, output format, and trigger conditions remain limited, Chinese-language support is absent, and the workflow depends on GKE, kubectl, Cloud Monitoring, and Cloud Logging environments, so points are deducted.

Convention8 / 15 · 2.7/5

The documentation uses a staged diagnostic workflow and the repository context supplies installation guidance, an Apache-2.0 license, and several command examples; however, the skill lacks its own version, changelog, dependency setup, maintenance owner, or dedicated update path, and limitations and FAQs are sparse.

Effectiveness6 / 15 · 2.0/5

The workflow can directly guide checks of maintenance labels, PromQL, logs, and taints and offers mitigation directions involving termination grace periods, opportunistic maintenance, and PDBs; however, representative outputs are not verified, the mandatory triad may not fit every workload, and static review cannot establish correctness, so points are deducted.

Verifiability4 / 10 · 2.0/5

The skill provides concrete fields, metrics, PromQL, and links to Google Cloud documentation, giving limited auditability; however, it contains no committed tests, CI coverage, execution evidence, or cross-source corroboration, leaving conclusions primarily author-supplied.

Evidence confidence:Low Reviewed Jul 28, 2026 Reviewed revision d1c9be2009ba
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
  • Recheck absolute claims such as a scheduled-maintenance label guaranteeing disruption against authoritative semantics and actual event evidence.
  • Before running kubectl or querying logs and monitoring, confirm authorization, least-privilege access, and sensitive-data redaction requirements.
  • Apply opportunistic maintenance, termination grace periods, and PDBs according to workload type, controller behavior, and recovery objectives rather than unconditionally.
  • The skill provides no Chinese-language guidance or mainland-China reachability information; access to dependent Google Cloud services may be environment-sensitive.
Review evidence [1][2][3][4]
See the full review method →

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

This skill targets GKE node pools running GPU or TPU workloads. It uses node maintenance labels, Cloud Monitoring PromQL, Cloud Logging, and node taints to determine whether a disruption came from Compute Engine host maintenance. When maintenance is confirmed, it recommends graceful termination, opportunistic maintenance, and PodDisruptionBudgets together. When all maintenance signals are absent, it directs investigation toward application-level causes such as OOMKill, CUDA errors, or resource limits.

For incomplete real-incident reports, it requests project_id, location, cluster_name, and timestamp; uses kubectl to query the scheduled-maintenance-time label; provides PromQL for kubernetes_io:node_interruption_count and node_pool_interruption_count; checks logs for active-node-maintenance=ONGOING and the impending-node-termination:NoSchedule taint; and produces a high-signal conclusion with recommendations for terminationGracePeriodSeconds, opportunistic maintenance, and PodDisruptionBudgets.

  1. GKE operators investigating an unexpected restart or disruption on a GPU node.
  2. Platform engineers checking whether a GPU or TPU node pool has upcoming host maintenance.
  3. Observability engineers tracking hardware or software maintenance interruptions with PromQL.
  4. Machine learning teams protecting workloads that need time to save checkpoints.
  5. Teams distinguishing Compute Engine host maintenance from OOMKill, CUDA errors, or resource-limit failures.

What are this skill's strengths and limitations?

Pros
  • Has a clearly defined focus on host-maintenance disruptions affecting GKE GPU/TPU nodes.
  • Includes concrete kubectl checks, PromQL expressions, and log/taint verification.
  • Requires three complementary workload-protection measures when maintenance is confirmed.
  • Provides an explicit application-level fallback when maintenance evidence is negative.
Limitations
  • It does not cover general GKE cluster creation, network policies, or non-disruption workload deployment.
  • It requires four pieces of incident context before investigating an actual disruption.
  • The source provides no test suite, version compatibility matrix, or detailed permission guidance.
  • The source does not document installation paths or automatic Cloud Monitoring/Logging tool integration.

How do you install this skill?

Run the command provided by the repository README to install the collection: npx skills add google/skills. The installer allows selection of individual skills from the repository; the source does not document a destination path or a separate command for selecting this skill.

How do you use this skill?

Place the skill directory containing SKILL.md where the Agent Skills client can discover it, then use a request such as “Investigate the GPU node disruption in project PROJECT_ID, location LOCATION, cluster CLUSTER_NAME, at TIMESTAMP.” Real incident investigations require project_id, location, cluster_name, and timestamp; the skill should request missing values before diagnosing.

FAQ

Does this skill have a usage fee?
The supplied source does not provide pricing information for the skill.
Can an investigation start without project_id, location, cluster_name, or timestamp?
For a real incident, the skill requires all four values first. They may be skipped only for a reusable generic runbook or a complete static telemetry or log dump.
What if the maintenance label, PromQL, and logs are all negative?
Conclude that Compute Engine host maintenance did not cause the disruption and investigate application-level causes such as OOMKill, CUDA runtime errors, or resource limits.
Should workloads tolerate the impending-node-termination:NoSchedule taint?
No. The taint indicates that GKE has cordoned the node to prevent new Pods from being scheduled there.

More skills from this repository

All from google/skills

Automation & Ops ✓ Google · Official

GKE Observability Configuration

Configure GKE logging, monitoring, and Prometheus metrics.

Automation & Ops ✓ Google · Official

GKE AI Inference Deployment Assistant

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

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

AI Workload Migration to GKE Inference

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

Automation & Ops ✓ Google · Official

GKE Cluster Creation Advisor

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

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 Enterprise RAG Search Architect

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

Automation & Ops ✓ Google · Official

GKE Cost Optimization

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

Automation & Ops ✓ Google · Official

GKE Service Networking

Configure secure GKE traffic routing, load balancing, edge protection, and private service connectivity.

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.

Dev & Engineering ✓ Google · Official

Google Agents CLI Agent Development Guide

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

Automation & Ops ✓ Google · Official

GKE Workload Reliability Guide

Reduce GKE workload disruption with high-availability configuration.

Automation & Ops ✓ Google · Official

Google Cloud Monitoring Metric Finder

Discover and filter relevant monitoring metrics for GCP services.

Automation & Ops ✓ Google · Official

Google Cloud Foundation Builder

Deploys a secure enterprise landing-zone foundation for a Google Cloud organization.

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 Cost Intelligence

Analyze GKE costs across clusters and workloads by combining BigQuery billing exports with live utilization metrics.

Automation & Ops ✓ Google · Official

GKE Production Readiness Review

Assess whether GKE clusters and workloads are ready for production.

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 Workload Security

Audit and harden workload-level security controls for GKE applications and namespaces.

Related skills