gke-ai-troubleshooting-handle-disruption-gpu-tpu

Installation
SKILL.md

Handle Disruption on GPUs and TPUs Troubleshooting

🔍 Diagnostic Workflow

Step 0: Context Acquisition & Execution Trigger

  • Mandatory Context: project_id, location, cluster_name, timestamp.
  • Optional Context: node_name, workload_name, workload_namespace, nodepool_name.
  • CRITICAL EXECUTION DIRECTIVE (STRICTLY ENFORCED):
    • IF ALL 4 MANDATORY PARAMETERS ARE PRESENT: DO NOT ask the user for confirmation, DO NOT echo parameters back asking for verification, and DO NOT output a text-only plan waiting for user input. YOU MUST IMMEDIATELY INVOKE DIAGNOSTIC TOOLS (get_k8s_resource, query_prometheus, query_logs) IN YOUR VERY FIRST TURN.
    • IF ANY MANDATORY PARAMETER IS MISSING: Stop immediately and ask the user to provide ONLY the missing mandatory parameters.

Step 1: [Low Risk] Check for Upcoming Scheduled Maintenance

Installs
13
GitHub Stars
163
First Seen
Jul 1, 2026
gke-ai-troubleshooting-handle-disruption-gpu-tpu — googlecloudplatform/gke-mcp