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.
- 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 (