google-cloud-solution-guided-gke-ai-migration

GKE AI migration is an agent skill that guides the move of existing AI inference workloads, such as those running on Cloud Run, the Gemini API or Gemini Enterprise Agent Platform, to self-hosted inference on Google Kubernetes Engine. The agent acts as an interactive architect and works through a structured four-phase process: discovering requirements, designing a Google Cloud-native solution, carrying out the implementation with the gcloud and kubectl command-line tools, and validating the deployment. The skill is specifically for manual, architect-guided migration. Automated migration belongs to the Gemini Cloud Assist MCP server, and the skill says how it routes between the two. If you ask to use Cloud Assist or MCP automation for the migration, the skill stops the manual workflow, explains what the MCP server can do, including automated analysis and direct resource changes, and links the MCP documentation and a codelab for setting it up. If you mention MCP only in passing or decline it, the skill carries on with the manual steps. The skill is intended for teams who want to run open models on their own GKE cluster and want a guided path that they can follow and review step by step. It is published by Google on skills.sh under the google skills repository, with about 4.3K installs. The skills.sh listing shows Gen Agent Trust Hub and Socket passing, with Snyk showing Warn.…