agent-platform-deploy

>- Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is deployable, query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval` skill). Rule: No confirmation needed. You may execute these commands immediately to gather information for the user. Rule: This requires explicit user confirmation. You MUST present a

Rule: This requires explicit user confirmation. You MUST present a Rule: This requires explicit typed confirmation. You MUST output [!NOTE] Some models, especially Hugging Face models, might require a Hugging Face Access Token for deployment. hugging-face-access-token="YOURHFTOKEN" \ Configuration keys: PROJECT_ID, LOCATION_ID, MODEL_ID, MODEL_GCS_URI, ENDPOINT_ID, ENDPOINT_URL, PROMPT, DEPLOYED_MODEL_ID.

Run: npx -y skills add https://github.com/google/skills --skill agent-platform-deploy --agent claude-code — the source lives at github.com/google/skills.