القائمة
Deploy or redeploy an inference model on the cluster. Use when asked to deploy, update, or restart a model.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Run the full integration test suite
Resume from last checkpoint — show progress, cluster state, next actions
Deploy Kaizen components with safety checks and validation
Development workflow for Kaizen - branching, commits, testing
Launch autonomous overnight build session with Ralph Wiggum
Emergency rollback for Kaizen deployments
| name | deploy-model |
| description | Deploy or redeploy an inference model on the cluster. Use when asked to deploy, update, or restart a model. |
| disable-model-invocation | true |
| allowed-tools | Bash, Read, Edit |
Deploy or manage inference models on Kaizen. Argument should be one of: reasoning, embedding, heavy, or a manifest path.
kubectl get nodeskubectl describe node <node> | grep -A3 nvidia.com/gpukubectl get pods -n inferencek8s/apps/inference/ — All inference deploymentsk8s/apps/inference/sglang-core.yaml — Heavy model (Qwen2.5-72B, TP=4, CORE)kubectl apply --dry-run=client -f <manifest>kubectl apply -f <manifest>kubectl rollout status -n inference deploy/<name> --timeout=300scurl http://10.10.10.10:<port>/v1/modelskubectl rollout restart -n inference deploy/<name>
kubectl rollout status -n inference deploy/<name>