메뉴
Design phase playbook — propose target architecture on AKS Automatic.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
ACR integration for AKS Automatic. Teaches attaching an ACR, image reference conventions (digest pinning, no :latest), and pull-secret-free authentication via the managed identity.
Writing idiomatic, safe, and reviewable Bicep templates for Azure resources.
Non-blocking cluster status peek — run at the end of Phases 3, 4, 5 to check AKS provisioning progress without hanging.
Voice, tone, and interaction patterns for Kickstart agents.
Configure Infrastructure phase playbook — launch the dedicated Kickstart cluster-setup view, which collects and creates the Azure resources (subscription, resource group, AKS Automatic cluster, ACR) and hands the results back to the chat.
Deploy phase playbook — build, push, apply with Azure CLI and kubectl.
| name | kickstart-design |
| description | Design phase playbook — propose target architecture on AKS Automatic. |
| disable-model-invocation | true |
Propose a target deployment architecture and get user approval.
Present a summary covering:
Container strategy: Single or multi-container. Multi-stage builds. Pin base images to specific versions.
AKS Automatic: Managed Kubernetes with Node Auto-Provisioning (Karpenter). Auto-upgrades (default: patch channel). No node pools to manage. Define PodDisruptionBudget for stateful workloads.
Networking: Gateway API with HTTPRoute (not Ingress). GatewayClass: azure-application-lb is pre-installed. Cilium network policies enabled by default. Clusters are private by default (API server via private endpoint).
Identity: Azure Workload Identity — federated credentials, no secrets in pods. Managed identity for Azure services (Key Vault, Storage). Prefer managed identity over service principals.
Registry: ACR attached to AKS (no pull secrets). Geo-replication if multi-region.
Monitoring: Azure Monitor managed Prometheus + Grafana (auto-enabled). Container Insights for logs. Alert on CPU >80%, pod restarts >5, PVC >85%.
| Question | Answer |
|---|---|
| "Do I need Kubernetes knowledge?" | No. AKS Automatic manages nodes, scaling, upgrades. |
| "How much will this cost?" | Explain the cost drivers: AKS Automatic control-plane fee + node compute (pay-as-you-go per vCPU/memory, scaled by Karpenter) + ACR tier + egress. Offer a rough estimate for their expected load. |
| "Can I use existing CI/CD?" | Yes, but recommend GitHub Actions with OIDC. |
User approves the architecture via vscode_askQuestions. Announce: "Architecture approved — moving to Generate."
