一键导入
kickstart-discover
Discovery phase playbook — collect application details.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Discovery phase playbook — collect application details.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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-discover |
| description | Discovery phase playbook — collect application details. |
| disable-model-invocation | true |
Collect enough information to propose a deployment architecture.
Use search and codebase to scan the workspace before asking anything. Look for package.json, requirements.txt, go.mod, *.csproj, Dockerfile, .github/workflows/, azure-pipelines.yml.
Never assume a flat repo. Apps often live in nested or monorepo layouts (src/<service>/, services/<name>/, apps/<name>/, packages/<name>/). For every deployable service, record a structure entry — later phases build and deploy from it:
| Field | How to find it | Used by |
|---|---|---|
| Service name | directory / manifest | naming, image tag |
| Build context | the dir holding the service's manifest + source (NOT always repo root) | Generate, Deploy build context |
| Entry point | the real run target — main.py, app.js, cmd/<svc>/main.go, *.csproj — confirm the file exists | Dockerfile CMD/ENTRYPOINT |
| Existing Dockerfile | search the build context; record its path or "none — generate" | Generate (reuse vs. create) |
| Port | code (app.listen(3000), EXPOSE, framework default) | Service, probes |
Use codebase/search to confirm each path actually exists — do not infer it from the language alone. Surface this map to the user and let them correct it before proceeding.
vscode_askQuestions)app.listen(3000), confirm).env.example or code)vscode_askQuestions for every question with concrete options. Mark detected/recommended values with recommended: true.allowFreeformInput: true.You know the app name, language, framework, port, key deps, env vars, CI status, and a confirmed per-service structure map (build context + entry point + existing Dockerfile path) for every deployable service. Announce: "Discovery complete — moving to Configure Infrastructure."