メニュー
Use when building or debugging LangGraph multi-agent systems - eval-first execution, task decomposition, model routing by complexity, and cost discipline
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Debug frontend vanilla JS issues - console errors, rendering bugs, SPA navigation, WebSocket
Automates the process of setting up the first admin user or adding new admins via the bootstrap endpoint. Includes a Python script for easy execution.
Push to remote and wait for CI to pass. If CI fails, read logs, fix bugs, and re-push. Repeat until green.
Use when AI agent modifies API routes or backend logic - catch systematic blind spots where the same model writes and reviews code
Use when making or recording significant architectural decisions - capture context, alternatives, and rationale as structured ADRs
Use when you have a written implementation plan to execute with review checkpoints between tasks
| name | agentic-engineering |
| description | Use when building or debugging LangGraph multi-agent systems - eval-first execution, task decomposition, model routing by complexity, and cost discipline |
For engineering workflows where AI agents perform most implementation work and humans enforce quality.
| Task Complexity | Model Tier | Examples |
|---|---|---|
| Classification, boilerplate, narrow edits | Fast/cheap | Tag routing, format conversion |
| Implementation and refactors | Standard | API endpoints, DB queries, tests |
| Architecture, root-cause, multi-file invariants | Powerful | ORM design, security review, debugging |
Prioritize (don't waste cycles on style):
Track per task: model, token estimate, retries, wall-clock, success/failure. Escalate model tier only when lower tier fails with clear reasoning gap.
