stacked PRの下位PRがマージされた後に上位branchをrestack(rebase/cherry-pick再構成)する際に使用。「restackして」「上位PRを更新して」「restack after merge」「PRのbaseを更新」「スタックを整理」という依頼でトリガーする。対象sliceの特定→rebase→変更ファイル確認と代表テスト実行→force-with-leaseでpush→PR base更新→auto-merge判定の順で進める。
kiro-validate-design
Interactive technical design quality review and validation
含まれるファイル(3)
- SKILL.md4.9 KB
- LICENSE.txt1.0 KB
- rules/design-review.md4.3 KB
SKILL.md(原文)
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Technical Design Validation
<background_information>
- Mission: Conduct interactive quality review of technical design to ensure readiness for implementation
- Success Criteria:
- Critical issues identified (maximum 3 most important concerns)
- Balanced assessment with strengths recognized
- Clear GO/NO-GO decision with rationale
- Actionable feedback for improvements if needed </background_information>
Execution Steps
- Gather Context:
- Read
docs/specs/$1/spec.jsonfor language and metadata - Read
docs/specs/$1/requirements.mdfor requirements - Read
docs/specs/$1/design.mdfor design document - Core steering context:
product.md,tech.md,structure.md - Additional steering files only when directly relevant to architecture boundaries, integrations, runtime prerequisites, domain rules, security/performance constraints, or team conventions that affect implementation readiness
- Relevant local agent skills or playbooks only when they clearly match the feature's host environment or use case and provide review-relevant context
- Read
Parallel Research
The following research areas are independent and can be executed in parallel:
- Context & rules loading: Spec documents, core steering, task-relevant extra steering, relevant local agent skills/playbooks, and
rules/design-review.mdfrom this skill's directory for review criteria - Codebase pattern survey: Gather existing architecture patterns, naming conventions, and component structure from the codebase to use as reference during review
If multi-agent is enabled, spawn sub-agents for each area above. Otherwise execute sequentially.
After all parallel research completes, synthesize findings for review.
-
Execute Design Review:
- Reference conversation history when available: leverage prior requirements discussion and user's stated design intent
- Follow design-review.md process: Analysis → Critical Issues → Strengths → GO/NO-GO
- Limit to 3 most important concerns
- Engage interactively with user — ask clarifying questions, propose alternatives
- Use language specified in spec.json for output
-
Decision and Next Steps:
- Clear GO/NO-GO decision with rationale
- Provide specific actionable next steps (see Next Phase below)
Important Constraints
- Quality assurance, not perfection seeking: Accept acceptable risk
- Critical focus only: Maximum 3 issues, only those significantly impacting success
- Conversation-aware: Leverage discussion history for requirements context and user intent when available
- Interactive approach: Engage in dialogue, ask clarifying questions, propose alternatives
- Balanced assessment: Recognize both strengths and weaknesses
- Actionable feedback: All suggestions must be implementable
- Context Discipline: Start with core steering and expand only with review-relevant steering or use-case-aligned local agent skills/playbooks </instructions>
Tool Guidance
- Read first: Load spec, core steering, relevant local playbooks/agent skills, and rules before review
- Grep if needed: Search codebase for pattern validation or integration checks
- Interactive: Engage with user throughout the review process
Output Description
Provide output in the language specified in spec.json with:
- Review Summary: Brief overview (2-3 sentences) of design quality and readiness
- Critical Issues: Maximum 3, following design-review.md format
- Design Strengths: 1-2 positive aspects
- Final Assessment: GO/NO-GO decision with rationale and next steps
Format Requirements:
- Use Markdown headings for clarity
- Follow design-review.md output format
- Keep summary concise
Safety & Fallback
Error Scenarios
- Missing Design: If design.md doesn't exist, stop with message: "Run
/kiro-spec-design $1first to generate design document" - Design Not Generated: If design phase not marked as generated in spec.json, warn but proceed with review
- Empty Steering Directory: Warn user that project context is missing and may affect review quality
- Language Undefined: Default to English (
en) if spec.json doesn't specify language
Next Phase: Task Generation
If Design Passes Validation (GO Decision):
- Review feedback and apply changes if needed
- Run
/kiro-spec-tasks $1to generate implementation tasks - Or
/kiro-spec-tasks $1 -yto auto-approve and proceed directly
If Design Needs Revision (NO-GO Decision):
- Address critical issues identified
- Re-run
/kiro-spec-design $1with improvements - Re-validate with
/kiro-validate-design $1
Note: Design validation is recommended but optional. Quality review helps catch issues early.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
cc-sdd実装用統合ブランチのコミット群(ベースブランチとの差分)をreview slice単位のstacked PRに再構成する際に使用。「review sliceに分割」「stacked PRを作成」「PRをスタックして」「レビュー用にPRを分けて」「review slice stack」という依頼でトリガーする。dry-run(既定)でslice計画を提示し、apply指示で実際にブランチ・PRを作成する。
CI環境で安定動作するPythonテスト(特にstructlogのログ検証)を書く際に使用。「CIで失敗する」「capture_logsが不安定」「ログアサーションがCIだけ落ちる」「caplogフォールバック」「ANSI混入」「xdistでログが取れない」という課題で起動。capture_logs→caplogフォールバック→ANSI正規化→アサーション設計の流れで堅牢なテストを書く。
GitHub Issueを作成してGitHubに投稿するスキル。「Issueを作成」「Issue作成」「Issueにして」「Issueとして投稿」「GitHubにIssue」「create issue」「open issue」「バグ報告」「機能追加をIssueに」「改善提案をIssueに」などの依頼でトリガーする。コンテキスト収集→Issue本文生成→ラベル存在確認・作成→gh issue create投稿の流れでIssueを作成する。
Dockerベースのアプリケーションのデプロイメント手順書(Markdown)を作成するスキル。「デプロイ手順書」「デプロイメント手順」「deployment guide」「本番環境への配置手順」「サーバーへの配置手順」などの依頼でトリガーする。Docker Composeビルド→イメージ転送→サーバー配置→設定→動作確認→cron設定の流れで手順書を生成する。
タスク完了後にPCを休止状態にする。Use when: ユーザーが「休止」「hibernate」「タスク完了後に休止状態」「作業後にPCをスリープ/休止」と明示的に指示した場合のみ。正常終了時だけでなく、エラーや未解決事項が残っていても、明示指示があれば最後に休止へ移行する。Windows only.