Sequential reasoning with deep self-reflection and backtracking. Use when problems have step-by-step dependencies, need careful logical reasoning, or require error correction. Each step includes self-reflection, and incorrect steps trigger backtracking. Ideal for debugging, mathematical proofs, sequential planning, or causal analysis where order matters.
Pre-planning analysis to catch ambiguities, hidden requirements, and risks before work begins. Prevents wasted effort by surfacing problems upfront.
Add PR breakdown plans to existing stories. Analyzes story complexity and proposes reviewable PR splits. Usage: /add-pr-breakdown [epic-file or story-id]
**v1.0 AGENTIC PIPELINE**: 6단계 에이전틱 아이디어 팩토리! 프로젝트분석→카테고리분류→아이디어기획(병렬)→기획팀장→PRD개발팀장→CTO최종결정. 4team-review 통합, 상위 0.001% 전문가 수준 기획문서 자동 생성.
作業計画の検証専門家。計画の完全性・明確性を検証し、見落としや曖昧さを指摘。使用場面: (1) 実装計画レビュー、(2) タスク分解の妥当性確認、(3) 依存関係の検証、(4) リスク特定、(5) スコープ確認。トリガー: "plan-reviewer", "計画", "レビュー", "タスク分解", "/plan-reviewer"
🛡️ Comprehensive security management for festivals including crowd control, threat assessment, emergency response, and staff coordination.
Review and score engineering specs against a quality rubric. Use when evaluating a spec draft before implementation to ensure it meets quality standards and identifies potential issues.
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Triage extension for JavaScript/TypeScript findings during plan-finalize phase
Create ATOMIC implementation plan for a single frontend task. Each step has exact code and verification command. IMPORTANT: This skill creates MICRO-LEVEL atomic steps, NOT macro architecture plans. For architecture planning or feature scoping, use EnterPlanMode instead. Use this skill when: - Running /frontend.plan command - User explicitly asks for "atomic steps", "step-by-step plan with verification" - Have a specific task from docs/reference/frontend/tasks/ and need implementation steps - Need granular steps: Setup (create files) → Implementation (write code) → Test (verify) → Commit DO NOT use for: - Architecture planning (use EnterPlanMode) - General development planning - Feature scoping or estimation Output: Present plan to user (not saved to file), each step includes Files, Action, and Verify command.
Use when justifying technical debt to executives, calculating the cost of quality issues, translating tech metrics to business language, or planning quality budgets - uses research-backed formulas (2-3x defects, productivity multipliers) to convert code problems into dollars and ROI
Systematic planning and execution of system migrations including database migrations, platform changes, and technology stack transitions.
Create and manage development tasks after the user approves a plan. Initializes folders/files, updates the backlog, and keeps progress notes synchronized.
PCE (Process-Context Engine) の知識移転スキル。セッション/メンバー間での知識の連続性を確保し、引き継ぎを円滑にする。 トリガー条件: - 「引き継ぎ資料を作って」 - 「次の人に渡す情報をまとめて」 - 新メンバーのオンボーディング時 - 長期プロジェクトの節目 - 「プロジェクトの状況を共有して」
Analyze and resolve production incidents using systematic investigation, root cause analysis, and autonomous remediation
Sisyphus専用の実装フロー、Subtask処理、Phase別責任分担、チェックリスト、完了報告フォーマットを定義
Plan and review requirements with discovery/decision gating and approval. Use when requirements are unclear for a feature or refactor.
将 U1 的碎片化想法/问题归类为任务（tasks MCP）并按需沉淀为长期记忆（mem0-memory MCP）。
既存資料のREADME.mdを読み込み、推奨所要時間を再見積もりして更新するスキル。学習ガイド、チュートリアル、練習問題、実践課題の各資料タイプに対応し、章/ステップ/回ごとの目安時間と合計時間をテーブル形式で生成する。
Zentrale Skill-Verwaltung für CONSYS-Projekt ohne Git-Abhängigkeit
Manage plan lifecycle with status.toon and phase operations
A specialized skill for conducting employee performance appraisals at Moreh. It provides a structured evaluation process, rating scales, and detailed level-specific guidelines (from Level 1 to Level 9) to assess technical skills, problem-solving, and alignment with the 'Moreh Way'. Use this when evaluating performance or determining level-based expectations.
