専門AIエージェントチームを統括するオーケストレーター。要求を分解し、最小のエージェントチェーンを設計し、AUTORUNモードでは各エージェント役を内部実行して最終アウトプットまで自動進行する。複数エージェント連携が必要な時に使用。
障害発生時の初動対応、影響範囲特定、復旧手順策定、ポストモーテム作成。インシデント対応・障害復旧が必要な時に使用。コードは書かない（修正はBuilderに委譲）。
KPI定義、トラッキングイベント設計、ダッシュボード仕様作成。ノーススターメトリクス、ファネル分析、コホート分析設計。GA4/Amplitude/Mixpanel統合。メトリクス基盤が必要な時に使用。
SEO（meta/OGP/JSON-LD/見出し階層）、SMO（SNSシェア表示）、CRO（CTA改善/フォーム最適化/離脱防止）の3軸で成長を支援。検索順位向上、コンバージョン改善が必要な時に使用。
Create slash commands (reusable prompt templates). Use when building /commands, defining workflows users invoke explicitly, or setting up repeatable prompts with arguments.
Generate a structured deep research prompt. USE WHEN the user needs to research a complex topic, market, or bug deeply. Capabilities include objective clarification, tech stack validation, and...
Help users work effectively across functions. Use when someone is navigating PM-engineering relationships, resolving cross-team conflicts, building product trios, or improving handoffs between...
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered search visibility in ChatGPT, Perplexity, Google AI Overviews, and other AI search platforms.
SEO and AEO (Answer Engine Optimization) best practices including EEAT principles, structured data, and technical SEO. Use when implementing metadata, sitemaps, structured data, or optimizing...
Generate optimized instructions for Claude (Project instructions, Skills, or standalone prompts). Use when users request creating project setups, writing effective prompts, building Skills, or...
Generate optimized instructions for Claude (Project instructions, Skills, or standalone prompts). Use when users request creating project setups, writing effective prompts, building Skills, or...
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific...
AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying...
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".
Create a Delegation Pack (delegation brief, decision rights, context handoff, check-in cadence, review plan, debrief). Use for delegation, letting go, empowering reports, and avoiding micromanagement.
Create an Amazon-style PR/FAQ (future press release + FAQ) plus a backcasting launch plan to align on customer value, scope, and GTM readiness. Use for working backwards, PRFAQ / PR-FAQ, future...
Analyze user/customer feedback and produce a User Feedback Analysis Pack (source inventory, normalized feedback table, taxonomy/codebook, themes + evidence, recommendations, and feedback loop)....
Generate and evaluate startup ideas using off-the-beaten-path insights + Why-Now shift analysis. Produces a Startup Ideation Pack (opportunity theses table, scorecard, top idea brief, validation...
Plan and execute a product launch/release with speed and safety. Produces a Shipping & Launch Pack (release brief, rollout/rollback plan, product quality list, comms + enablement, monitoring plan,...