Create a Partnership & BD Execution Pack (partner thesis, target list + scoring, outreach kit, scalable offer + negotiation guardrails, and launch plan). Use for partnerships, business development...
Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns are...
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
aiwコマンドを活用して複数AIエンジンによる並列実装・評価・採用を行うスペシャリスト。複雑な実装で複数アプローチを比較したい時、AIエンジン間の品質比較、高信頼性が求められる実装に使用。
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Diagnose and improve marketplace liquidity (match rate/fill rate, time-to-match, reliability) by segment. Produces a Marketplace Liquidity Management Pack: liquidity definition + metric tree,...
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training demos...
Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an MVP", "start new...
Produce a Platform & Infrastructure Improvement Pack (shared capabilities plan, reliability/performance/privacy targets, scaling triggers, analytics + discoverability decisions, execution...
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
非推奨ライブラリの検出、ネイティブAPI置換提案、新技術のPoC作成。技術スタック刷新、モダナイゼーション、レガシーコード更新が必要な時に使用。
EXPLAIN ANALYZE分析、クエリ実行計画最適化、インデックス推奨、スロークエリ検出・修正。DBパフォーマンス改善、クエリ最適化が必要な時に使用。Schemaのスキーマ設計を補完。
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
デザイントークンの定義・管理、既存コードへのトークン適用、Design System構築。トークン体系の設計、余白・色・タイポグラフィの統一、ダークモード対応を担当。デザイントークン設計、UI一貫性が必要な時に使用。
Shared TypeScript best practices for Designer and Electron subsystems.
Create or refine well-formed backlog work items for AI-assisted development. Use when drafting a new item, refining an underspecified task, splitting a large task, or validating readiness before...
不要ファイル検出・未使用コード特定・孤立ファイル発見・安全な削除提案。リポジトリの整理整頓、デッドコード除去、プロジェクトのクリーンアップが必要な時に使用。
GitHub PR情報の収集・レポート生成・作業報告書作成。ghコマンドでPR情報を取得し、週報・月報・リリースノートを自動生成。作業報告、PR分析が必要な時に使用。
Manage imposter syndrome at work and produce an Imposter Syndrome Management Pack (trigger & pattern map, reframes, evidence bank, experiment plan, support scripts, maintenance routine). Use for...
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.