Coding standards, frameworks, refactoring, and code review (16.6K skills)
依頼者と議論・対話を進める場面で必ず発火させる skill。共創を目指して、認識を小さく揃えながら、同じ抽象度・レイヤーで話すための対話の進め方を扱う。要件・設計フェーズの対話、実装中の設計判断の議論、レビュー結果の共有、複数の論点・選択肢を依頼者に渡す場面、依頼者からの指摘・反論に応答する場面、「確認したい」「議論したい」「相談したい」と問いかけたいとき、いずれも発火対象。「会話」ではなく「対話」を成立させたい全場面で効く。質問がスルーされる・訂正が続く・話題を変えられる・「そうじゃなくて」と返されるなど、噛み合っていない兆候を観測したときは軌道修正のために再度発火させる。
The English summary is being prepared. Showing the original description.
デザインツール（Figma等）やUI要件を「壊れない・拡張しやすい」実装へ翻訳するための判断軸。px写経を避け、比率・構造・制約・状態を先に設計してからUIを組み立てる。
The English summary is being prepared. Showing the original description.
設計と実装を「最小で正確」に進め、差分思考で品質と速度を両立する。設計の溶け込み（責務不明/重複/暫定対応）を防ぎ、レビュー可能な変更へ落とし込むときに使う。
The English summary is being prepared. Showing the original description.
セマンティックHTML/JSXとWAI-ARIAを「最小で正しく」適用し、キーボード操作・スクリーンリーダ・コントラスト等を満たす実装を作るための判断軸。ネイティブ要素優先、ARIAの過剰使用を避ける。
The English summary is being prepared. Showing the original description.
体験品質（動き/触感/視線誘導）を「実装可能な制約」に落とし、アクセシビリティとパフォーマンスを犠牲にせずに表現を実現する。UIの表現・アニメーション・インタラクション設計/実装の相談で使う。
The English summary is being prepared. Showing the original description.
Export Codex rollout/session JSONL as a self-contained HTML report that can be opened offline. Use when a user provides a complete session file path or Codex session ID, or asks to export a Codex session to HTML, generate a session report, or convert a rollout to HTML. Supports exact full-ID lookup in the CODEX_HOME sessions and archived_sessions directories.
The English summary is being prepared. Showing the original description.
Analyze Codex provider rollout JSONL and ego-benchmark-harness run artifacts to identify slow or failed individual tasks, tool retries, token/cost anomalies, and differences in agent execution paths. Use when users ask to analyze a Codex session or rollout, explain why a Codex task was slow or failed, inspect a Codex provider execution trace, compare Codex runs, count function_call or tool output events, or investigate agent-home/.codex/sessions.
The English summary is being prepared. Showing the original description.
Choose between deterministic GitHub API tools, local git facts, and approved gh CLI workflows in Neondeck.
The English summary is being prepared. Showing the original description.
Explain how external local agents can register completed work with Neondeck through the CLI or localhost handoff API.
The English summary is being prepared. Showing the original description.
Build revision-bound guided PR code tours. Use for /show-me, /tour, or natural requests to show, trace, or walk through a changed code path in the continuing PR reviewer.
The English summary is being prepared. Showing the original description.
修正方針を実装担当へ渡す前に、実装しない別の担当が独立した文脈で、方針の前提・変更対象の利用者・構造で解くべき問題・同じ箇所の再修正・対症療法を確かめる。変更対象のpathと方針だけを渡す。要件をユーザーと決める場合は brainstorm、選択肢の比較は deepthink。
The English summary is being prepared. Showing the original description.
Stage intended changes and create a clean git commit.
The English summary is being prepared. Showing the original description.
Investigate Symphony run failures, stalls, and retry loops.
The English summary is being prepared. Showing the original description.
Use for AI SDK for Python async-generator tools, streaming tool output, subagent tools, PartialToolCallResult events, and custom tool aggregation.
The English summary is being prepared. Showing the original description.
Use when building serverless AI SDK for Python endpoints, handling hook approvals, deferring hooks, or resuming runs across requests.
The English summary is being prepared. Showing the original description.
Use when building custom agent loops. Modify tool dispatch, history management, hooks, control flow.
The English summary is being prepared. Showing the original description.
Use for implementing custom providers in AI SDK for Python.
The English summary is being prepared. Showing the original description.
Use when adding durable execution to AI SDK for Python, building durable agent loops, or serializing messages across workflow steps.
The English summary is being prepared. Showing the original description.
Use for the subagent-as-a-tool pattern.
The English summary is being prepared. Showing the original description.
Use for AI SDK for Python basics. Configure a model, make messages, stream, declare tools, build a basic agent.
The English summary is being prepared. Showing the original description.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
The English summary is being prepared. Showing the original description.
Reqordのデータモデル（Requirement, Specification, ProjectContext, Feedback）とCLI操作ルールの共通知識ベース。
The English summary is being prepared. Showing the original description.
Reqordプラグインの環境セットアップと前提条件チェック。CLIツール・GitHub認証・プロジェクト初期化状態を確認し、証憑を記録する。
The English summary is being prepared. Showing the original description.
フィードバック運用（作成・同期・分類・リンク・クローズ・フラグ解消）。GitHub Issueの作成または既存フィードバックの取り込みワークフローを実行する。
The English summary is being prepared. Showing the original description.