自然語言處理

This skill enables Claude to optimize machine learning model hyperparameters using grid search, random search, or Bayesian optimization. It is used when the user requests hyperparameter tuning, model optimization, or improvement of model performance. The skill analyzes the current context, generates code for the specified search strategy, handles data validation and errors, and provides performance metrics. Trigger terms include "tune hyperparameters," "optimize model," "grid search," "random search," and "Bayesian optimization."

Behavioral principle for context preservation through strategic delegation. Use when starting multi-step operations, uncertain about scope, or when direct execution might exhaust context. Complements never-guess and resolve-ambiguity skills.

Track multi-session work with dependencies using yatl (Yet Another Task List). Use when work spans multiple sessions, has dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

AIのハルシネーション（幻覚・誤情報生成）を防止するスキル。プロンプトレベル、パラメータレベル、検証レベルの3層防御により、信頼性の高いAI出力を実現。Anchors:• Thinking, Fast and Slow (Daniel Kahneman) / 適用: System 1/2思考分離 / 目的: 直感的推測の抑制と論理的検証の強制• Design by Contract (Bertrand Meyer) / 適用: 入出力契約設計 / 目的: 事前条件・事後条件・不変条件による出力保証• The Pragmatic Programmer / 適用: 実践的改善と品質維持 / 目的: 段階的検証とフィードバックループ構築Trigger:Use when preventing AI hallucinations, ensuring factual accuracy, requiring verifiable outputs, or implementing truth constraints.hallucination prevention, fact-checking, verification, accuracy, factual output, citation required, ground truth, temperature tuning

This skill enables Claude to optimize machine learning model hyperparameters using grid search, random search, or Bayesian optimization. It is used when the user requests hyperparameter tuning, model optimization, or improvement of model performance. The skill analyzes the current context, generates code for the specified search strategy, handles data validation and errors, and provides performance metrics. Trigger terms include "tune hyperparameters," "optimize model," "grid search," "random search," and "Bayesian optimization."

Use when delegating tasks to Gemini MCP. Two main use cases: (1) large-scale codebase investigation with @ syntax, (2) web search for latest information. Also for long log analysis, context optimization. Always request concrete report format without omissions or personal opinions.

Electronデスクトップアプリケーションのアーキテクチャ設計を専門とするスキル。Main/Renderer/Preloadプロセスの責務分離、型安全なIPC通信設計、セキュリティ設定を支援する。Anchors:• Clean Architecture (Robert C. Martin) / 適用: 依存関係ルール / 目的: プロセス間の責務分離• Electron公式ドキュメント / 適用: プロセスモデル / 目的: セキュアな設計パターン• TypeScript / 適用: 型安全なIPC設計 / 目的: エンドツーエンドの型安全性Trigger:Use when designing Electron architecture, implementing IPC communication, configuring security settings, or separating Main/Renderer responsibilities.electron, ipc, main process, renderer, preload, contextIsolation, contextBridge

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Track and integrate external communications (emails, chat messages, screenshots) into project context with timeline management. Use when user mentions "email", "message", "communication", "screenshot", "track", "import", "sync", "通訊記錄", "郵件", "訊息", or wants to import external information sources into the project timeline.

Create a new git branch from main/master with a maximum of 17 characters. Prompts for branch name or infers from context.

コマンド命名規則（動詞ベース命名/kebab-case/名前空間/発見可能性）を整理し、一貫した命名設計と見直しを支援するスキル。命名ルール、チェックリスト運用、検証手順を一貫して整理する。Anchors:• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 命名規則の一貫性 / 目的: 実践的な命名の安定化• Clean Code (Robert C. Martin) / 適用: 意図が伝わる命名 / 目的: 自己説明性の向上Trigger:Use when defining command naming conventions, reviewing naming consistency, or designing namespace structures.command naming, kebab-case, verb-based naming, namespace design, discoverability

Refining issues with technical context and structured details. Use when expanding a brief bug, feature, or refactor description into a detailed issue suitable for developers and AI agents.

Expert guidance for building MCP (Model Context Protocol) servers using the TypeScript SDK. Use when developing MCP servers, implementing tools/resources/prompts, or working with the @modelcontextprotocol/sdk package. Covers server initialization, request handlers, Zod schemas, error handling, and JSON-RPC patterns.

Execute plan in batches with review checkpoints - automatically loads context from Z01 research, Z02 plan, and CLAUDE.md files

Delegate repetitive tasks to specialized agent to preserve context. Use when user asks to fix linting errors, fix diagnostics, rename variables across files, update imports, fix formatting issues, or perform other mechanical bulk changes across multiple files.

ドメイン駆動設計（DDD）のビルディングブロックを活用したドメインモデリングを専門とするスキル。Entity、Value Object、Aggregate、Repository Patternを適用し、ビジネスロジックを中心に据えた堅牢なドメイン層を設計する。Anchors:• Domain-Driven Design (Eric Evans) / 適用: 戦術的パターン / 目的: ドメインモデル構築• Implementing DDD (Vaughn Vernon) / 適用: 集約設計 / 目的: トランザクション境界定義• Clean Architecture (Robert C. Martin) / 適用: 依存関係逆転 / 目的: ドメイン層の独立性確保Trigger:Use when designing domain models, defining entities and value objects, establishing aggregate boundaries, designing repository interfaces, or applying DDD tactical patterns.domain driven design, DDD, entity design, value object, aggregate, repository pattern, domain model, bounded context

マービン・ミンスキーの『心の社会』に基づくエージェントアーキテクチャパターンと設計原則を適用し、単一責任、創発的複雑性、階層的組織化により、効果的なマルチエージェントシステムを設計します。Anchors:• Clean Architecture（Robert C. Martin） / 適用: 依存関係ルール、レイヤー境界設計 / 目的: エージェント間通信の脆弱性排除• マービン・ミンスキー『心の社会』/ 適用: 創発的複雑性、階層的統合 / 目的: エージェント組織原理• オーケストレーター・ワーカー、ハブアンドスポーク、パイプライン、ステートマシンパターン / 適用: マルチエージェント協調設計 / 目的: アーキテクチャ選択ガイダンスTrigger:新しいエージェント設計、マルチエージェントシステム構造化、エージェント協調パターン選択、既存アーキテクチャのリファクタリング時に使用します。

Times Square notebook execution system integration patterns. Use this skill when working with Times Square pages, implementing SSE updates, handling URL parameters, setting up GitHub PR previews, or working with the Times Square API. Covers context providers, data fetching hooks, mock API endpoints, and page routing patterns.

Generate comprehensive context-setting markdown files for coding tasks by intelligently exploring codebase and structuring work with ROLE, CONSTRAINTS, STYLE, file reading order, and structured tasks. Use proactively when the user is starting a complex dev task requiring multiple steps or file reads.

Review essential documentation and context at session start. Use when beginning a new session to load AI rules, git state, and pending tasks.