PM2エコシステム設定の設計と最適化を専門とするスキル。 Alexandre Strzelewiczの思想に基づき、ecosystem.config.js の 構成、実行モード選択、環境設定、監視設定を体系的に設計します。 📖 参照書籍: - 『The Pragmatic Programmer』(Andrew Hunt, David Thomas): 実践的改善 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/config-structure-guide.md`: ecosystem.config.js構造(apps配列、必須/推奨オプション、共通設定) - `resources/environment-management.md`: env階層設計、env_production分離、機密情報外部化パターン - `resources/execution-modes.md`: fork vs cluster選択基準、instances数決定、負荷タイプ別最適化 - `resources/legacy-skill.md`: 旧SKILL.mdの全文 - `scripts/log_usage.mjs`: 使用記録・自動評価スクリプト - `scripts/validate-ecosystem.mjs`: ecosystem.config.js構文検証と設定項目の整合性チェック - `scripts/validate-skill.mjs`: スキル構造検証スクリプト - `templates/ecosystem.config.template.js`: PM2設定ファイルテンプレート(実行モード、再起動戦略、環境変数含む) Use proactively when designing PM2 configurations, optimizing.
Automatically detect and prevent common Wheels framework errors before code is generated. This skill activates during ANY Wheels code generation (models, controllers, views, migrations) to validate patterns and prevent known issues. Scans for mixed arguments, query/array confusion, non-existent helpers, and database-specific SQL.
Unified agent management from selection through completion - spawning, execution, output processing. Use when selecting agents for tasks, spawning agents with dependency validation, processing agent outputs, or tracking agent lifecycle events with audit trails.
RAN system integration with microservices architecture, cognitive consciousness, and intelligent orchestration for seamless network integration. Use when integrating RAN systems, implementing microservices architecture, designing service orchestration, or enabling intelligent network integration.
SOLID原則のインターフェース分離原則(ISP)を専門とするスキル。 Robert C. Martinの『アジャイルソフトウェア開発の奥義』に基づき、 クライアントが使用しないメソッドへの依存を強制しない、 📖 参照書籍: - 『The Pragmatic Programmer』(Andrew Hunt, David Thomas): 実践的改善 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/fat-interface-detection.md`: 空実装/例外スロー/条件付き実装による肥大化検出手法 - `resources/interface-composition.md`: allOf/extends/mixinによる小インターフェース組み合わせパターン - `resources/isp-principles.md`: クライアント固有インターフェース分離とSOLID準拠設計 - `resources/legacy-skill.md`: 旧SKILL.mdの全文 - `resources/role-interface-design.md`: 役割ベース(IValidatable/IRetryable等)インターフェース設計手法 - `scripts/analyze-interface.mjs`: インターフェース凝集性とISP違反の自動検出 - `scripts/log_usage.mjs`: 使用記録・自動評価スクリプト - `scripts/validate-skill.mjs`: スキル構造検証スクリプト - `templates/segregated-interface-template.md`: コア+拡張インターフェース分離設計テンプレート - `resources/requirements-index.md`: 要求仕様の索引(docs/00-requirements と同期) Use proactively when hand
Automated service deployment with validation, templating, and verification - use when deploying new services, updating existing deployments, or troubleshooting deployment issues
Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.
Analyze design docs, calculate velocity from recent work, and create realistic sprint plans with day-by-day breakdowns. Use when user asks to "plan sprint", "create sprint plan", or wants to estimate development timeline.
Implements tRPC-based communication between VS Code extension host and React webviews. Use when creating new webview procedures (queries, mutations, subscriptions), adding a new webview router, wiring up a webview controller, using the tRPC client from React components, applying telemetry middleware (trpcToTelemetry), or supporting AbortSignal-based cancellation in webview operations.
MCPサーバーと外部システム間の統合パターンに関する専門知識。 同期・非同期通信、イベント駆動アーキテクチャ、データ同期パターンの設計指針を提供します。 📚 リソース参照: このスキルには以下のリソースが含まれています。 必要に応じて該当するリソースを参照してください: - `.claude/skills/integration-patterns/resources/async-patterns.md`: Message Queue/Pub-Sub/Sagaパターンの詳細と実装ガイド - `.claude/skills/integration-patterns/resources/event-driven-guide.md`: Event Sourcing/CQRS/Webhookによるイベント駆動設計 - `.claude/skills/integration-patterns/resources/sync-patterns.md`: Request-Response/Aggregator/Gatewayパターンの詳細 - `.claude/skills/integration-patterns/scripts/review-integration-design.mjs`: 統合設計のアーキテクチャレビューと改善提案 - `.claude/skills/integration-patterns/scripts/validate-message-schema.mjs`: メッセージスキーマ定義の検証とバージョン互換性チェック - `.claude/skills/integration-patterns/templates/integration-design-template.md`: 統合パターン選択と設計ドキュメントテンプレート - `.claude/skills/integration-patterns/templates/message-schema-template.json`: イベント/メッセージスキーマ定義テンプレート 使用タイミング: - MCPサーバーと外部システムの連携設計時 - 非同期処理パターンの設計時 - イベント駆動統合の設計時 - マルチサービス連携の設計時
Research latest library documentation, industry best practices, and technical knowledge to automatically generate project-level skills. Use when asked to: (1) Research and create a skill for a library/framework, (2) Build a skill based on architectural patterns, (3) Generate skills from technical research, (4) Create domain-specific technical skills from web research, or (5) Any request combining research with skill creation.
Initialize new projects using this template structure. LOAD THIS SKILL WHEN: User says "新專案", "初始化", "create project", "建立專案", "bootstrap" | starting fresh project | cloning template. CAPABILITIES: Copy directory structure, reset Git, configure project name, setup Memory Bank, interactive configuration.
Understand the already-done project folder structure, archtecture, file patterns, and similar, in order to apply better solutions and file organizations. Use when you need to understand the project archtecture, and file/folder patterns and conventions.
Guide for implementing Google Gemini API audio capabilities - analyze audio with transcription, summarization, and understanding (up to 9.5 hours), plus generate speech with controllable TTS. Use when processing audio files, creating transcripts, analyzing speech/music/sounds, or generating natural speech from text.
Convert between Markdown, DOCX, and PDF formats bidirectionally. Handles text extraction from PDF/DOCX, markdown to document conversion. Use when converting document formats or extracting structured content from Word or PDF files.
Analiza ejercicios matemáticos tipo ICFES según 6 dimensiones oficiales (dificultad, competencia, componente, pensamiento, contenido, eje). Usa cuando tengas imagen de problema ICFES, pregunta matemática para clasificar, o necesites decidir si requiere gráficos complejos. Detecta automáticamente si el ejercicio necesita Graficador Experto para replicación visual.
Guides development of AILANG builtin functions. Use when user wants to add a builtin function, register new builtins, or understand the builtin system. Reduces development time from 7.5h to 2.5h (-67%).
Manages authentication flow for MutuaPIX (Laravel Sanctum + Next.js), handles mock mode security, and validates environment configurations
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.
Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures', 'close Python-AILANG gap', or after running evals.