CQRS (Command Query Responsibility Segregation) patterns with MediatR for .NET Clean Architecture projects. Covers commands, queries, handlers, validation, and pipeline behaviors.
Expert in groups, rings, fields, and algebraic structures with applications to cryptography and number theory
Rustのエラーハンドリング方針に関する依頼で使う。回復可能性を基準にResultとpanicを使い分け、境界で適切にエラー型を設計・変換する。
命名・設計レビューにおいて、Manager / Util / Facade / Service / Runtime / Engine など意味が一意に定まらないサフィックスの使用を検出し、責務・境界・契約が明確に伝わる命名へ導くためのスキル。
Comprehensive system architecture design and implementation workflow that orchestrates expert analysis, technical decision-making, and architectural pattern selection using the integrated toolset. Handles everything from initial system analysis to implementation-ready technical specifications.
Build deterministic IoC containers with proper lifecycle management, scoping, and disposal patterns. Use when implementing DI containers, managing service lifetimes, or designing runtime systems.
Spring Boot and Java best practices. Use when developing REST APIs, services, repositories, or any Java code. Applies DDD architecture, transaction management, and code style conventions.
Automated detection and enforcement of design system guidelines including dark mode, colors, spacing, typography, focus states, and accessibility compliance
Common Tokio patterns and idioms for async programming. Use when implementing worker pools, request-response patterns, pub/sub, timeouts, retries, or graceful shutdown.
Essential principle for writing clear, testable, maintainable code - separate decisions from effects
Monorepo architecture patterns for AI context control. Covers structure design, shared modules, and CLAUDE.md hierarchy. Triggers: monorepo, context control, shared modules, 모노레포, モノレポ, 单仓库
Advanced concurrency patterns for Tokio including fan-out/fan-in, pipeline processing, rate limiting, and coordinated shutdown. Use when building high-concurrency async systems.
Architectural patterns and design principles for scalable, maintainable systems. Use when designing systems, refactoring architecture, or choosing patterns.
Production-ready code standards following CLAUDE Framework with TDD, security, and quality requirements
A reasoning pattern for diagnosing and fixing bugs that span multiple abstraction layers in complex systems.
Code implementation patterns and best practices learned from real mistakes. Covers file I/O safety (locking, atomic writes), data persistence, and validation. Use for file-based state, shared resources, concurrent access. NOT for auto-learning patterns (see learned-patterns skill).
Use when encountering failures - assess severity, preserve evidence, execute rollback decision tree, and verify post-recovery state
Use when managing agent state transitions (START/INIT/IMPLEMENT/TEST/COMPLETE), triggering context compression at 80% capacity, or handling session lifecycle. Load at session start, on state change, or when context exceeds threshold. Core skill for single-orchestrator architecture.
Expert code reviewer focusing on quality, maintainability, performance, and best practices
Skill for defining terminology and data structures used throughout the project. Covers domain terminology, entities, relationships, and schema design. Triggers: schema, terminology, data model, entity, 스키마, 用語, データモデル, 数据模型
Skill for building platform-independent design systems. Develops consistent component libraries for all UI frameworks. Triggers: design system, component library, design tokens, shadcn, 디자인 시스템, デザインシステム, 设计系统
JaegerとTempoによる分散トレーシングを実装して、マイクロサービス間のリクエストを追跡し、パフォーマンスボトルネックを特定します。マイクロサービスのデバッグ、リクエストフローの分析、分散システムの可観測性実装時に使用します。
Microservices design expert covering service decomposition, communication patterns, and distributed systems
Design modular libraries with clear package boundaries, feature-first organization, and clean API surfaces. Use when structuring monorepos, defining module boundaries, or designing library APIs.
