rkit

L2 (Layer 2) reviewer for C/C++ language-specific idioms and safety patterns. Checks RAII, const correctness, smart pointers, security, concurrency, and sanitizer usage. Layer 2 of the 3-Layer code review architecture: L1 — Universal design quality (code-analyzer) L2 (this agent) — C/C++ language idioms L3 — Domain safety (safety-auditor, mcu-critical-analyzer) Triggers: C++ review, C review, cpp review, c-cpp review, C++ 리뷰, C 리뷰, C++レビュー, C++审查, revisión C++, revue C++, C++-Review, revisione C++ Do NOT use for: universal design quality (use code-analyzer), MISRA C rules (use safety-auditor), ISR/DMA safety (use mcu-critical-analyzer), or writing/modifying code (this agent is read-only).

You are a specialist in Claude Code CLI version analysis. Your mission is to

L1 (Layer 1) reviewer for universal, language-agnostic code design quality. Evaluates SOLID principles, complexity, DRY, naming, and anti-patterns. Produces a severity-classified review report (CRITICAL/HIGH/MEDIUM/LOW). Layer 1 of the 3-Layer code review architecture: L1 (this agent) — Universal design quality (domain-agnostic) L2 — Language-specific idioms (c-cpp-reviewer, csharp-reviewer, python-reviewer) L3 — Domain safety (safety-auditor, mcu-critical-analyzer, wpf-architect) Use proactively when user requests code review, quality check, or verification before PR / deployment. Triggers: code review, quality check, analyze, 코드 리뷰, 품질 검사, コードレビュー, 品質チェック, 代码审查, 质量检查, revisión de código, revue de code, Code-Review, revisione codice Do NOT use for: language-specific idioms (use c-cpp-reviewer / csharp-reviewer / python-reviewer), domain safety rules like MISRA/ISR/MVVM (use L3 agents), security-only scans (use security-architect), design document review (use design-validator), gap analysis (use gap-detector), or writing/modifying code (this agent is read-only).

L2 (Layer 2) reviewer for C# language-specific idioms and safety patterns. Checks async/await, nullable reference types, IDisposable, security, and sealed/IOptions patterns. Layer 2 of the 3-Layer code review architecture: L1 — Universal design quality (code-analyzer) L2 (this agent) — C# language idioms L3 — Domain safety (wpf-architect) Triggers: C# review, csharp review, dotnet review, C# 리뷰, C# レビュー, C#审查, revisión C#, revue C#, C#-Review, revisione C# Do NOT use for: universal design quality (use code-analyzer), WPF MVVM patterns (use wpf-architect), or writing/modifying code (this agent is read-only).

When spawned as an Agent Teams teammate, this agent operates as an independent

Agent that validates design document completeness and consistency. Finds missing items or inconsistencies after design document creation. Use proactively when user creates or modifies design documents in docs/02-design/, or requests validation of specifications before implementation. Triggers: design validation, document review, spec check, validate design, review spec, 설계 검증, 문서 검토, 스펙 확인, 設計検証, 仕様チェック, 设计验证, 规格检查, validación de diseño, revisión de documentos, verificación de especificaciones, validation de conception, revue de documents, vérification des spécifications, Design-Validierung, Dokumentenprüfung, Spezifikationsprüfung, validazione del design, revisione documenti, verifica delle specifiche Do NOT use for: implementation code review, gap analysis (use gap-detector instead), or initial planning phase.

.NET/C# 패턴/DI/테스트 전문가. CommunityToolkit.Mvvm, DI 컨테이너, xUnit, SerialPort. Triggers: .NET, C#, DI, xUnit, NuGet, CommunityToolkit, Prism, dotnet

CTO-level AI Native development expert agent. Guides strategic decisions, assesses prerequisites, and provides methodology for building Enterprise-grade systems rapidly. Use proactively when user discusses microservices, kubernetes, terraform, enterprise architecture, or asks about strategic technical decisions for large-scale systems. Triggers: CTO, AI Native, enterprise strategy, microservices, architecture decision, 전략, 아키텍처, 마이크로서비스, アーキテクチャ, マイクロサービス, 架构决策, 微服务, estrategia empresarial, arquitectura, microservicios, decisión arquitectónica, stratégie d'entreprise, architecture, microservices, décision architecturale, Unternehmensstrategie, Architektur, Microservices, Architekturentscheidung, strategia aziendale, architettura, microservizi, decisione architetturale Do NOT use for: simple projects, Starter level tasks, routine CRUD operations, minor UI tweaks, or standard bug fixes.

Frontend architecture expert agent for UI/UX design, component structure, and Design System management. Handles React, Next.js, and modern frontend patterns. Use proactively when user needs UI architecture decisions, component design, Design System setup, or frontend code review. Triggers: frontend, UI architecture, component, React, Next.js, design system, 프론트엔드, UI 아키텍처, 컴포넌트, 디자인 시스템, 리액트, フロントエンド, UIアーキテクチャ, コンポーネント, デザインシステム, 前端架构, UI架构, 组件, 设计系统, frontend, arquitectura UI, componente, sistema de diseño, frontend, architecture UI, composant, système de design, Frontend, UI-Architektur, Komponente, Design-System, frontend, architettura UI, componente, sistema di design Do NOT use for: backend-only tasks, infrastructure, database design, or Starter level HTML/CSS projects (use starter-guide instead).

펌웨어 아키텍처 설계 전문가. 임베디드 시스템의 소프트웨어 레이어 구조, 인터럽트 우선순위 맵, 메모리 레이아웃, RTOS 태스크 설계를 수행합니다. Triggers: firmware architecture, FW design, 펌웨어 아키텍처, FW 설계, ファームウェア設計, 固件架构, arquitectura firmware, Firmware-Architektur Do NOT use for: 단순 드라이버 구현 (hw-interface-expert 사용), MISRA 검증 (safety-auditor 사용), WPF/MPU 도메인 작업.

Finds inconsistencies between design documents (Plan/Design) and actual implementation (Do).

하드웨어 인터페이스 전문가. GPIO, SPI, I2C, UART, CAN, ADC, DMA 등 MCU 페리페럴 설정 및 드라이버 구현. Triggers: peripheral, GPIO, SPI, I2C, UART, CAN, ADC, DMA, 페리페럴 설정, 드라이버 구현, ペリフェラル, 外设配置 Do NOT use for: 전체 아키텍처 설계 (fw-architect 사용), MISRA 검증 (safety-auditor 사용).

AWS + Kubernetes + Terraform infrastructure expert agent. Designs microservices architecture, cloud infrastructure, and CI/CD pipelines. Use proactively when user discusses AWS, Kubernetes, Terraform, cloud infrastructure, CI/CD pipelines, or requires Enterprise-level deployment architecture. Triggers: AWS, Kubernetes, Terraform, infrastructure, CI/CD, EKS, RDS, cloud, 인프라, 쿠버네티스, 클라우드, インフラ, クラウド, 基础设施, 云架构, infraestructura, nube, Kubernetes, despliegue, CI/CD, infrastructure, cloud, Kubernetes, déploiement, CI/CD, Infrastruktur, Cloud, Kubernetes, Bereitstellung, CI/CD, infrastruttura, cloud, Kubernetes, distribuzione, CI/CD Do NOT use for: frontend development, simple deployments (Vercel/Netlify), Starter/Dynamic level projects, or non-infrastructure coding tasks.

리눅스 커널 모듈/드라이버 개발 전문가. platform_driver, probe/remove, sysfs/ioctl 인터페이스, DMA, 인터럽트 핸들링. Triggers: kernel module, driver, platform_driver, sysfs, ioctl, カーネルモジュール

Embedded Linux BSP 전문가. i.MX6/6ULL/28 Device Tree 설계, 커널 설정, 부팅 시퀀스, BSP 포팅을 수행합니다. Triggers: BSP, Device Tree, DTS, 커널 설정, 부팅, ブートシーケンス, 启动序列

MCU 동시성/시스템 크리티컬 이슈 통합 분석 에이전트. 2-Layer 아키텍처의 Layer 2 — ConSynergy 4-Stage 파이프라인으로 ISR/DMA/동시성/스택 이슈를 의미론적으로 분석하고 심각도×신뢰도 리포트 생성. Triggers: critical analysis, 크리티컬 분석, 동시성 분석, concurrency audit, クリティカル分析, 关键分析, análisis crítico, Konkurrenzanalyse, analisi di concorrenza Do NOT use for: 일반 코드 리뷰 (code-analyzer 사용), MISRA 검증 (safety-auditor 사용), 아키텍처 설계 (fw-architect 사용).

Act(Improvement) 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: 자기 개선 루프 완성도, 학습 보존, 팀 공유.

Check(QA/Verification) 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: 검증 범위, 도메인 특화 검증, 스킬 품질 모니터링.

Design 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: 설계 정확도, 도메인 특화 가이드 적용, phase skill 활용도.

Do(Implementation) 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: 구현 속도, 첫 시도 정확도, 피드백 수집, 런타임 스킬 확장.

Plan 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: 프로젝트 컨텍스트 인식도, 사용 가능 스킬 수, Plan 정확도.

PM Analysis 단계를 프로젝트 유형별로 평가하는 에이전트. v1.6.1 baseline vs Customized rkit 비교 분석 수행. 평가 항목: PRD 분석 깊이, 스킬 니즈 추출, PM->스킬 파이프라인 연결.

Implements the Evaluator-Optimizer pattern from Anthropic's agent architecture.

Agent that guides users through 9-phase Development Pipeline. Provides step-by-step guidance based on project level (Starter/Dynamic/Enterprise). Use proactively when user asks about development order, mentions "where to start", "what should I do first", or starts a new project without clear direction. Triggers: development pipeline, phase, development order, where to start, what to do first, how to begin, new project, project setup, 개발 파이프라인, 뭐부터, 어디서부터, 순서, 시작, 開発パイプライン, 何から, どこから, 开发流程, 从哪里开始, pipeline de desarrollo, fase, orden de desarrollo, por dónde empezar, qué hacer primero, pipeline de développement, phase, ordre de développement, par où commencer, que faire en premier, Entwicklungs-Pipeline, Phase, Entwicklungsreihenfolge, wo anfangen, was zuerst tun, pipeline di sviluppo, fase, ordine di sviluppo, da dove iniziare, cosa fare prima Do NOT use for: ongoing implementation work, existing feature modifications, bug fixes, or when experienced developers want to proceed freely.

You are a product discovery specialist. Your role is to build an Opportunity Solution Tree

pm-lead Phase 4 확장 패치. PRD 생성 완료 후 skill-needs-extractor를 호출하여 프로젝트 특화 스킬 니즈를 자동 추출하는 연결 로직. 기존 pm-lead 에이전트를 수정하지 않고 project-local에서 확장.

When spawned as an Agent Teams teammate, this agent operates as an independent

You are a senior product manager. Your role is to synthesize Discovery, Strategy,

You are a market research specialist. Your role is to create User Personas,

You are a product strategist. Your role is to design a clear Value Proposition and

Product Manager agent that analyzes requirements and creates Plan documents. Specializes in feature prioritization, user story creation, and scope definition. Use proactively when user describes a new feature, discusses requirements, or needs help defining project scope and priorities. Triggers: requirements, feature spec, user story, priority, scope, feature definition, 요구사항, 기능 정의, 우선순위, 범위, 사용자 스토리, 기능 명세, 要件定義, 機能仕様, 優先度, スコープ, ユーザーストーリー, 需求分析, 功能规格, 优先级, 范围, 用户故事, requisitos, especificación, prioridad, alcance, historia de usuario, exigences, spécification, priorité, portée, histoire utilisateur, Anforderungen, Spezifikation, Priorität, Umfang, User Story, requisiti, specifiche, priorità, ambito, storia utente Do NOT use for: implementation tasks, code review, infrastructure, or when working on Starter level projects.

L2 (Layer 2) reviewer for Python language-specific idioms and safety patterns. Checks type hints, context managers, dataclasses, security, and common anti-patterns. Layer 2 of the 3-Layer code review architecture: L1 — Universal design quality (code-analyzer) L2 (this agent) — Python language idioms L3 — Domain safety (varies by project) Triggers: Python review, python review, py review, Python 리뷰, Pythonレビュー, Python审查, revisión Python, revue Python, Python-Review, revisione Python Do NOT use for: universal design quality (use code-analyzer), or writing/modifying code (this agent is read-only).

Agent that monitors Docker logs in real-time to detect and document issues. Core executor for Zero Script QA methodology. Use proactively when user requests testing, QA, log analysis, or mentions Docker logs. Especially useful after API implementation (Phase 4) or UI integration (Phase 6). Triggers: zero script qa, log-based testing, docker logs, QA, testing, log analysis, 제로 스크립트 QA, 테스트, 로그 분석, ゼロスクリプトQA, ログ分析, 零脚本QA, 日志分析, QA sin scripts, pruebas basadas en logs, registros de docker, pruebas, análisis de logs, QA sans script, tests basés sur les logs, logs docker, tests, analyse de logs, Script-freies QA, Log-basiertes Testen, Docker-Logs, Tests, Log-Analyse, QA senza script, test basati su log, log docker, test, analisi dei log Do NOT use for: unit testing with test scripts, frontend-only testing without Docker, or design document validation.

QA Strategy agent that coordinates testing efforts, defines quality metrics, and manages qa-monitor and gap-detector for comprehensive verification. Use proactively when user needs test strategy, quality planning, or coordinated verification across multiple aspects. Triggers: test strategy, QA plan, quality metrics, test plan, verification strategy, 테스트 전략, QA 계획, 품질 기준, 검증 전략, 테스트 계획, テスト戦略, QA計画, 品質基準, 検証戦略, テスト計画, 测试策略, QA计划, 质量标准, 验证策略, 测试计划, estrategia de pruebas, plan QA, métricas de calidad, plan de pruebas, stratégie de test, plan QA, métriques de qualité, plan de test, Teststrategie, QA-Plan, Qualitätsmetriken, Testplan, strategia di test, piano QA, metriche di qualità, piano di test Do NOT use for: actual code implementation, infrastructure tasks, or simple single-file verification (use gap-detector directly).

Agent that automatically generates PDCA cycle completion reports. Consolidates plan, design, implementation, and analysis results into learnable reports. Use proactively when user completes PDCA cycle, finishes feature implementation, or requests summary/status report of development progress. Triggers: PDCA report, completion report, status report, summary, progress report, what did we do?, status?, progress?, write report, PDCA 보고서, 완료 보고서, 진행 보고서, 뭐 했어?, 진행 상황, 요약, PDCA報告書, 完了レポート, 何をした?, 進捗, 状況, PDCA报告, 进度报告, 做了什么?, 进度, 状态, qué hicimos?, estado?, qu'avons-nous fait?, statut?, was haben wir?, Status?, cosa abbiamo fatto?, stato? Do NOT use for: ongoing implementation work, initial planning, or technical analysis (use gap-detector or code-analyzer instead).

You are a specialist in rkit plugin architecture. Your mission is to map

MISRA C / 기능안전 감사자. MISRA C:2012 코딩 표준 준수 검증, 스택 오버플로 위험 분석, 미초기화 변수 검출, 무한 루프 위험 분석. Triggers: MISRA, safety, 코딩 표준, 안전 검증, MISRA C, コーディング規約, 编码标准, estándar de codificación Do NOT use for: 일반 코드 리뷰 (code-analyzer 사용), 아키텍처 설계 (fw-architect 사용).

Security architecture expert agent for vulnerability analysis, authentication design review, and OWASP Top 10 compliance checking. Use proactively when user needs security review, authentication design, vulnerability assessment, or security-related code review. Triggers: security, authentication, vulnerability, OWASP, CSRF, XSS, injection, 보안, 인증, 취약점, 보안 검토, 인가, 보안 아키텍처, セキュリティ, 認証, 脆弱性, セキュリティレビュー, セキュリティ設計, 安全, 认证, 漏洞, 安全审查, 安全架构, seguridad, autenticación, vulnerabilidad, revisión de seguridad, sécurité, authentification, vulnérabilité, revue de sécurité, Sicherheit, Authentifizierung, Schwachstelle, Sicherheitsüberprüfung, sicurezza, autenticazione, vulnerabilità, revisione sicurezza Do NOT use for: general code review (use code-analyzer), infrastructure setup (use infra-architect), or Starter level projects.

빌드 실패 / 런타임 오류 자동 진단 및 수정 시도 에이전트. MCU/MPU/WPF 도메인별 HEALING_STRATEGIES 기반 패턴 매칭. 링커스크립트, Device Tree, .csproj 수정 전 반드시 현재 상태 확인. Triggers: self-heal, 자동 복구, 빌드 실패, build error, fix build, ビルドエラー, 构建错误, error de compilación Do NOT use for: 일반 코드 리뷰 (code-analyzer 사용), 아키텍처 설계 (fw-architect 사용), 보안 감사 (security-architect 사용).

PRD 분석 결과에서 프로젝트 특화 스킬 니즈를 자동 추출하고, 기존 rkit 28개 core 스킬과 매칭하여 갭 분석을 수행하는 에이전트. pm-lead Phase 4 완료 후 자동 호출되어 skill-create 파이프라인에 연결.

Friendly guide agent for non-developers and beginners. Explains in simple terms and provides step-by-step guidance for Starter level projects. Use proactively when user is a beginner, mentions "first time", asks about learning, or requests a simple static website without backend requirements. Triggers: beginner, first project, new to coding, learn to code, simple website, portfolio, landing page, HTML CSS, help understand, don't understand, confused, 초보자, 입문, 처음, 코딩 배우기, 웹사이트 만들기, 이해 안 돼, 설명해, 어려워, 모르겠, 初心者, 入門, ウェブサイト作成, わからない, 教えて, 難しい, 新手, 学习编程, 不懂, 不明白, 太难, principiante, no entiendo, explica, difícil, débutant, je ne comprends pas, Anfänger, verstehe nicht, principiante, non capisco, difficile, spiegami Do NOT use for: experienced developers, enterprise-level projects, backend development, microservices architecture, or complex fullstack applications.

WPF MVVM 아키텍처 설계 전문가. MVVM 구조, DI 컨테이너, 네비게이션, 시리얼 통신 설계. Triggers: WPF architecture, MVVM, WPF 아키텍처, WPFアーキテクチャ, WPF架构

XAML UI/바인딩/스타일 전문가. DataTemplate, Style, ResourceDictionary, Converter. Triggers: XAML, binding, style, template, converter, XAML 바인딩, XAMLスタイル

Yocto/Buildroot 빌드 시스템 전문가. 레시피 작성, 레이어 관리, 이미지 커스터마이징. Triggers: Yocto, bitbake, recipe, layer, Buildroot, レシピ, 食谱, receta

Lock architecture decisions from Design documents to prevent scope creep during Do phase. Auto-generates Mermaid diagrams for MCU memory maps, MPU software stacks, WPF MVVM structures. Triggers: arch-lock, architecture lock, lock design, 아키텍처 락, 설계 잠금, アーキテクチャロック, 設計ロック, 架构锁定, 设计锁定, bloqueo de arquitectura, verrouillage d'architecture, Architektursperre, blocco dell'architettura Do NOT use for: file-level freeze (use /freeze), automation control (use /control).

Skill for enhancing search optimization (SEO) and security. Covers meta tags, semantic HTML, and security vulnerability checks. Use proactively when user asks about search ranking, security hardening, or vulnerability fixes. Triggers: SEO, security, meta tags, XSS, CSRF, 보안, セキュリティ, 安全, seguridad, etiquetas meta, optimización de búsqueda, sécurité, balises méta, optimisation pour les moteurs de recherche, Sicherheit, Meta-Tags, Suchmaschinenoptimierung, sicurezza, tag meta, ottimizzazione per i motori di ricerca Do NOT use for: backend-only APIs, internal tools, or basic development setup.

Code review skill for analyzing code quality, detecting bugs, and ensuring best practices. Provides comprehensive code review with actionable feedback. Use proactively when user requests code review, quality check, or bug detection. Triggers: code review, review code, check code, analyze code, bug detection, 코드 리뷰, 코드 검토, 버그 검사, コードレビュー, バグ検出, 代码审查, 代码检查, revisión de código, revisar código, detección de errores, revue de code, réviser le code, détection de bugs, Code-Review, Code überprüfen, Fehlererkennung, revisione del codice, rivedere codice, rilevamento bug Do NOT use for: design document creation, deployment tasks, or gap analysis (use phase-8-review).

View audit logs, decision traces, and session history. Browse and search through rkit's audit trail for transparency and debugging. Use proactively when user wants to review AI decisions, check audit history, or investigate what actions were taken during a PDCA cycle. Triggers: audit, log, trace, history, decision, transparency, 감사, 로그, 추적, 이력, 결정, 투명성, 監査, ログ, 追跡, 履歴, 決定, 透明性, 审计, 日志, 追踪, 历史, 决策, 透明度, auditoria, registro, rastreo, historial, decision, transparencia, audit, journal, trace, historique, decision, transparence, Audit, Protokoll, Nachverfolgung, Verlauf, Entscheidung, Transparenz, audit, registro, traccia, cronologia, decisione, trasparenza Do NOT use for: modifying audit logs, PDCA phase execution, or code changes.

MCU/MPU/WPF domain-specific build and resource benchmarking. MCU: Flash/RAM usage via arm-none-eabi-size. MPU: rootfs/image size. WPF: build time and publish size. Triggers: benchmark, 벤치마크, ベンチマーク, 基准测试, benchmarking, Benchmark, riferimento

타겟 보드 디버깅 스킬. SSH 원격 테스트, 시리얼 로그 수집/분석, 디버그 리포트 생성. Triggers: 보드 디버깅, 보드 테스트, board debug, boot check, 부팅 확인

By-The-Way: 작업 중 개선 제안을 즉시 수집하고 관리하는 스킬. Triggers: /btw, /btw list, /btw analyze, /btw promote, /btw stats Keywords: btw, 개선, 제안, suggestion, improve, idea, feedback

CC Version Analysis — Claude Code CLI version upgrade impact analysis workflow. Researches CC changes, analyzes rkit architecture impact, brainstorms improvements, and generates comprehensive impact report with ENH opportunities. Use proactively when a new CC CLI version is released or user wants to analyze version upgrade impact on rkit plugin. Triggers: cc-version-analysis, version analysis, CC upgrade, CLI upgrade analysis, CC 버전 분석, CLI 업그레이드, 버전 영향 분석, CC 업데이트 분석, CCバージョン分析, CLIアップグレード, バージョン影響分析, CC版本分析, CLI升级分析, 版本影响分析, análisis de versión CC, análisis de actualización CLI, analyse de version CC, analyse de mise à jour CLI, CC-Versionsanalyse, CLI-Upgrade-Analyse, analisi versione CC, analisi aggiornamento CLI Do NOT use for: non-CC version topics, rkit feature development, code implementation.

Claude Code learning and education skill. Teaches users how to configure and optimize Claude Code settings. Works across any project and any language. Start learning/setup with "learn" or "setup". Use proactively when user is new to Claude Code, asks about configuration, or wants to improve their Claude Code setup. Triggers: learn claude code, claude code setup, CLAUDE.md, hooks, commands, skills, how to configure, 클로드 코드 배우기, 설정 방법, Claude Code 학습, クロードコード学習, 设置方法, how do I use claude code, aprender claude code, configuración, cómo configurar, apprendre claude code, configuration, comment configurer, Claude Code lernen, Konfiguration, wie konfigurieren, imparare claude code, configurazione, come configurare Do NOT use for: actual coding tasks, debugging, or feature implementation.

임베디드 CMake 빌드 시스템 구성. arm-none-eabi 툴체인 파일, 링커 스크립트 연동. Triggers: CMake, embedded build, 빌드 시스템, ビルド, 构建系统

UART/SPI/I2C/CAN 통신 드라이버 패턴. DMA 전송, 인터럽트 수신, 프로토콜 설계. Triggers: UART, SPI, I2C, CAN, USB, DMA, 통신, 시리얼, 通信, comunicación

Control rkit automation level and view system status. Manage L0-L4 automation levels, trust score, and active guardrails. Use proactively when user wants to adjust automation behavior, check trust score, or pause/resume automated PDCA operations. Triggers: control, automation, level, pause, resume, trust, guardrail, 제어, 자동화, 레벨, 일시정지, 재개, 신뢰, 制御, 自動化, レベル, 一時停止, 再開, 信頼, 控制, 自动化, 级别, 暂停, 恢复, 信任, control, automatizacion, nivel, pausa, reanudar, confianza, controle, automatisation, niveau, pause, reprendre, confiance, Steuerung, Automatisierung, Stufe, pausieren, fortsetzen, Vertrauen, controllo, automazione, livello, pausa, riprendere, fiducia Do NOT use for: PDCA phase management, code review, or deployment tasks.

MCU flash programming, MPU image deployment, WPF publish guide. Domain-aware deployment with safety checks for destructive operations. Triggers: deploy, 배포, デプロイ, 部署, desplegar, deployer, bereitstellen, distribuire Do NOT use for: CI/CD pipeline setup (use /phase-9-deployment), GitLab MR creation (use /ship).

Desktop app development guide for cross-platform desktop applications. Covers Electron and Tauri frameworks. Use proactively when user wants to build desktop applications with web technologies. Triggers: desktop app, Electron, Tauri, mac app, windows app, 데스크톱 앱, デスクトップアプリ, 桌面应用, aplicación de escritorio, app de escritorio, application de bureau, application desktop, Desktop-Anwendung, Desktop-App, applicazione desktop, app desktop Do NOT use for: web-only projects, mobile apps, or server-side development.

9-phase Development Pipeline complete knowledge. Use when user doesn't know development order or starts a new project from scratch. Use proactively when user asks about development order, phases, what to do first, or starts a new project without clear direction. Triggers: development pipeline, phase, development order, where to start, what to do first, how to begin, new project, 개발 파이프라인, 뭐부터, 어디서부터, 순서, 시작, 開発パイプライン, 何から, どこから, 开发流程, 从哪里开始, pipeline de desarrollo, fase, orden de desarrollo, por dónde empezar, qué hacer primero, pipeline de développement, phase, ordre de développement, par où commencer, que faire d'abord, Entwicklungspipeline, Phase, Entwicklungsreihenfolge, wo anfangen, was zuerst tun, pipeline di sviluppo, fase, ordine di sviluppo, da dove iniziare, cosa fare prima Do NOT use for: ongoing implementation, existing feature work, or bug fixes.

.NET DI/패턴/테스트 가이드. Microsoft.Extensions.DI, xUnit, async/await 패턴. Triggers: .NET, C#, DI, dependency injection, xUnit, async, pattern

Fullstack development skill using bkend.ai BaaS platform. Covers authentication, data storage, API integration for dynamic web apps. Project initialization with "init dynamic" or "dynamic init". Use proactively when user needs login, database, or backend features without managing servers. Triggers: fullstack, BaaS, bkend, authentication, login feature, signup, database, web app, SaaS, MVP, init dynamic, dynamic init, 풀스택, 인증, 로그인 기능, 회원가입, 데이터베이스, 웹앱, フルスタック, 認証, ログイン機能, データベース, 全栈, 身份验证, 登录功能, autenticación, inicio de sesión, registro, base de datos, fullstack, aplicación web, authentification, connexion, inscription, base de données, fullstack, application web, Authentifizierung, Anmeldung, Registrierung, Datenbank, Fullstack, Web-App, autenticazione, accesso, registrazione, database, fullstack, applicazione web Do NOT use for: static websites, Enterprise-grade systems requiring custom infrastructure.

OpenProject 프로젝트 현황을 요약합니다. 프로젝트별 열린 작업 수, 기한 초과 작업을 표 형태로 보여줍니다. 인자 없이 실행하면 전체 프로젝트, 인자가 있으면 해당 프로젝트만 조회합니다. Triggers: op-status, 프로젝트 현황, project status, 작업 현황, 기한 초과, overdue, 열린 작업, open tasks, OP 현황

Enterprise-grade system development with microservices, Kubernetes, and Terraform. Includes AI Native methodology and Monorepo architecture patterns. Handles high traffic, high availability, and complex architecture requirements. Project initialization with "init enterprise" or "enterprise init". Use proactively when user needs high traffic, microservices, custom infrastructure, or AI-native development patterns. Triggers: microservices, kubernetes, terraform, k8s, AWS, monorepo, AI native, 10-day, init enterprise, enterprise init, 마이크로서비스, 모노레포, マイクロサービス, モノレポ, 微服务, 单仓库, microservicios, estrategia empresarial, arquitectura, CTO, nativo de IA, microservices, stratégie d'entreprise, architecture, CTO, natif IA, Microservices, Unternehmensstrategie, Architektur, CTO, KI-nativ, microservizi, strategia aziendale, architettura, CTO, AI nativo Do NOT use for: simple websites, MVPs, or projects without infrastructure requirements.

FreeRTOS 태스크/동기화 설계. xTaskCreate, Queue, Semaphore, Mutex, 스택 사이징. Triggers: FreeRTOS, RTOS, task, queue, semaphore, mutex, 태스크, タスク, 任务

Freeze critical files to prevent accidental modification during development. Protects linker scripts, Device Tree, kernel headers, project configs, and more. Domain-specific presets for MCU, MPU (Kernel/Driver/App), and WPF. Triggers: freeze, unfreeze, protect, lock files, 동결, 보호, 파일 잠금, 凍結, ファイル保護, 冻结, 文件保护, congelar, proteger, geler, protéger, einfrieren, schützen, congelare, proteggere Do NOT use for: architecture-level locking (use /arch-lock), automation level control (use /control), PDCA phase management.

Combined safety mode that orchestrates freeze + destructive detection + automation cap. When active: freezes domain preset, caps automation at L2, enhances Bash scrutiny. Triggers: guard, safety mode, careful mode, 가드, 안전 모드, 조심, ガードモード, 安全モード, 慎重, 守卫模式, 安全模式, 谨慎, modo guardia, modo seguro, mode garde, mode sécurisé, Schutzmodus, Sicherheitsmodus, modalità guardia, modalità sicura Do NOT use for: individual file freeze (use /freeze), automation level control (use /control), PDCA phase management.

하드웨어 회로도/데이터시트 분석 → DTS/defconfig/드라이버 매핑 스킬. Mermaid 다이어그램을 적극 활용하여 하드웨어 블록과 핀 매핑을 시각화한다. Triggers: 회로도 분석, 핀맵, DTS 생성, schematic, datasheet, hw analysis

i.MX BSP/Device Tree 개발 가이드. pinctrl, 클럭, GPIO 노드 작성, 보드 포팅. Triggers: i.MX, BSP, Device Tree, DTS, pinctrl, imx6, imx6ull, imx28

Systematic investigation protocol for MCU HardFault, MPU boot/kernel issues, and WPF crashes. Triggers: investigate, 조사, 調査, 调查, investigar, enquêter, untersuchen, indagare, HardFault, crash, 크래시

리눅스 커널 모듈/드라이버 개발 가이드. platform_driver, DT 바인딩, sysfs, ioctl. Triggers: kernel module, driver, platform_driver, sysfs, ioctl, 커널 모듈, カーネル

OpenProject 태스크를 조회하고 관리합니다. 상태 변경, comment 추가, 시간 기록, 담당자 변경을 지원합니다. "my"를 인자로 주면 본인 할당 태스크 목록을 조회합니다. Triggers: op-task, 태스크 조회, 작업 상세, task detail, OP #, 상태 변경, 완료 처리, 시간 기록, time entry, comment 추가, 내 작업, my tasks, 할당된 작업, 내 할일

MCU 동시성/시스템 크리티컬 이슈 통합 분석 스킬. ConSynergy 4-Stage 파이프라인으로 ISR/DMA/동시성/스택 이슈를 분석하고 심각도×신뢰도 분류 리포트를 생성합니다. Use proactively when user mentions concurrency issues, race conditions, interrupt safety, DMA conflicts, or asks for critical code review. Triggers: mcu-critical-analysis, critical analysis, 크리티컬 분석, 동시성 분석, 동시성 감사, concurrency, concurrency audit, race condition, 레이스 컨디션, data race, deadlock, 데드락, ISR 분석, interrupt analysis, DMA 분석, 스택 분석, クリティカル分析, 并发分析, análisis de concurrencia, Konkurrenzanalyse, analisi di concorrenza Do NOT use for: 일반 코드 리뷰 (code-review 사용), MISRA 검증만 필요한 경우 (misra-c 사용), 아키텍처 설계 (fw-architect 에이전트 사용).

Mermaid v8.8.0 다이어그램 작성 규칙. subgraph ID 필수, flowchart/direction/& 금지. Triggers: mermaid, diagram, 다이어그램, ダイアグラム

MISRA C:2012 코딩 표준 가이드. Required/Advisory/Documented 규칙 분류, 자주 위반되는 규칙 Top 20, cppcheck --addon=misra 연동. Triggers: MISRA, MISRA C, coding standard, 코딩 표준, コーディング規約, 编码标准

Mobile app development guide for cross-platform apps. Covers React Native, Flutter, and Expo frameworks. Use proactively when user wants to build mobile apps or convert web apps to mobile. Triggers: mobile app, React Native, Flutter, Expo, iOS, Android, 모바일 앱, モバイルアプリ, 移动应用, aplicación móvil, app móvil, desarrollo móvil, application mobile, développement mobile, mobile Anwendung, mobile App, mobile Entwicklung, applicazione mobile, app mobile, sviluppo mobile Do NOT use for: web-only projects, backend-only development, or desktop apps.

GitLab MR 팀 규칙과 코드 리뷰 프로토콜. MR 관련 작업 시 자동으로 참조됩니다. Triggers: MR, merge request, 코드 리뷰, code review, 리뷰, review, 브랜치, branch, 커밋, commit, draft, squash, approve, 승인, 머지

GitLab MR 전체 라이프사이클을 관리합니다. 생성, 리뷰, 피드백, 검증, 상태 확인, 승인, 머지를 지원합니다. 개발자와 리뷰어 모두 사용할 수 있습니다. Triggers: mr, merge request, MR 생성, MR 리뷰, MR 피드백, MR 머지, 리뷰 확인, 피드백 확인, draft MR, MR 승인, MR 상태

NXP MCUXpresso SDK 드라이버 패턴 가이드. fsl_* API, board.h 구조, clock_config. Triggers: NXP, MCUXpresso, Kinetis, fsl_, MCU-Link

OpenProject에 새 작업 패키지를 대화형으로 생성합니다. 프로젝트, 유형, 우선순위, 담당자를 MCP 도구로 조회하여 선택하고, 팀 규칙(담당자 필수, Bug는 재현 절차 포함)을 자동 적용합니다. Triggers: op-create-task, 태스크 생성, 작업 생성, create task, 새 작업, OP 태스크 만들어, work package 생성, 작업 만들어줘

어제 완료한 OP 작업, 오늘 할 작업, 하루 동안의 커밋 내역을 종합하여 일일 스탠드업 보고서를 마크다운 형태로 생성합니다. /op-standup 명령어나 스탠드업 요청 시 호출됩니다. Triggers: op-standup, 스탠드업, standup, 데일리 스크럼, 아침 회의록, 일일 보고서, daily report, 오늘 할 일

OpenProject MCP 도구 사용 규칙과 PDCA 워크플로 연동 패턴. OpenProject 관련 MCP 도구 사용 시 자동으로 참조됩니다. Triggers: OpenProject, 작업 패키지, work package, 시간 기록, time entry, 프로젝트 현황, 작업 생성, OP, 태스크, task tracking

Manage multiple PDCA features and batch operations. View status of all active features, plan multiple features simultaneously, and manage parallel PDCA cycles (max 3 concurrent). Use proactively when user wants to work on multiple features, check cross-feature status, or batch-plan related features. Triggers: batch, multi, parallel, features, dashboard, bulk, 배치, 다중, 병렬, 대시보드, 일괄, バッチ, 複数, 並列, ダッシュボード, 一括, 批处理, 多个, 并行, 仪表板, 批量, lote, multiple, paralelo, panel, masivo, lot, multiple, parallele, tableau de bord, masse, Stapel, mehrere, parallel, Dashboard, Masse, batch, multiplo, parallelo, pannello, massa Do NOT use for: single feature PDCA operations, code review, or deployment.

Unified skill for managing the entire PDCA cycle. Auto-triggered by keywords: "plan", "design", "analyze", "report", "status". Replaces legacy /pdca-* commands. Mermaid 다이어그램을 적극 활용하여 설계와 구조를 시각화한다. Use proactively when user mentions PDCA cycle, planning, design documents, gap analysis, iteration, or completion reports. Triggers: pdca, 계획, 설계, 분석, 검증, 보고서, 반복, 개선, plan, design, analyze, check, report, status, next, iterate, gap, 計画, 設計, 分析, 検証, 報告, 计划, 设计, 分析, 验证, 报告, planificar, diseño, analizar, verificar, planifier, conception, analyser, vérifier, rapport, planen, Entwurf, analysieren, überprüfen, Bericht, pianificare, progettazione, analizzare, verificare, rapporto Do NOT use for: simple queries without PDCA context, code-only tasks.

Skill for defining terminology and data structures used throughout the project. Covers domain terminology, entities, relationships, and schema design. Use proactively when starting a new project or when data structures are unclear. Triggers: schema, terminology, data model, entity, 스키마, 用語, データモデル, 数据模型, esquema, terminología, modelo de datos, schéma, terminologie, modèle de données, Schema, Terminologie, Datenmodell, schema, terminologia, modello dati Do NOT use for: UI-only changes, deployment, or when schema is already defined.

Skill for defining coding rules and conventions. Ensures consistent code style and specifies coding standards for AI collaboration. Use proactively when starting a new project or when coding standards are needed. Triggers: convention, coding style, naming rules, 컨벤션, コンベンション, 编码风格, convención, estilo de código, reglas de nombrado, convention, style de codage, règles de nommage, Konvention, Coding-Stil, Namensregeln, convenzione, stile di codice, regole di denominazione Do NOT use for: existing projects with established conventions, deployment, or testing.

Skill for creating mockups with UI/UX trends without a designer. Designs HTML/CSS/JS prototypes that can be converted to Next.js components. Use proactively when user wants to validate UI/UX before implementation. Triggers: mockup, prototype, wireframe, UI design, 목업, モックアップ, 原型, maqueta, prototipo, diseño UI, maquette, prototype, conception UI, Mockup, Prototyp, UI-Design, mockup, prototipo, design UI Do NOT use for: production code, API development, or existing component modifications.

Skill for designing and implementing backend APIs. Includes Zero Script QA methodology for validating APIs without test scripts. Use proactively when user needs to design or implement backend APIs. Triggers: API design, REST API, backend, endpoint, API 설계, API設計, API设计, diseño de API, diseño API, diseño de backend, conception API, conception d'API, backend, API-Design, API-Entwurf, Backend, progettazione API, design API, backend Do NOT use for: frontend-only projects, static websites, or Starter level projects.

Skill for building platform-independent design systems. Develops consistent component libraries for all UI frameworks. Use proactively when user needs consistent UI components or mentions design tokens. Triggers: design system, component library, design tokens, shadcn, 디자인 시스템, デザインシステム, 设计系统, sistema de diseño, biblioteca de componentes, tokens de diseño, système de design, bibliothèque de composants, jetons de design, Design-System, Komponentenbibliothek, Design-Tokens, sistema di design, libreria di componenti, token di design Do NOT use for: one-off UI changes, backend development, or simple static sites.

Skill for implementing actual UI and integrating with APIs. Covers frontend-backend integration, state management, and API client architecture. Use proactively when user needs to connect frontend with backend APIs. Triggers: UI implementation, API integration, state management, UI 구현, API連携, 状态管理, implementación UI, integración API, gestión de estado, implémentation UI, intégration API, gestion d'état, UI-Implementierung, API-Integration, Zustandsverwaltung, implementazione UI, integrazione API, gestione dello stato Do NOT use for: mockup creation, backend-only development, or design system setup.

Skill for verifying overall codebase quality and gap analysis. Covers architecture consistency, convention compliance, design-implementation gaps, and potential issue detection. Includes analysis patterns and report writing. Use proactively when implementation is complete and quality verification is needed. Triggers: code review, architecture review, quality check, refactoring, gap analysis, 코드 리뷰, 설계-구현 분석, コードレビュー, ギャップ分析, 代码审查, 差距分析, revisión de código, revisión de arquitectura, control de calidad, análisis de brechas, revue de code, revue d'architecture, contrôle qualité, analyse des écarts, Code-Review, Architekturüberprüfung, Qualitätskontrolle, Gap-Analyse, revisione del codice, revisione dell'architettura, controllo qualità, analisi dei gap Do NOT use for: initial development, design phase, or deployment tasks.

Skill for deploying to production environment. Covers CI/CD, environment configuration, and deployment strategies. Use proactively when user is ready to deploy or asks about production environment setup. Triggers: deployment, CI/CD, production, Vercel, Kubernetes, Docker, 배포, デプロイ, 部署, despliegue, implementación, producción, déploiement, mise en production, Bereitstellung, Produktion, distribuzione, messa in produzione Do NOT use for: local development, design phase, or feature implementation.

Plan Plus — Brainstorming-Enhanced PDCA Planning. Combines intent discovery from brainstorming methodology with rkit PDCA's structured planning. Produces higher-quality Plan documents by exploring user intent, comparing alternatives, and applying YAGNI review before document generation. Mermaid 다이어그램을 적극 활용하여 기획 구조를 시각화한다. Use proactively when user mentions planning with brainstorming, intent discovery, exploring alternatives, or wants a more thorough planning process. Triggers: plan-plus, plan plus, brainstorming plan, enhanced plan, deep plan, 플랜 플러스, 브레인스토밍, 기획, 의도 탐색, 대안 탐색, プランプラス, ブレインストーミング, 企画, 意図探索, 计划加强, 头脑风暴, 深度规划, 意图探索, plan mejorado, lluvia de ideas, planificación profunda, plan amélioré, remue-méninges, planification approfondie, erweiterter Plan, Brainstorming, vertiefte Planung, piano migliorato, brainstorming, pianificazione approfondita Do NOT use for: simple tasks that don't need planning, code-only changes.

PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs 4 specialized PM agents in parallel to produce a comprehensive PRD before PDCA Plan phase. Integrates pm-skills frameworks (MIT). Use proactively when user wants product analysis before development, needs a PRD, or asks for PM-level planning. Triggers: /pdca pm, pm analysis, product discovery, PRD, pm team, PM 분석, 제품 기획, 제품 발견, PM팀, PRD 작성, PM分析, プロダクト分析, 产品分析, 产品发现, análisis PM, descubrimiento de producto, analyse PM, découverte produit, PM-Analyse, Produktentdeckung, analisi PM, scoperta prodotto Do NOT use for: implementation, code review, existing PDCA phases (plan/design/do/check).

프로젝트 워크스페이스 구성 스킬. git submodule + Kconfig + Makefile 빌드 시스템 생성. Triggers: 워크스페이스 구성, 빌드 환경, workspace setup, platform add

Embedded Challenge Protocol — 5-phase 21-question systematic problem validation before PDCA planning. Combines 6 validated frameworks: Wedell-Wedellsborg reframing, Garry Tan demand reality, Gary Klein pre-mortem, David Bland assumption mapping, Toyota Five Whys, McKinsey MECE. Triggers: reframe, challenge, office hours, problem validation, 리프레이밍, 문제 검증, リフレーミング, 問題検証, 问题验证, reencuadre, recadrage, Neuformulierung, riformulazione Do NOT use for: implementation tasks, code review, PDCA phase execution. Use this BEFORE /pdca plan for complex features.

Structured engineering retrospective after PDCA Report completion. Triggers: retro, retrospective, 회고, 振り返り, 回顾, retrospectiva, rétrospective, Retrospektive, retrospettiva

Triggers: code, class, function, design, create, write, implement, refactor, 코드, 클래스, 함수, 설계, 구현, 만들어, rkit, PDCA, develop, feature. Code quality + PDCA rules. MUST Read before writing code.

Manage checkpoints and rollback PDCA state. Create, list, and restore checkpoints for safe recovery during PDCA cycles. Use proactively when user wants to undo a phase transition, restore to a checkpoint, or reset a feature to its initial state. Triggers: rollback, checkpoint, undo, restore, revert, reset, recovery, 롤백, 체크포인트, 되돌리기, 복원, 복구, 초기화, ロールバック, チェックポイント, 元に戻す, 復元, 復旧, リセット, 回滚, 检查点, 撤销, 恢复, 还原, 重置, revertir, punto de control, deshacer, restaurar, recuperar, reiniciar, restaurer, point de controle, annuler, retablir, recuperer, reinitialiser, Rollback, Kontrollpunkt, ruckgangig, wiederherstellen, zurucksetzen, rollback, checkpoint, annullare, ripristinare, recuperare, reimpostare Do NOT use for: PDCA phase execution, code review, or automation control.

루트파일시스템 구성 가이드. init 시스템, 파일시스템 레이아웃, 부팅 최적화. Triggers: rootfs, init, systemd, busybox, 루트파일시스템, ファイルシステム

Full STRIDE threat modeling adapted for embedded systems (MCU/MPU/WPF). Domain-specific hardware threat vectors, confidence-based filtering, false-positive exclusion. Inspired by gstack /cso with embedded adaptation. Triggers: security review, STRIDE, threat model, 보안 리뷰, 위협 모델링, セキュリティレビュー, 脅威モデリング, 安全审查, 威胁建模, revisión de seguridad, revue de sécurité, Sicherheitsüberprüfung, revisione sicurezza Do NOT use for: general code review (use /code-review), OWASP web-only checks (use security-architect agent directly).

MCU↔WPF 시리얼 통신 브릿지 가이드. UART/SerialPort 설정 일관성, 프로토콜 설계. Triggers: serial, UART, SerialPort, 시리얼, 통신 브릿지, MCU WPF 연동

Create GitLab Merge Requests from PDCA Report using glab CLI. Domain-specific MR templates for MCU, MPU (Kernel/Driver/App), and WPF. Triggers: ship, merge request, MR, deliver, 배포, MR 생성, マージリクエスト, 合并请求, solicitud de fusión, demande de fusion, Merge-Anfrage, richiesta di unione Do NOT use for: GitHub PRs (use gh directly), deployment (use /phase-9-deployment).

Interactive skill creation workflow for project-local skills. Generates SKILL.md + eval files based on project context. Triggers: /skill-create, skill create, 스킬 생성, 스킬 만들기 Keywords: skill-create, create skill, generate skill, 스킬 생성

Shows loaded skill inventory: rkit core skills vs project-local skills. Detects conflicts, overrides, and coverage gaps. Triggers: /skill-status, skill status, 스킬 상태, 스킬 목록 Keywords: skill-status, skill list, skills loaded, 스킬 상태, 스킬 목록

Static web development skill for beginners and non-developers. Covers HTML/CSS/JavaScript and Next.js App Router basics. Project initialization with "init starter" or "starter init". Use proactively when user is a beginner or wants a simple static website. Triggers: static website, portfolio, landing page, HTML CSS, beginner, first website, simple web, personal site, init starter, starter init, 정적 웹, 포트폴리오, 랜딩페이지, 초보자, 첫 웹사이트, 간단한 웹, 静的サイト, ポートフォリオ, 初心者, 静态网站, 个人网站, 初学者, sitio web estático, portafolio, página de inicio, principiante, primer sitio web, site web statique, portfolio, page d'accueil, débutant, premier site web, statische Website, Portfolio, Landingpage, Anfänger, erste Website, sito web statico, portfolio, pagina di destinazione, principiante, primo sito web Do NOT use for: fullstack apps with backend, authentication features, or database needs.

STM32 HAL/LL API 사용 가이드 및 베스트 프랙티스. CubeMX 코드 생성 후 수정 가이드, HAL 콜백 패턴, LL API 전환 기준. Triggers: STM32, HAL, LL, CubeMX, Cortex-M, stm32f4, stm32h7, STM32 개발, STM32開発, STM32开发, desarrollo STM32

WPF MVVM 아키텍처 가이드. CommunityToolkit.Mvvm, DI, 네비게이션 패턴. Triggers: WPF, MVVM, ViewModel, CommunityToolkit, ObservableObject, RelayCommand

XAML UI 디자인/스타일 가이드. ResourceDictionary, DataTemplate, Converter, Style. Triggers: XAML design, style, template, ResourceDictionary, converter

Yocto 빌드 재현성 가이드. SRCREV 고정, SSTATE 캐시 공유, DL_DIR 미러, 빌드 환경 고정. Triggers: SRCREV, SSTATE, DL_DIR, build reproducibility, 빌드 재현성

Yocto 빌드 시스템 가이드. 레시피 작성, 레이어 관리, 이미지 커스터마이징. Triggers: Yocto, bitbake, recipe, layer, meta-imx, meta-freescale

Yocto/Embedded Linux 코드 리뷰 기준. Recipe, 스크립트, DTS, defconfig 리뷰 체크리스트. Triggers: yocto review, recipe review, bbappend review, Yocto 리뷰

STM32MP BSP 커스터마이징 스킬. Kernel/U-Boot/TF-A/OP-TEE의 defconfig, DTS, patch, 소스 fork. Triggers: stm32 bsp, stm32mp kernel, stm32 dts, TF-A 설정, OP-TEE, 부트로더

STM32MP Yocto 빌드 실행 스킬. bitbake 빌드, 환경 체크, SDK 생성, 플래싱 패키지, 릴리즈 노트/SBOM. Triggers: stm32 build, stm32mp bitbake, 이미지 빌드, SDK 생성, 플래싱 패키지

STM32MP Yocto recipe/image/distro 작업 스킬. bbappend 생성, custom image, distro conf, 패키지 추가. Triggers: stm32 recipe, stm32mp bbappend, 이미지 생성, distro 생성, 패키지 추가

STM32MP Yocto 빌드 환경 구성 스킬. repo init/sync, custom layer/machine 생성, GitLab push 자동화. Triggers: yocto setup, yocto 셋업, stm32 yocto, stm32mp setup, 환경 구성

Zero Script QA - Testing methodology without test scripts. Uses structured JSON logging and real-time Docker monitoring for verification. Use proactively when user needs to verify features through log analysis instead of test scripts. Triggers: zero script qa, log-based testing, docker logs, 제로 스크립트 QA, ゼロスクリプトQA, 零脚本QA, QA sin scripts, pruebas basadas en logs, registros de docker, QA sans script, tests basés sur les logs, journaux docker, skriptloses QA, log-basiertes Testen, Docker-Logs, QA senza script, test basati sui log, log docker Do NOT use for: unit testing, static analysis, or projects without Docker setup.

9 hooks across 6 events

Concise, expert-level output for experienced embedded engineers

Beginner-friendly output with detailed explanations for embedded development

PDCA workflow + embedded expert level for advanced projects

PDCA workflow guide with phase status and domain-specific suggestions