Claude Skills by Yoodaddy0311

멀티에이전트 실증 패턴 - supervisor/swarm/hierarchical 아키텍처, 토큰 multiplier, 컨텍스트 격리, 합의 메커니즘. Auto-activates when: multi-agent system design, agent coordination, context isolation needs. Triggers: multi-agent, supervisor, swarm, agent coordination, 멀티에이전트, 에이전트 협업

통합 관측성 가이드 — Prometheus, Grafana, 분산 트레이싱, SLI/SLO, 알림 규칙. Use when setting up monitoring, tracing, or alerting. 자연어 트리거: '모니터링 설정해줘', '관측성 구성', 'SLO 정의해줘', '알림 규칙 만들어'.

Catalog of agent orchestration patterns: agents-as-tools, handoff with history filter, deterministic workflows, parallelization, and LLM-as-judge loops. Triggers: orchestration, multi-agent, handoff, agent as tool, agent topology, parallelize agents, LLM-as-judge.

Routing intelligence engine that analyzes requests and routes to optimal agents, skills, and commands. Supports two delegation modes: Sub-Agent (Task tool) for focused tasks and Team Mode (Agent Teams API) for complex multi-domain coordination. Auto-activates when: complex multi-step requests, team composition needed, multi-domain tasks, ambiguous intent. Triggers: orchestrate, build, implement, design, route, complex, multi-step, team, coordinate 한국어: 오케스트레이션, 팀 구성, 복잡한 작업, 병렬 처리, 위임, 조율

Curated open-source AI catalog reference. Auto-activates when llm-architect, content-marketer, data-analyst, mcp-developer, backend-developer, or any agent needs to RECOMMEND an open-source AI tool, model, framework, inference engine, vector DB, or agent/RAG library to the user. Provides category-indexed lookup across 14 domains (Deep learning frameworks, Foundation models, Inference engines, Agentic AI, RAG/Vector DBs, Generative media, Training/Fine-tuning, MLOps, Evaluation, Safety, Specia...

Evidence-based root cause analysis decision framework for systematic debugging and investigation. Use when user asks to analyze, investigate, debug, troubleshoot, diagnose, or find root cause of issues, or mentions 분석, 조사, or 근본 원인.

Systems architecture decision framework with long-term thinking focus on scalability, modularity, and dependency management. Use when user discusses architecture, system design, scalability, module boundaries, trade-off analysis, dependency graphs, or ADR decisions, or mentions 아키텍처, 설계, or 확장성.

Reliability-focused backend decision framework for API design, database operations, and server-side systems. Use when user works on API endpoints, database schemas, authentication, middleware, REST or GraphQL services, or mentions server, backend, 서버, 백엔드, or 인증.

Infrastructure automation and reliability engineering decision framework for deployment pipelines and observability. Use when user mentions deployment, CI/CD, Docker, Kubernetes, monitoring, infrastructure as code, or pipeline automation. Triggers: deploy, infrastructure, CI/CD, DevOps, pipeline, monitoring, 배포, 인프라.

Distill a person, role, or character into a reusable persona skill via the 6-layer schema. Use when the user wants to compile a colleague, an internal role archetype, or an authoring style into a persona-* skill — not when invoking an existing persona.

UX and accessibility-focused frontend decision framework for component creation, responsive design, and Core Web Vitals optimization. Use when user creates UI components, works on responsive design, accessibility or WCAG compliance, CSS, React, Vue, or design systems, or mentions 컴포넌트, 반응형, or 접근성.

Educational and knowledge transfer decision framework for explanations, tutorials, and learning guidance. Use when user asks to explain, learn, understand, or teach concepts, requests step-by-step guidance, asks how or why something works, or mentions 설명, 배우기, or 이해.

Measurement-driven optimization decision framework for bottleneck elimination, profiling, and performance budgets. Use when user reports slow performance, requests optimization, needs benchmarking or profiling, works on latency or throughput issues, or mentions 성능, 최적화, or 병목.

Prevention-focused quality assurance decision framework for testing strategy, coverage analysis, and edge case detection. Use when user works on tests, quality validation, TDD workflow, coverage improvement, regression prevention, or edge cases, or mentions 품질, 테스트, or 검증.

Code quality and technical debt management decision framework for systematic refactoring and simplification. Use when user requests refactoring, code cleanup, technical debt reduction, code smell detection, complexity reduction, or DRY improvements, or mentions 리팩토링 or 코드 품질.

Professional documentation and localization decision framework for technical writing, API docs, and multilingual content. Use when user creates documentation, writes guides or READMEs, drafts changelogs or PR descriptions, needs localization, or mentions 문서, 작성, or 가이드.

Security-first decision framework for threat modeling, vulnerability assessment, and compliance review. Use when user discusses security concerns, authentication design, encryption, OWASP compliance, XSS or CSRF prevention, or vulnerability remediation, or mentions 취약점, 보안, or 위협.

Provides authentication and authorization patterns including JWT, OAuth2, RBAC, session management, and managed auth services like Auth0 and Clerk. Use when the user asks about login flows, access control, OAuth or OIDC, JWT tokens, or CSRF protection. Triggers: authentication, authorization, OAuth, JWT, RBAC, session, Auth0, Clerk.

Provides cloud database patterns for serverless PostgreSQL, real-time databases, and edge-compatible data access (Neon, Supabase, Firebase, PlanetScale). 자연어 트리거: '클라우드 DB 골라줘', 'Supabase 연동해줘', '서버리스 데이터베이스 설정', '커넥션 풀링 구성'.

Provides deployment patterns for modern applications: cloud platforms, Docker, Kubernetes, and CI/CD. 자연어 트리거: '배포 파이프라인 설정해줘', 'Vercel 배포해줘', 'Dockerfile 작성해줘', '쿠버네티스 배포 구성'.

AI-slop auto-detection and human-voice rewriting for any text output produced by Artibot agents (content-marketer, copywriter, ad-specialist, presentation-designer, seo-specialist, doc-updater). Auto-activates on every content-producing agent's output — user does NOT need to invoke this skill. Detects mechanical AI patterns (korean: "~에 대해 살펴보겠습니다", "~라고 할 수 있습니다", "또한/그러나/따라서" 과용, 획일적 문장 길이; english: delve/leverage/pivotal/robust/tapestry/"It's important to note"/"In conclusion" 남용) and rewr...

Designs presentation structures with narrative arcs, slide layouts, visual hierarchy, and speaker notes for pitch decks, reports, and keynotes. Use when user asks about presentation design, slides, pitch deck, keynote, PowerPoint, slide layout, speaker notes, 프레젠테이션, 슬라이드, 발표자료, or 피치덱.

Core development principles enforcing SOLID, DRY, KISS, YAGNI, and quality-first design. Auto-activates when: writing code, making design decisions, refactoring, reviewing architecture. Triggers: design, architecture, refactor, pattern, principle, SOLID, clean code

Auto-activates when the user asks to improve, enhance, audit, or propose changes without specifying a concrete problem — especially "개선", "보완", "발전방안", "제안", "감사", "전수조사", "업그레이드", "더 좋게", "추가하면 좋을", "enhance", "improve", "propose", "audit", "optimization", YAGNI, over-engineering, "필요한가", "어떻게 하면 더 좋아질까", "무엇을 더 보강할 수 있을까", "개선안 좀 찾아봐". Also fires when a candidate list of proposals exists and none has been cross-checked against live code evidence yet.

자율 코드베이스 스캔 방법론 - 라인별 분석, 보안/성능/아키텍처/품질 이슈 탐지, 기업급 변환 체크리스트. Auto-activates when: production readiness audit, codebase security scan, enterprise quality check. Triggers: production audit, code audit, make production-ready, 프로덕션 감사, 코드 감사

프롬프트 캐시 최적화 전략 — Dynamic Boundary 배치, 토큰 예산 관리, 정적·동적 영역 분리. 자연어 트리거: '프롬프트 캐시 최적화해줘', '토큰 예산 관리', '캐시 효율 높여줘', 'CLAUDE.md 레이아웃 정리'.

프롬프트 엔지니어링 패턴 - Few-shot, Chain-of-Thought, 시스템 프롬프트 설계, 템플릿 시스템, 최적화 기법. Auto-activates when: prompt optimization, system prompt design, few-shot learning, CoT prompting. Triggers: prompt engineering, few-shot, chain of thought, system prompt, 프롬프트 설계, prompt audit, 프롬프트 감사, 프롬프트 품질

ATLAS Quality Framework for Artibot: Automated, Tested, Learned, Adaptive, Secure. Defines the validation cycle, coverage targets, and GRPO-driven continuous quality improvement. Auto-activates when: reviewing code, setting quality gates, running a validation cycle, or assessing coverage. Triggers: quality framework, ATLAS, validation cycle, quality gate, coverage threshold, 품질 게이트, 커버리지, 품질 검토.

Interactive first-run quickstart guide with project type detection and command suggestions for new user onboarding. Use when user says quickstart, getting started, first run, new project, onboarding, welcome, or setup, or needs help navigating available commands for the first time.

Clones and benchmarks external git repositories against Artibot with quantified 10-dimension scoring, structural comparison, pattern extraction, and adoption recommendations. Use when user asks to compare repos, benchmark a project, analyze external code, evaluate competitors, 레포 비교, 벤치마크, 외부 레포 분석, or 채택 평가.

Executive summaries and data narratives with templates for weekly, monthly, and quarterly cadences. Use when user asks about executive summary, performance recap, weekly digest, monthly rollup, marketing report, 리포트, 성과 보고서, 주간 보고서, 월간 보고서, 성과 리포트 만들어줘, 이번 달 마케팅 보고서 써줘, or 임원 요약 만들어줘.

CronCreate-based automatic scheduling for the nightly-learner pipeline and drift checks. Activates learning jobs within the current Claude Code session using in-memory cron scheduling. Triggers: schedule learning, cron learning, nightly learner schedule, 학습 스케줄, 자동 학습

Security standards and checklist enforcing OWASP Top 10, secret management, and input validation. Auto-activates when: API endpoints, authentication, user input handling, data storage, deployment. Triggers: security, auth, password, token, secret, API key, input, validate, sanitize, encrypt, 보안, 인증, 비밀번호, 토큰, API 키, 입력 검증, 암호화

Develops audience segmentation strategies with lead scoring models, behavioral triggers, persona development, and RFM analysis across demographic, firmographic, and psychographic dimensions. Use when user asks about segmentation, audience segment, lead scoring, persona, behavioral targeting, cohort, RFM, 세그먼테이션, 타겟팅, 리드 스코어링, or 페르소나.

Self-Rewarding + GRPO hybrid evaluation system for autonomous quality assessment, optimization, and improvement. Combines Meta Self-Rewarding patterns with Group Relative Policy Optimization (GRPO) for rule-based self-learning without judge AI. Auto-activates when: task completed, quality review needed, performance trends requested, team optimization needed. Triggers: evaluate, self-assess, quality, improve, performance, trend, score, feedback, grpo, optimize, candidates, compare

Toolformer + GRPO self-learning tool selection system. Tracks tool usage patterns, learns success rates per context, applies group relative policy optimization for comparative tool ranking, and recommends optimal tools. Auto-activates when: tool selection is ambiguous, repeated tool failures detected, or new task patterns encountered without prior history. Triggers: tool selection, which tool, best tool, recommend tool, optimize tools, GRPO, group comparison, 도구 추천, 도구 선택, 최적 도구

SEO strategy covering keyword research, search intent, ranking factors, keyword clustering, and GEO (Generative Engine Optimization). Use when user asks about SEO strategy, keyword research, search intent, ranking factors, content gaps, SEO roadmap, GEO, 검색엔진최적화, 키워드 리서치, 검색 의도, 키워드 뭐로 잡을지 알려줘, SEO 로드맵 짜줘, or 검색 상위 노출 전략 세워줘.

Automatic session work journal maintained in auto-memory, recording tasks, decisions, and pending items for recovery. 자연어 트리거: '작업 기록해줘', '세션 로그 남겨줘', '오늘 한 일 정리', '결정 사항 기록'.

Artibot 초기 설정 인터랙티브 위저드 — 언어, 개발 환경, Agent Teams, MCP 서버, 권한, Git 자동화를 단계별로 안내. Auto-activates when: first install, setup wizard, artibot 설정, initial configuration. Triggers: /setup, /artibot setup, setup wizard, 초기 설정, artibot 설정

Use when creating or editing a SKILL.md. 자연어 트리거: '스킬 만들어줘', '새 스킬 추가', '스킬 작성해줘', 'skill 만들기', '스킬 프론트매터 고쳐줘', 'create a skill', 'edit SKILL.md'.

Creates multi-platform social media content with scheduling strategy, engagement optimization, platform-specific formats, and content calendars. Use when user asks about social media, Twitter, LinkedIn, Instagram, TikTok, YouTube, content calendar, hashtag strategy, social engagement, 소셜 미디어, 소셜 콘텐츠, or 콘텐츠 캘린더.

Grounds every framework, library, and SDK implementation decision in current official documentation rather than training data. Auto-activates when framework-specific code is requested, a version migration is underway, or best-practice verification is needed. Pairs with sdd-cache hook for cheap revalidation. Triggers: framework, library, SDK, current best practice, official docs, MDN, deprecated, migration, API reference, version migration, 공식 문서, 마이그레이션, 최신 문서, API 레퍼런스, 공식 문서 보고 짜줘, 이 라이브러리 ...

SPEC format for structured requirements, acceptance criteria, and technical specifications. Use when the user asks about requirements, acceptance criteria, or technical specs. Triggers: spec, requirements, specification, acceptance criteria, EARS, user story.

Cross-session multi-worktree split — opens N Claude Code windows on stems with non-overlapping file ownership and reads completion from git trailers. Use when the user asks for parallel windows, multi-worktree fan-out, or cross-session coordination on one repo. Triggers: split, 창 나눠서, 여러 창으로, multi-worktree, 워크트리 병렬, cross-session, 세션 나눠서, 줄기 분할.

Context compaction timing strategy — suggests WHEN to trigger compaction based on context usage patterns. Auto-activates when: context >75%, PreCompact triggered, long sessions, multi-phase tasks. Triggers: strategic compact, context strategy, compress timing, long session, context window, memory pressure See also: compaction-survival (정보 보존 전략)

Federated Swarm Intelligence for collective learning across Artibot instances. Shares anonymized learning patterns (tool success rates, error signatures, team compositions) with the swarm network while preserving privacy through PII scrubbing and differential privacy. Enables all participants to benefit from collective experience without exposing individual data. Triggers: swarm, collective, federated, sync patterns, share learning, global weights, opt-in, contribution

Systematic debugging methodology enforcing root cause investigation before any fix. Iron Law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Auto-activates when: debugging errors, investigating failures, fixing bugs, troubleshooting issues. Triggers: debug, bug, error, fix, investigate, troubleshoot, root cause, regression, crash, 디버그, 버그, 에러, 수정

Test-first discipline for new features, bug fixes, and coverage work. Auto-activates when tests are requested, TDD is mentioned, or refactoring needs a safety net. Triggers: test, TDD, test-driven, coverage, unit test, red green refactor, 테스트, 커버리지, 테스트 먼저 써줘, TDD로 짜줘, 테스트 커버리지 올려줘

Parallel team execution with cross-check — the leader delegates, teammates work independently, then verify each other. Use when the user asks for parallel independent work with cross-verification. Triggers: team, parallel team, cross-check, verification, 팀, 병렬 팀, 팀원들, 병렬로.

Audits and optimizes technical SEO covering site structure, crawlability, Core Web Vitals, schema markup, and indexation with scoring checklists. Use when user asks about technical SEO audit, site speed, Core Web Vitals, schema markup, crawlability, robots.txt, sitemap, page speed, 테크니컬 SEO, 사이트 속도, or 크롤링.