artibot

(Artibot) Ad copy creation, creative briefs, campaign structure, and A/B variant generation for paid channels

(Artibot) ADR(Architecture Decision Record) 작성 - 두 개 이상 기술 선택지의 trade-off, 숨겨진 비용, 2년 뒤 부채까지 7섹션으로 비교하고 추천안 제시

(Artibot) Adversarial code review from attacker's perspective using code-reviewer + security-reviewer agents

(Artibot) Marketing analytics dashboards, KPI tracking, performance reports, and attribution analysis

(Artibot) Multi-dimensional code and system analysis with agent delegation

Backend specialist focused on API design, server-side reliability, and data integrity. Expert in Python FastAPI, Node.js (Express/Fastify), PostgreSQL, Redis, and microservices. Use proactively when building APIs, implementing server logic, designing data models, or optimizing backend performance and security. Triggers: API, endpoint, server, database, authentication, middleware, FastAPI, Express, 백엔드, 서버, 인증, 데이터베이스 Do NOT use for: UI components, CSS styling, frontend state management, DevOps pipelines

Build and TypeScript error resolution specialist. Diagnoses compilation failures, type errors, and dependency issues. Applies minimal, targeted fixes only. Use proactively when build fails, TypeScript reports type errors, dependency resolution fails, or CI pipeline breaks on compilation. Triggers: build error, type error, compilation failed, tsc error, build failed, 빌드 오류, 타입 에러, 컴파일 실패, 빌드 실패 Do NOT use for: runtime bugs, logic errors, performance issues, feature implementation

LLM integration specialist focused on prompt engineering, model orchestration, RAG pipelines, and AI application architecture. Expert in Claude, OpenAI, LangChain, and vector databases. Use proactively when designing AI-powered features, building prompt chains, implementing RAG systems, or optimizing LLM cost and latency. Triggers: LLM, prompt, RAG, embedding, AI, Claude, OpenAI, vector database, agent, 프롬프트, 임베딩, AI 아키텍처, 벡터 DB Do NOT use for: traditional backend logic, CSS styling, database schema without AI context

Systems architecture specialist focused on long-term maintainability, scalability, and structural integrity. Evaluates trade-offs, designs module boundaries, and defines dependency strategies. Use proactively when making architectural decisions, designing new systems or modules, evaluating structural trade-offs, or planning large-scale refactoring. Triggers: architecture, design, scalability, system design, module boundary, dependency, 아키텍처, 설계, 확장성, 시스템 설계, 모듈 경계 Do NOT use for: implementation details, bug fixes, styling, test writing, DevOps

CTO-level team leader for complex multi-step projects using Claude Agent Teams API. Creates teams, spawns specialized teammates, distributes tasks, manages quality gates, and coordinates collaboration through native team messaging and task management. Use proactively when multi-step project coordination, team composition, cross-domain implementation, or architectural decisions spanning multiple agents are needed. Triggers: team, orchestrate, coordinate, project lead, multi-agent, delegate, 팀, 오케스트레이션, 조율, 프로젝트 리드, 다단계, 위임, チーム, オーケストレーション, 調整, プロジェクトリード, マルチエージェント, 委任 Do NOT use for: single-file edits, simple questions, documentation-only tasks

Manages brand identity including voice guidelines, visual standards, messaging consistency, and brand governance with frameworks for style guides and cross-channel consistency. Use when user asks about brand guidelines, brand voice, style guide, brand identity, tone of voice, messaging framework, visual identity, 브랜드 가이드라인, 브랜드 보이스, or 스타일 가이드.

Designs campaign architecture, timelines, cross-channel coordination, and budget allocation for marketing campaigns from planning through measurement. Use when user asks about campaign planning, launch coordination, cross-channel marketing, campaign calendar, UTM tracking, budget allocation, 캠페인 기획, 캠페인 런칭, or 멀티채널.

GitHub Actions 심화 패턴 — matrix strategy, reusable workflows, composite actions, 시크릿 관리, 캐싱 전략. Use when designing CI/CD pipelines, GitHub Actions workflows, or deployment automation. 자연어 트리거: 'CI 파이프라인 만들어줘', '깃헙 액션 워크플로 짜줘', '배포 자동화 해줘', 'GitHub Actions 설정'.

Turns ambiguous user requests into precise, actionable specifications using hypothesis-based MCQ clarification. Auto-activates when ambiguity score exceeds threshold, multi-intent conflicts are detected, or the user explicitly requests clarification on scope, target, or constraints. Triggers: clarify, unclear, what do you mean, ambiguous, vague, specify, 명확히, 구체적으로, 뭘 원하시는지, 좀 더 자세히 말해줘, 어떤 걸 원하는 건지 모르겠어, 범위가 너무 넓어

Audit CLAUDE.md files in a repository against a 6-criteria quality rubric, output a scored report and diff preview, and require user approval before any Edit. 자연어 트리거: 'CLAUDE.md 점검해줘', '메모리 품질 감사', '프로젝트 메모리 검토해줘', 'claude.md audit'.

25 hooks across 15 events

Ultra-compressed output for high context usage (--uc mode)

Default Artibot output style with structured sections

Intelligence output style — surfaces active features and session stats inline

Educational mentor mode - detailed explanations with examples

Narrative structure output style — Hero-Support-Detail-CTA storytelling for CLI analysis reports