AI Agent Workflow Collection

Reviews marketing content for legal and regulatory compliance across Korean (PIPA, Act on Fair Labeling, E-Commerce Act) and global (FTC guidelines, GDPR, ASA) frameworks. Identifies risk areas and required disclosures. Use when user asks about ad compliance, legal review, 광고 법규, 표시광고법, 개인정보보호법, 전자상거래법, or marketing legal check.

Designs paid advertising campaigns with creative briefs, platform constraints, and bidding strategy optimization for Google Ads, Meta Ads, and LinkedIn Ads. Use when user asks about advertising, ad copy, paid media, Google Ads, Meta Ads, PPC, retargeting, creative brief, 광고, 유료 광고, or 리타겟팅.

Claude advisor tool strategy for cost-optimized quality retention. Sonnet executor + Opus advisor pattern reduces API cost by ~50% while maintaining near-Opus quality on complex judgment calls. Auto-activates when discussing model cost optimization, executor-advisor delegation, or advisor API integration.

세션 상태를 압축 스냅샷으로 변환하여 서브에이전트 프롬프트에 주입. Use when spawning sub-agents, delegating tasks, or needing session context transfer between agents.

Detects and eliminates AI slop patterns from any text output. Scans for generic filler phrases, hollow adjectives, structural laziness, and robotic cadence that signal AI-generated writing. Run this after any content-creation or copywriting task. Use when user asks about ai slop, ai writing review, text quality check, writing polish, 텍스트 품질, AI 패턴 검사, 슬롭 검사, 글쓰기 품질, AI 글 검토, 문체 교정, 자연스러운 글, 인간 문체, or 글 다듬기.

Fully autonomous nightly learning pipeline — self-scan, pattern extraction, knowledge update, skill refinement, and auto-commit without human intervention. Integrates with claude schedule, Git server webhooks, and existing lib/learning/ modules.

Audit CLAUDE.md files in repository against 6-criteria quality rubric. Auto-activates when: user mentions CLAUDE.md / project memory quality / audit memory. Outputs scored report (A-F grade) + diff preview, requires user approval before Edit.

Detects AI-generated code slop patterns (defensive try/catch wrapping, premature abstractions, builtin wrappers, owner-less TODOs, over-configurable params) and scores 0-100 across five tiers. Gating input for code-reviewer agent. Use when user asks about code slop, AI 코드 검토, over-engineering 탐지, defensive code, boilerplate 코드, PR 리뷰, 코드 품질 게이트, slop detection, or LLM 코드 검증.

Provides codex-plugin-cc integration workflow for cross-checking, development delegation, and idea generation with OpenAI Codex. Use when user asks about Codex, cross-check, 크로스체크, OpenAI CLI, dual-AI review, or wants to delegate tasks to Codex.

Dual-process cognitive routing engine inspired by Kahneman's System 1/2 theory. Routes user requests through fast intuitive pattern matching (System 1) or deep deliberative reasoning (System 2) based on complexity scoring, confidence thresholds, and adaptive learning. Auto-activates on every user request via the cognitive-router hook.

Writes argumentative columns, editorials, and op-eds with contrarian thesis, steelmanned counter-arguments, and layered evidence. Use when user asks about column writing, op-ed, editorial, opinion piece, thought piece, 칼럼, 오피니언, 사설, 논평, or 기고문.

Optimizes forms for lead generation, signups, and data collection with friction reduction, field optimization, validation UX, and progressive profiling strategies. Use when user asks about form optimization, form fields, lead form, signup form, form completion, progressive profiling, form UX, 폼 최적화, 양식, or 리드 폼.

Analyzes multi-step conversion funnels to identify drop-offs and optimize signup flows, onboarding, checkout processes, and lead qualification pipelines. Use when user asks about funnel analysis, conversion funnel, drop-off analysis, signup flow, checkout optimization, onboarding funnel, funnel optimization, 퍼널, 전환 퍼널, or 이탈 분석.

Optimizes landing page conversion rates covering above-the-fold analysis, value proposition clarity, CTA optimization, and trust signal placement with heuristic evaluation. Use when user asks about landing page optimization, page CRO, conversion rate, above the fold, CTA optimization, trust signals, hero section, 랜딩페이지, 페이지 CRO, or 전환율 최적화.

Maps customer journeys with touchpoint analysis, lifecycle stage management, and experience optimization from awareness through advocacy. Use when user asks about customer journey, journey map, touchpoint analysis, lifecycle management, customer experience, onboarding, retention, CX, 고객 여정, 터치포인트, or 라이프사이클.

Design DDD strategic artifacts including subdomains, bounded contexts, and ubiquitous language for complex business domains.

DDD 전술적 설계 - Entity, Value Object, Aggregate, Repository, Domain Service, Domain Event 패턴. Auto-activates when: implementing domain models, aggregate design, invariant enforcement.

Provides structured DESIGN.md schema and curated brand references for AI-native visual design specification. Use when user asks about design system, DESIGN.md, visual design, UI design language, design tokens, color palette, typography system, 디자인 시스템, 비주얼 디자인, 디자인 토큰, or UI 디자인.

Artibot Evolution Loop — conceptual guide to the continuous self-improvement cycle that drives GRPO-based learning, pattern extraction, skill refinement, and collective intelligence growth. Use as reference when configuring, understanding, or extending Artibot's autonomous learning system.

Git 통합 워크플로우 허브 — autopilot, collab (팀 온보딩), conflict (충돌 해결), guide (초보자 가이드), safe (안전망), strategy (브랜치 전략), sync (동기화), workflow (커밋·브랜치·PR), worktree (병렬 브랜치) 9개 서브툴을 통합. Auto-activates when: git, commit, branch, merge, PR, push, pull, rebase, release, conflict, stash, worktree, git flow, github flow, autopilot, 커밋, 브랜치, 머지, 충돌, 푸시, 동기화, 워크트리, git 자동화, 협업, 팀 온보딩 등 git 관련 작업이 감지될 때.

로컬 관측성(observability) 스킬 — Claude Code hook 이벤트를 JSONL 큐로 fan-out하고 localhost WebSocket 브로드캐스트로 대시보드에 노출. 외부 전송 0건, Artibot 내부 전용. Use when building a local hook monitor, agent dashboard, event tap, or any observability surface that must stay on-device.

Hook feedback to tool result merge pattern. Documents how pre/post hook feedback (warnings, blocks, suggestions) gets merged into tool results so the model sees quality signals inline with tool output. Auto-activates when: writing hooks that produce feedback, reviewing hook output flow.

Structures long-form interview storytelling for expert interviews, internal feature stories, and multi-expert roundups. Applies 5W1H question matrix, 3-part answer arc, verbal signposting, NNGroup 4-dimension voice profile, and quote-approval workflow. Use when user asks about interview article, expert interview, feature story, storytelling, quote roundup, 인터뷰 기사, 전문가 인터뷰, 스토리텔링, 인용 모음, or 피처 스토리.

Korean digital marketing specialist for Naver, Kakao, Coupang, and local platform strategies. Covers Naver SEO (C-Rank/DIA), Kakao Moment ads, Korean content formats, PIPA compliance, and domestic consumer behavior. Use when user asks about 한국 마케팅, 네이버 마케팅, 카카오 광고, 쿠팡 마케팅, 국내 디지털 마케팅, or Korea-specific marketing.