Reactive Observer-Worker: Playwright Observer가 상주하며 Worker 코드 변경을 즉시 검증하고, 설계 불일치 시 즉각 피드백하는 폐쇄 루프(Closed-Loop) 개발 스킬. Use when asked to "reactive dev", "reactive build", "build with live feedback", "실시간 검증 개발", "리액티브 개발", "Observer-Worker 개발", or when feature implementation requires continuous Playwright verification. Requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1.
EnglishUse when the user asks to "audit infra", "infra audit", "인프라 감사", "인프라 검사", "check infrastructure", "health check", "infra health", "설정 검사", or "인프라 건강도". Claude Code 인프라(CLAUDE.md, hooks, skills, rules, scripts, agents, MCP)의 종합 건강도를 점수(0-100) + 등급(S/A/B/C/F)으로 진단하고, 하니스 5축(CE/AC/GC/EL/SI) 기여도를 매핑한다.
EnglishOODA Loop 기반 적응적 실행 스킬. Observe-Orient-Decide-Act 순환으로 실행 중 환경 변화에 적응한다. Use when "/ooda", "적응적으로 진행해", "상황 변했어", "계획 수정 필요", "중간 점검", "방향 재설정", or during long tasks (5+ turns) as checkpoint. NOT for: simple one-shot tasks, initial planning (use /what), problem classification (use /cynefin).
EnglishQA testing using Playwright MCP tools with multi-expert panel analysis. Use when asked to "test this page", "QA test", "check UI bugs", "test website", "run QA checks", "QA 테스트", "버그 확인", or "웹 테스트". Supports 3 tiers: basic (~30), --full (~80), --all (175 items). Routes to agent-teams when AGENTTEAMS=1, to uiux-audit with --audit flag.
English구조화된 사고 프레임워크. Why-What-How-So What 4단계로 근본 목적을 역추적·정립. Use when "what 분석", "what 정리", "what 파악", "목적 정리", "왜 하는 건지 정리", "의도 분석", "기획 의도", or user prefixes request with "what" in structured thinking context. NOT for: "what is X?" simple knowledge questions, "what does X do?" explanations.
English2단계 파이프라인: What 목적 정립 → CE 프롬프트 최적화. Stage 1이 Why-What-How-So What 4단계로 진짜 목적을 정립하고, 그 결과가 자동으로 Stage 2 CE+PE 최적화의 입력이 된다. Use when "what-ce", "목적 정립 후 최적화", "what then ce", "what ce", "프롬프트 최적화 전에 목적부터", or when user wants to clarify purpose before optimizing execution. Fast mode: add "--fast" to compress Stage 1 confirmation. NOT for: "what is X?" knowledge questions, standalone CE advice (use ce-advisor), standalone purpose analysis (use what).
English
AGENT SKILLS ATLASIncludes Agent Teams Reactive Dev, Infra Audit, Playwright QA Expert, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agent Teams Reactive Dev
Reactive Observer-Worker: Playwright Observer가 상주하며 Worker 코드 변경을 즉시 검증하고, 설계 불일치 시 즉각 피드백하는 폐쇄 루프(Closed-Loop) 개발 스킬. Use when asked to "reactive dev", "reactive build", "build with live feedback", "실시간 검증 개발", "리액티브 개발", "Observer-Worker 개발", or when feature implementation requires continuous Playwright verification. Requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1.
Infra Audit
Use when the user asks to "audit infra", "infra audit", "인프라 감사", "인프라 검사", "check infrastructure", "health check", "infra health", "설정 검사", or "인프라 건강도". Claude Code 인프라(CLAUDE.md, hooks, skills, rules, scripts, agents, MCP)의 종합 건강도를 점수(0-100) + 등급(S/A/B/C/F)으로 진단하고, 하니스 5축(CE/AC/GC/EL/SI) 기여도를 매핑한다.
Ooda
OODA Loop 기반 적응적 실행 스킬. Observe-Orient-Decide-Act 순환으로 실행 중 환경 변화에 적응한다. Use when "/ooda", "적응적으로 진행해", "상황 변했어", "계획 수정 필요", "중간 점검", "방향 재설정", or during long tasks (5+ turns) as checkpoint. NOT for: simple one-shot tasks, initial planning (use /what), problem classification (use /cynefin).
Playwright QA Expert
QA testing using Playwright MCP tools with multi-expert panel analysis. Use when asked to "test this page", "QA test", "check UI bugs", "test website", "run QA checks", "QA 테스트", "버그 확인", or "웹 테스트". Supports 3 tiers: basic (~30), --full (~80), --all (175 items). Routes to agent-teams when AGENTTEAMS=1, to uiux-audit with --audit flag.
What
구조화된 사고 프레임워크. Why-What-How-So What 4단계로 근본 목적을 역추적·정립. Use when "what 분석", "what 정리", "what 파악", "목적 정리", "왜 하는 건지 정리", "의도 분석", "기획 의도", or user prefixes request with "what" in structured thinking context. NOT for: "what is X?" simple knowledge questions, "what does X do?" explanations.
What Ce
2단계 파이프라인: What 목적 정립 → CE 프롬프트 최적화. Stage 1이 Why-What-How-So What 4단계로 진짜 목적을 정립하고, 그 결과가 자동으로 Stage 2 CE+PE 최적화의 입력이 된다. Use when "what-ce", "목적 정립 후 최적화", "what then ce", "what ce", "프롬프트 최적화 전에 목적부터", or when user wants to clarify purpose before optimizing execution. Fast mode: add "--fast" to compress Stage 1 confirmation. NOT for: "what is X?" knowledge questions, standalone CE advice (use ce-advisor), standalone purpose analysis (use what).
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agent Teams Reactive Dev skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.