Gojiberry AI
AI agents that find and contact high-intent leads for you
Try Gojiberry free →
Hermes Agent
Run your Hermes agent, fully managed
Launch on Hostinger →
Hostinger VPS
Spin up a VPS in one click, 20% off
Launch on Hostinger →
Firecrawl
Crawl and scrape any site into clean data
Try Firecrawl free →
Runable
One AI agent to build, run, and grow your business
Try Runable free →
Context.dev
One API to scrape, enrich, and extract the web
Start building free →
Jotform
Forms, workflows, and AI Agents for your team
Try Jotform free →
Runable
One AI agent to build, run, and grow your business
Try Runable free →
OpenClaw
Deploy a managed OpenClaw agent in 60 seconds
Launch on Hostinger →
Sponsor here
9/10 sponsor slots taken — 1 left
Claim it →
Claude Market
Menu
SkillsMCPPluginsMarketplacesNewsletterSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Claude Market
SkillsMCPPluginsMarketplacesNewsletterSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Skills/ai-native-camp/camp-2/team-assemble
team-assemble logo

team-assemble

ai-native-camp/camp-2
1K installs17 stars
Run it on Hostinger, 20% off →Your friend gets 20% off too, using this linkFree API →|Command ExecutionPrompt InjectionData Exfiltration|View on GitHub|Create your own skill →

Installation

npx skills add https://github.com/ai-native-camp/camp-2 --skill team-assemble

Summary

This skill should be used when the user asks to "팀 구성해줘", "team assemble", "전문가 팀으로 해줘", "팀으로 해줘", "swarm", "병렬로 전문가 팀", or wants to decompose a complex task into specialist roles executed via TeamCreate. Also triggers when user describes a task clearly benefiting from parallel expert execution.

SKILL.md

Team Assemble

작업을 분석하여 전문가 팀을 동적으로 구성하고 TeamCreate 기반으로 즉시 실행하는 스킬.

When to Use

  • 독립적인 하위 작업 2개 이상으로 분해 가능한 복잡한 태스크
  • 리서치 + 구현 + 검증처럼 역할 분리가 명확한 작업
  • 병렬 실행으로 시간을 절약할 수 있는 작업

사용하지 말 것: 단일 파일 수정, 간단한 질문, 순차적으로만 가능한 작업

Workflow

digraph team_assemble {
  rankdir=TB;
  "사용자 입력" [shape=doublecircle];
  "Phase 1:\n작업 분석 & 팀 설계" [shape=box];
  "사용자 승인?" [shape=diamond];
  "Phase 2:\nTeamCreate & TaskCreate" [shape=box];
  "Phase 3:\nTeammate 실행" [shape=box];
  "Phase 4:\n결과 종합 & 정리" [shape=box];
  "완료" [shape=doublecircle];

  "사용자 입력" -> "Phase 1:\n작업 분석 & 팀 설계";
  "Phase 1:\n작업 분석 & 팀 설계" -> "사용자 승인?";
  "사용자 승인?" -> "Phase 1:\n작업 분석 & 팀 설계" [label="수정"];
  "사용자 승인?" -> "Phase 2:\nTeamCreate & TaskCreate" [label="승인"];
  "Phase 2:\nTeamCreate & TaskCreate" -> "Phase 3:\nTeammate 실행";
  "Phase 3:\nTeammate 실행" -> "Phase 4:\n결과 종합 & 정리";
  "Phase 4:\n결과 종합 & 정리" -> "완료";
}

---

Phase 1: 작업 분석 & 팀 설계

작업을 분석하여 다음을 결정:

  1. 역할 분해 — 독립적인 하위 작업으로 분해하고 전문가 역할 부여
  2. 모델 선택 — 역할별 최적 모델 배정
  3. 의존성 그래프 — 선행 관계 결정

역할-모델 매핑

역할 유형모델예시
기획/설계/의사결정opusarchitect, planner, lead
분석/리서치/복잡한 판단opusanalyzer, researcher, code-reviewer
구현/실행/수집sonnetimplementer, collector, writer
검증/정리/포맷팅sonnetvalidator, formatter, tester

경계 역할 판단: "새로운 판단을 내려야 하는가?" → opus. "주어진 기준대로 실행하는가?" → sonnet.

팀 구성 제안

AskUserQuestion으로 반드시 승인을 받은 후 진행:

팀 구성 제안: {team-name}

| # | 역할 | 모델 | 담당 작업 | 의존성 |
|---|------|------|----------|--------|
| 1 | role-name | opus | 작업 설명 | - |
| 2 | role-name | sonnet | 작업 설명 | #1 |

Options: "좋아요, 실행해주세요" / "역할 수정이 필요해요"

"역할 수정" 선택 시 구체적으로 뭘 바꿀지 질문. 2회 이상 수정 요청 시 자유 텍스트 입력으로 전환.

---

Phase 2: 팀 생성 & 태스크 분배

승인 후 순서대로 실행:

TeamCreate(team_name: "{keyword}-team", description: "작업 설명")

team_name 규칙: 작업 핵심 키워드 + -team (예: migration-team, research-team)

각 역할별 TaskCreate 호출 후 TaskUpdate로 blockedBy 의존성 설정:

TaskCreate(subject: "#1 {역할}: {작업 요약}", description: "상세 설명", activeForm: "{작업} 진행 중")
TaskUpdate(taskId: "2", addBlockedBy: ["1"])

---

Phase 3: Teammate 실행

핵심 메커니즘: Task 도구는 foreground(기본)에서 blocking — teammate가 끝날 때까지 대기하고 결과 텍스트를 반환. 이 반환값이 teammate의 작업 결과.

병렬 실행

blockedBy가 없는 태스크들을 단일 메시지에서 동시에 Task 호출:

Task(name: "analyst", team_name: "...", subagent_type: "general-purpose", model: "opus", prompt: "...", mode: "bypassPermissions")
Task(name: "collector", team_name: "...", subagent_type: "general-purpose", model: "sonnet", prompt: "...", mode: "bypassPermissions")
// 두 Task 완료 후 각각의 결과 텍스트 수신

순차 실행 (의존성)

선행 Task의 반환값을 다음 teammate 프롬프트에 삽입:

Task(name: "writer", prompt: "선행 작업 결과:\n{result_1}\n\n이 결과를 바탕으로...")

Teammate 프롬프트 필수 요소

  1. 맥락 — 전체 프로젝트와 이 작업의 관계
  2. 구체적 목표 — 정확히 무엇을 달성해야 하는지
  3. 제약조건 — 하지 말아야 할 것, 변경 범위 제한
  4. 출력 형식 — 결과물 형태 (텍스트/파일/테이블)
  5. 팀 정보 — team_name, task ID → TaskUpdate 완료 표시 지시

상세 프롬프트 템플릿은 references/prompt-templates.md 참조.

---

Phase 4: 결과 종합 & 정리

결과 수집

모든 teammate 결과를 종합하여 사용자에게 보고:

## 팀 실행 결과: {team-name}
### 1. {역할}: {작업}  →  {결과 요약}
### 최종 산출물
- {파일 경로 또는 결과물 목록}

팀 정리

foreground Task 완료 후 teammate는 idle 상태. 정리 순서:

SendMessage(type: "shutdown_request", recipient: "{name}", content: "작업 완료")
TeamDelete()  // 모든 teammate 종료 확인 후

shutdown_request에 응답 없으면 이미 종료된 것 — 무시하고 TeamDelete 진행.

---

Common Mistakes

실수올바른 방법
사용자 승인 없이 팀 생성Phase 1에서 반드시 AskUserQuestion으로 승인
모든 작업을 순차 실행독립 작업은 단일 메시지에서 병렬 Task 호출
teammate 프롬프트가 모호맥락 + 목표 + 제약 + 출력형식 필수 포함
TeamDelete 누락반드시 shutdown_request → TeamDelete 순서로 정리
모든 역할에 opus 사용실행/수집 역할은 sonnet으로 비용 절약

Quick Reference

Phase 1: 분석 → AskUserQuestion (팀 구성 승인)
Phase 2: TeamCreate → TaskCreate × N → TaskUpdate (의존성)
Phase 3: Task × N (병렬) → 결과 전달 → Task × N (후속)
Phase 4: 결과 종합 → shutdown_request × N → TeamDelete

Additional Resources

Reference Files

  • references/examples.md — DB 마이그레이션, 경쟁사 분석, 풀스택 구현 등 3개 worked example (전체 Phase 1~3 흐름)
  • references/prompt-templates.md — 역할별 teammate 프롬프트 템플릿 (analyst, implementer, validator) 및 작성 팁

Score

0–100
63/ 100

Grade

C

Popularity15/30

1,133 installs — growing adoption.

Completeness27/30

Documented: full SKILL.md body, description, one-line install. Missing: category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Team Assemble skill score badge previewScore badge

Markdown

[![Team Assemble skill](https://www.claudemarket.ai/skills/ai-native-camp/camp-2/team-assemble/badges/score.svg)](https://www.claudemarket.ai/skills/ai-native-camp/camp-2/team-assemble)

HTML

<a href="https://www.claudemarket.ai/skills/ai-native-camp/camp-2/team-assemble"><img src="https://www.claudemarket.ai/skills/ai-native-camp/camp-2/team-assemble/badges/score.svg" alt="Team Assemble skill"/></a>

Team Assemble FAQ

How do I install the Team Assemble skill?

Run “npx skills add https://github.com/ai-native-camp/camp-2 --skill team-assemble” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Team Assemble skill do?

This skill should be used when the user asks to "팀 구성해줘", "team assemble", "전문가 팀으로 해줘", "팀으로 해줘", "swarm", "병렬로 전문가 팀", or wants to decompose a complex task into specialist roles executed via TeamCreate. Also triggers when user describes a task clearly benefiting from parallel expert execution. The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Team Assemble skill free?

Yes. Team Assemble is a free, open-source skill published from ai-native-camp/camp-2. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Team Assemble work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Team Assemble works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.9M installsInstall
grill-me logo

grill-me

mattpocock/skills

819K installsInstall
frontend-design logo

frontend-design

anthropics/skills

763K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

697K installsInstall
improve-codebase-architecture logo

improve-codebase-architecture

mattpocock/skills

672K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

653K installsInstall

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideHow To Build Your First Openclaw SkillGuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before Installing

Skills by category

FrontendBackend & APIsTesting & QASecurityDevOps & CI/CDMCP & ToolingAutomationData & Analysis+27 more

MCP servers by category

MCP & ToolingBackend & APIsData & AnalysisDevOps & CI/CDAutomationSecurityDocsTesting & QA+24 more

Plugins by category

AutomationDevOps & CI/CDData & AnalysisDesign & CreativeSecurityBackend & APIsFrontendTesting & QA+16 more

Marketplaces by category

AutomationData & AnalysisDevOps & CI/CDDesign & CreativeFrontendBackend & APIsTesting & QASecurity+21 more

The Agent Stack

Weekly Claude Code, Agent SDK, and MCP moves worth your time — free.

Claude Market

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

Independent project, not affiliated with Anthropic.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Plugins
  • Browse Marketplaces
  • Newsletter

More

  • Submit a Tool
  • Create a Skill
  • Advertise
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy
© 2026 Claude Market · Not affiliated with Anthropic
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed