team-orchestrator
Use when orchestrating Agent Teams for parallel development - team composition, task distribution, dependency management, and result aggregation.
Skill by sangrokjung
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sangrokjung-team-orchestrator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/team-orchestrator
What's inside
- Skill name
team-orchestrator- Description
- Use when orchestrating Agent Teams for parallel development - team composition, task distribution, dependency management, and result aggregation. Triggers on /orchestrate, multi-agent coordination, parallel team work, task delegation to teammates.
- License
- MIT
- Instructions
- 280 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Overview team-orchestrator 스킬은 `/orchestrate` 커맨드의 핵심 엔진으로, Agent Teams를 구성하고 작업을 분배하며 결과를 집계하는 오케스트레이션 로직을 정의한다. ## 전제조건 Agent Teams 전제조건(환경변수 설정)은 `reference/agents-teams-ref.md` 참조. --- ## Team Composition ### 팀 크기 결정 최대 팀원 수: Lead 1 + Teammates 3 (총 4명) | 작업 규모 | 팀원 수 | 구성 | |-----------|---------|------| | 소 (파일 1-3개) | 1-2명 | 구현1 (+테스트1) | | 중 (파일 4-8개) | 2-3명 | 구현1-2 + 테스트1 | | 대 (파일 9개 이상) | 3명 | 구현2 + 테스트1 또는 패턴별 분리 | ### 역할 템플릿 **풀스택 기능 구현:** | 역할 | subagent_type | 담당 | |------|--------------|------| | Frontend Dev | general-purpose | UI 구현, 컴포넌트 | | Backend Dev | general-purpose | API, DB, 로직 | | QA Engineer | general-purpose | 테스트, E2E | **리팩토링:** | 역할 | subagent_type | 담당 | |------|--------------|------| | Analyzer | Explore | 코드 분석/계획 | | Implementer | general-purpose | 리팩토링 실행 | | Verifier | general-purpose | 테스트/검증 | **버그 조사:** | 역할 | subagent_type | 담당 | |------|--------------|------| | Investigator 1 | Explore | 코드 분석 | | Investigator 2 | Explore | 로그/환경 분석 | | Fixer | general-purpose | 수정 구현 | --- ## Task Distribution ### 파일 소유권 분리 (CRITICAL) 같은 파일을 2명이 편집하면 덮어쓰기가 발생한다. 반드시 팀원별로 파일 소유권을 분리한다. ``` 파일 소유권 결정 로직: 1. 변경 예상 파일 목록 생성 2. 파일별 모듈/도메인 분류 3. 도메인 단위로 팀원 배정 4. 공유 파일(types, config)은 한 팀원에게 독점 배정 ``` ### 작업 분해 규칙 팀원당 5-6개 Task를 배정한다. | Task 크기 | 판단 기준 | 설명 | |-----------|----------|------| | 너무 작음 | 조율 오버헤드 > 이점 | 하나로 합치기 | | 적절함 | 명확한 결과물이 있는 자체 포함 단위 | 함수, 테스트 파일, 검토 | | 너무 큼 | 체크인 없이 오래 작동 | 더 작게 분할 | ### 의존성 관리 ``` 의존성 그래프 생성: Task A (types 정의) → Task B (API 구현) → Task C (UI 연동) 선행 Task가 완료되어야 후행 Task 시작 가능 순환 의존성 감지 시 경고 ``` TaskCreate에서 `addBlockedBy` 필드로 의존성을 설정한다. --- ## Context Inheritance (CRITICAL) 팀원은 프로젝트 컨텍스트(CLAUDE.md, MCP servers, skills)를 자동 로드하지만, **리더의 대화 기록은 상속하지 않는다.** 따라서 팀원 생성 프롬프트에 반드시 다음을 포함해야 한다: - 작업 목적과 배경 - 관련 파일 경로 - 기대하는 결과물 - 주의사항/제약사항 ``` # 좋은 예시 "Review the authentication module at src/auth/ for security vulnerabilities. Focus on token handling, session management, and input validation. The app uses JWT tokens stored in httpOnly cookies." # 나쁜 예시 "보안 검토 해줘" ← 팀원은 리더가 논의한 맥락을 모름 ``` CLAUDE.md는 정상 작동: 팀원들은 작업 디렉토리에서 CLAUDE.md를 자동으로 읽는다. --- ## Plan Approval Mode 위험하거나 복잡한 작업에서 팀원이 구현 전 계획 승인을 받도록 할 수 있다: ``` Spawn an architect teammate to refactor the auth module. Require plan approval before they make any changes.
From sangrokjung/claude-forge, MIT.
More from sangrokjung/claude-forge
- 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
skill-factory
sangrokjung
Analyze session work and automatically convert reusable patterns into Claude Code skills.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
systematic-debugging
sangrokjung
Structured debugging methodology — use before proposing fixes for any error or failure.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
session-wrap
sangrokjung
Use when wrapping up a session before ending.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
continuous-learning-v2
sangrokjung
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
korean-spell-check
sangrokjung
Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.
SkillBFreshness: B★ 863Claude Code +9 - 0.772score
loop-forge
sangrokjung
Turn a one-line description of a repetitive task into a reusable, self-guarding slash command.
SkillBFreshness: B★ 863Claude Code +9
Signals
- Stars
- 863
- Forks
- 184
- Open issues
- 22
- Last commit (this folder)
- Jun 19, 2026 (4 months ago)
- Last release
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sangrokjung/claude-forge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sangrokjung
- 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9
Cite this page
team-orchestrator skill. Agent Mart. https://agentmart.dev/skills/sangrokjung-team-orchestrator (last updated 2026-10-24)