Omd:Orchestrator logo

Omd:Orchestrator

Community
kwakseongjae
omd:orchestrator

멀티 에이전트 디자인 워크플로우 supervisor. writer, locale adaptation, humanize, UI slop audit, designer review, final QA, image materialization을 routing한다. 2-round revision cap을 유지하며 다국어 문서·UI 개선·출간 준비처럼 여러 역할이 필요한 요청에 사용한다.

Overview

Publisherkwakseongjae
Repositoryoh-my-design
Skill nameomd:orchestrator
Stars
533
Forks
48
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by kwakseongjae on GitHub. Read the source before you install it.

Installation

Install the Omd:Orchestrator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kwakseongjae/oh-my-design/tree/main/.claude/skills/omd-orchestrator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kwakseongjae/oh-my-design.git /tmp/oh-my-design
mkdir -p .claude/skills
cp -r /tmp/oh-my-design/.claude/skills/omd-orchestrator .claude/skills/kwakseongjae-omd-orchestrator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omd:Orchestrator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Omd:Orchestrator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Omd:Orchestrator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

omd:orchestrator

omd v0.2 agent layer의 supervisor. 한 글/한 컴포넌트가 여러 specialist를 거쳐야 할 때 routing을 책임진다.

채택 패턴: Anthropic orchestrator-workers (Building effective agents, 2024-12) + LangGraph supervisor의 revision-cap. 자세한 비교는 data/research/2026-05-18-agent-landscape.md §1.

런타임 dependency 없음. Claude Code의 subagent 호출 메커니즘이 그대로 orchestrator-workers 토폴로지를 구현한다.

0. Worker 카탈로그

역할subagent용도
Writeromd-kr-writer한국어 본문 작성. preset_id 인자로 voice 결정.
Localizeromd-locale-adapterKR → EN/JA/ZH-CN/ZH-TW adaptation (번역 아님)
Copy finalizeromd-humanizerlocale별 번역투·기계적 구조를 국소 수정하고 보호 구간 대조
Slop auditoromd-slop-auditor실제 route의 context-free UI/copy cluster를 품질·취향과 분리해 감사
Visual revieweromd-designer-reviewDESIGN.md 대비 typo/색/spacing/state 검수
UX engineeromd-ux-engineer실제 route의 interaction·responsive·focus·perceived performance 감사
UX writeromd-ux-writer섹션별 copy·정보 순서·CTA 계약 감사
A11y auditoromd-a11y-auditoraxe/lighthouse/키보드 기반 결정론 gate
Criticomd-final-qaRead-only rubric verdict. 2-round cap 강제.
Image materializeromd-codex-image<!-- omd:gen-image --> 블록을 채널별로 실체화 (Codex native gen / asset-curator fallback / OpenCode user-queue)

1. 입력

사용자 요청. 예:

  • "당근 디자인 시스템 분석 글 작성, KR + EN, 5500자+"
  • "이 컴포넌트 디자인 리뷰 받고 카피 다듬어줘"
  • "이 글 final QA 거쳐서 출간 ready로"

2. Routing decision tree

사용자 요청 도착
├─ "글 작성" 키워드 → Stage 1: omd-kr-writer
├─ "AI 티/번역투/문장이 기계적" → omd-humanizer
├─ 다국어 요청 ("EN", "영문", "JA", "간체", "대만어") → Stage 3 + locale별 humanize 추가
├─ "AI slop/템플릿 같음" + audit만 → omd-slop-auditor
├─ 기존 UI "고쳐/개선/구현" → UI delivery lane → 수정은 caller의 omd:apply
├─ artifact 첨부 + "리뷰" → Stage 2부터 진입
└─ "출간 ready" → Stage 4 final-qa로 직행

2.1 UI delivery lane — advice와 delivery를 분리

기존 UI의 변경 요청에서는 orchestrator가 제품 파일을 직접 편집하지 않는다. 다음 work packet을 먼저 고정하고 필요한 specialist를 최대 3개까지만 선택해 read-only로 실행한다.

yaml
intent: audit | implement
task: <user outcome>
consumer_route: <real user route>
acceptance: []
protected_behaviors: []
evidence: []
unknowns: []
implementation_owner: caller-main-agent
verification:
  routes: []
  viewports: []
  states: []
  commands: []

각 specialist에게는 packet과 필요한 artifact만 전달한다. 응답은 finding / evidence / smallest_useful_change / acceptance_check / unresolved로 정규화한다. orchestrator는 중복·충돌을 합쳐 우선순위가 있는 하나의 implementation handoff를 caller에게 반환한다.

  • intent: audit이면 report로 종료 가능.
  • intent: implement이면 status: advice-ready, implementation_owner: caller-main-agent로 반환한다. 완료·수정됨·검증됨이라고 표현하지 않는다.
  • caller는 omd:apply로 실제 편집한 뒤 packet의 같은 consumer route·viewport·state를 재검증한다.
  • specialist와 caller가 같은 제품 파일을 병렬 수정하지 않는다.

3. 표준 5-stage 워크플로우 (블로그 글 기준)

Stage 1  WRITE       omd-kr-writer  (preset=toss-tech-design)
Stage 1h HUMANIZE    omd-humanizer  (KO 보호 구간 + 자연스러움 검증)
Stage 2  REVIEW      omd-designer-review  (artifact + brand DESIGN.md)
Stage 2r REVISION    omd-kr-writer  (review feedback 반영)  ← max 2 round
Stage 3  LOCALIZE    omd-locale-adapter  (KR → EN/JA/ZH-CN/ZH-TW)
Stage 3h HUMANIZE    omd-humanizer  (각 locale 독립 검증)
Stage 4  CRITIC      omd-final-qa  (rubric, read-only)
Stage 4r REVISION    omd-kr-writer  (final-qa feedback)  ← max 2 round (Stage 2와 별도 카운트)
Stage 4i IMAGES      omd-codex-image  (`<!-- omd:gen-image -->` 블록 처리, 채널별 분기)
Stage 5  HANDOFF     사용자에게 최종 artifact + revision log + image manifest

4. Revision cap (hard)

각 critic gate (designer-review, final-qa)는 최대 2 round.

revision_state = {
  "designer_review": { "round": 0, "max": 2 },
  "final_qa":        { "round": 0, "max": 2 }
}

Round 2 후에도 BLOCK이면:

  1. 사용자에게 escalate ("designer-review가 2회 fail. 강제 통과? 재작성? 폐기?")
  2. 강제 통과 시 known issues 섹션을 artifact frontmatter에 명시
  3. 재작성 시 Stage 1로 회귀, 카운터 리셋

5. Handoff 로그 (필수)

각 stage 전후로 <work_dir>/.orchestrator.log에 append:

[2026-05-18T10:23:11] STAGE=write  agent=omd-kr-writer  status=ok  artifact=content/posts/karrot/index.ko.md
[2026-05-18T10:25:02] STAGE=review agent=omd-designer-review  status=WARN  issues=2
[2026-05-18T10:25:03] STAGE=write  agent=omd-kr-writer  round=2  reason="색 budget 위반 fix"
...

6. State 직렬화

Orchestrator 자체는 stateless. 모든 state는 파일 시스템:

  • artifact: content/posts/<slug>/index.<locale>.md
  • review reports: content/posts/<slug>/.reviews/round-<N>.md
  • final verdict: content/posts/<slug>/.reviews/final-qa.md

7. Subagent 호출 규약

Claude Code subagent 호출 시 다음 envelope:

yaml
agent: omd-kr-writer
inputs:
  work_packet:
    intent: publish
    task: "당근 디자인 분석 글 작성"
    consumer_route: null
    acceptance: ["KO article passes final QA"]
    protected_behaviors: ["facts and source URLs remain unchanged"]
    evidence: ["references/karrot/DESIGN.md"]
    unknowns: []
    implementation_owner: omd-kr-writer
    verification: { routes: [], viewports: [], states: [], commands: [] }
  task: "당근 디자인 분석 글 작성"
  preset_id: toss-tech-design
  brand_design_md: references/karrot/DESIGN.md
  target_length: 6000
  output_path: content/posts/karrot/index.ko.md
revision_round: 0
prior_review: null  # 또는 review report 경로

응답을 받으면 .orchestrator.log에 기록 후 다음 stage 결정.

8. Anti-patterns (금지)

  • 3+ round revision loop — cost runaway. Round 2에서 escalate.
  • Critic의 직접 수정 — final-qa는 read-only. Writer로 round-trip해야.
  • Stage skip — designer-review 없이 final-qa 진입 금지 (rubric 불충분).
  • 병렬 stage 같은 artifact 수정 — race condition. writer/locale-adapter는 직렬.
  • rubber-stamp — final-qa가 "looks good" 응답 시 orchestrator는 rejected로 처리.
  • advice를 delivery로 표시 — implement 요청에서 caller가 제품 파일과 실제 route를 재검증하기 전 done 금지.

9. 병렬화 허용 케이스

  • KR이 PASS된 뒤 EN/JA/ZH-CN/ZH-TW adaptation은 병렬 (각각 다른 파일이라 conflict 없음). ZH-TW는 ZH-CN을 상속하지 않는다.
  • DESIGN.md re-read는 stage마다 강제 (Anthropic best practice — memory hallucination 방지)

10. 종료 조건

  • final-qa verdict = PASS → handoff stage로
  • final-qa round 2 BLOCK → 사용자 escalation
  • 사용자가 명시적으로 abort → .orchestrator.log에 ABORT 기록 후 종료

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Omd:Orchestrator AI skill do?

멀티 에이전트 디자인 워크플로우 supervisor. writer, locale adaptation, humanize, UI slop audit, designer review, final QA, image materialization을 routing한다. 2-round revision cap을 유지하며 다국어 문서·UI 개선·출간 준비처럼 여러 역할이 필요한 요청에 사용한다.

Why use Omd:Orchestrator on TypingMind?

Because you install it once and use it with any model. Omd:Orchestrator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Omd:Orchestrator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kwakseongjae/oh-my-design/tree/main/.claude/skills/omd-orchestrator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Omd:Orchestrator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Omd:Orchestrator?

As many as you like. As long as a model supports skills, you can use Omd:Orchestrator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Omd:Orchestrator AI skill free?

Yes. It is published on GitHub by kwakseongjae under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇