Omd:Sync logo

Omd:Sync

Community
kwakseongjae
omd:sync

DESIGN.md 변경분을 CLAUDE.md / AGENTS.md / .cursor/rules/omd-design.mdc shim 3종에 전파. 'shim 갱신', 'drift 확인', 'ship', 'publish', 「shimを更新」, 「同步 CLAUDE.md」류의 요청에 트리거. DESIGN.md가 수정됐는데 shim이 오래됐을 때 자동 감지해 제안하기도 함.

Overview

Publisherkwakseongjae
Repositoryoh-my-design
Skill nameomd:sync
Stars
533
Forks
48
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Omd:Sync 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-sync
  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-sync .claude/skills/kwakseongjae-omd-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omd:Sync 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:Sync 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:Sync 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:sync — Shim Maintenance

DESIGN.md가 모든 주요 AI 코딩 에이전트(Claude Code, Codex, OpenCode, Cursor)에게 보이도록 shim 파일 3종을 관리한다. CLI 호출 없음 — Read/Write/Edit 툴로 직접 처리.

관리 대상 (3 파일)

ID경로모드
claudeCLAUDE.mdblock (managed marker만)
agentsAGENTS.mdblock (managed marker만)
cursor.cursor/rules/omd-design.mdcwhole (전체 파일이 omd 전용)

block 모드는 <!-- omd:start v=1 hash=<sha256:12> --> ~ <!-- omd:end --> 마커 안만 관리, 나머지 사용자 콘텐츠 보존. whole 모드는 frontmatter 포함 전체 파일이 관리 단위.

템플릿 (정확히 이 본문 — 절대 paraphrase 금지)

CLAUDE.md body

markdown
# Design System (oh-my-design)

Read the standalone design contract at **@./DESIGN.md** before any UI,
styling, microcopy, or motion work. When a valid adopted Core v2
`.omd/system/manifest.json` declares `profile: portable-core` and binds exact
graph/projection hashes, the System Graph is machine authority and DESIGN.md is
its standalone projection. A migration candidate is never adopted authority.

Preference log (pending corrections): @./.omd/preferences.md

Precedence: pending explicit preference corrections > adopted Bound System
graph/standalone DESIGN.md > your defaults. Fold pending corrections into the
graph and regenerate the projection before clearing them.

AGENTS.md body

markdown
## Design System (oh-my-design)

**Before any UI, styling, copy, or motion change, open and read `./DESIGN.md` in full.** It is the standalone design contract. If an exact valid adopted Core v2 manifest exists, its hash-bound System Graph is machine authority and DESIGN.md is the projection. A migration candidate remains non-authoritative.

If present, read `./.omd/preferences.md` — pending explicit corrections override the current contract until atomically folded into the graph/projection. Apply them and flag conflicts.

.cursor/rules/omd-design.mdc (whole, frontmatter 포함)

mdc
---
description: Authoritative brand & UI design system. Read DESIGN.md before UI work.
globs:
  - "**/*.tsx"
  - "**/*.jsx"
  - "**/*.vue"
  - "**/*.svelte"
  - "**/*.css"
  - "**/*.scss"
  - "**/tailwind.config.*"
  - "**/components/**"
  - "**/app/**/page.*"
alwaysApply: true
---

<!-- omd:start v=1 hash=<HASH> -->
<!-- omd:cursor-channel=skills -->
Read the standalone design contract at `@DESIGN.md` before generating/modifying UI. With an exact valid adopted `profile: portable-core` manifest, its hash-bound System Graph is machine authority and DESIGN.md is the projection. A migration candidate is non-authoritative.

Pending preference corrections: `@.omd/preferences.md`.

Precedence: pending explicit preference corrections > adopted Bound System graph/standalone DESIGN.md > framework defaults. Fold pending corrections into the graph and regenerate DESIGN.md before clearing them.

OmD Agent Skills live under `.cursor/skills/`. Use the smallest relevant `omd-*` skill automatically, or invoke it from Cursor with `/omd-<name>`.

Unknown fields stay absent. Never substitute a system font, generic component, guessed token, or adjacent surface as a product fact.
<!-- omd:end -->

해시 계산

<HASH> = sha256 of the body content (마커 제외, body 텍스트만), 12자 hex prefix:

bash
node -e "console.log(require('crypto').createHash('sha256').update(process.argv[1]).digest('hex').slice(0,12))" "<body 텍스트>"

block 모드 마커 형식 정확히:

<!-- omd:start v=1 hash=ab12cd34ef56 -->
<body>
<!-- omd:end -->

실행 절차

사용자가 어떤 모드를 요청하는지 분기:

  • 인터랙티브 (디폴트) — drift 발견 시 사용자에게 묻기
  • --force 의도 ("강제 덮어쓰기") — drift 무시하고 덮어씀
  • --check 의도 ("상태만 검사") — 파일 상태만 출력, write 안 함

각 shim별로:

Step 1 — Read existing

파일 없으면 → status: missing, 새로 write 진행 파일 있으면 → 내용 파싱

Step 2 — block 모드 파싱

<!-- omd:start v=N hash=H --> 라인 찾기:

  • 없으면 → status: missing (block 부재, 사용자 content 외에 새로 추가 필요)
  • 있으면 → marker 사이의 본문 추출. 추출된 본문의 sha256:12를 계산해서 marker의 hash=H와 비교
    • 불일치 → status: drifted (사용자가 수동 편집함)
    • 일치 + 본문 == 템플릿 → status: clean
    • 일치 + 본문 != 템플릿 → status: out-of-date (omd 템플릿이 갱신됨)

Step 3 — whole 모드 파싱

existing 전체 content와 rendered 템플릿 비교:

  • 동일 → clean
  • 차이 → drifted

Step 4 — drift 처리

  • 인터랙티브: drift된 shim별로 "${path}는 수동 편집됐어요. 덮어쓸까요? (yes/no/show diff)" 묻기
  • --force: drift 무시 덮어씀
  • --check: drift 있으면 exit 1 동등 — 사용자에게 "drift detected" 보고 후 종료

Step 5 — Write

  • block 모드: existing 안의 marker block만 새 hash + 새 body로 교체. 마커 외부 사용자 content는 보존
  • whole 모드: 파일 전체를 새 rendered content로 교체. 디렉토리 (.cursor/rules/) 없으면 mkdir

Step 6 — sync-lock 갱신

.omd/sync.lock.json 기록 (없으면 만든다):

json
{
  "design_md_hash": "<DESIGN.md sha256:12>",
  "targets": {
    "CLAUDE.md": "<hash>",
    "AGENTS.md": "<hash>",
    ".cursor/rules/omd-design.mdc": "<hash>"
  },
  "updated_at": "<ISO timestamp>"
}

DESIGN.md 해시:

bash
[ -f DESIGN.md ] && node -e "console.log(require('crypto').createHash('sha256').update(require('fs').readFileSync('DESIGN.md')).digest('hex').slice(0,12))"

결과 보고

CLAUDE.md (block) — updated
AGENTS.md (block) — unchanged
.cursor/rules/omd-design.mdc — created
DESIGN.md hash: ab12cd34ef56

언제 실행하나

  • DESIGN.md 변경 직후 (shim hash 갱신용)
  • 새 프로젝트 첫 도입 (3종 생성)
  • .claude / .cursor 디렉토리 추가 후
  • "drift 확인" 요청

금지

  • 마커 안 본문에 임의 추가/축약 금지 — 위 템플릿 정확히 사용
  • block 모드 파일에서 마커 외부 사용자 content 절대 삭제 금지
  • .omd/sync.lock.json 무시 금지 — 항상 갱신
  • DESIGN.md가 없어도 shim은 만들 수 있음 (DESIGN.md 생성 후에 hash만 채움)

Frequently asked questions

What does the Omd:Sync AI skill do?

DESIGN.md 변경분을 CLAUDE.md / AGENTS.md / .cursor/rules/omd-design.mdc shim 3종에 전파. 'shim 갱신', 'drift 확인', 'ship', 'publish', 「shimを更新」, 「同步 CLAUDE.md」류의 요청에 트리거. DESIGN.md가 수정됐는데 shim이 오래됐을 때 자동 감지해 제안하기도 함.

Why use Omd:Sync on TypingMind?

Because you install it once and use it with any model. Omd:Sync 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:Sync in TypingMind?

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

Which AI models can use Omd:Sync?

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:Sync?

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

Is the Omd:Sync 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 👇