Omd:Remember logo

Omd:Remember

Community
kwakseongjae
omd:remember

사용자의 디자인 선호·교정을 .omd/preferences.md에 기록. '이거 기억해줘', '앞으로는 이렇게', 'remember this', 'going forward never X', 「覚えておいて」, 「記住這個」류의 발화 또는 omd:apply가 교정을 감지했을 때 트리거. 기록된 내용은 omd:learn으로 DESIGN.md에 정식 반영.

Overview

Publisherkwakseongjae
Repositoryoh-my-design
Skill nameomd:remember
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:Remember 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-remember
  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-remember .claude/skills/kwakseongjae-omd-remember
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omd:Remember 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:Remember 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:Remember 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:remember — Preference Logger

사용자의 디자인 선호/교정을 .omd/preferences.md에 append-only로 기록한다. 나중에 omd:learn이 배치로 DESIGN.md에 반영. CLI 호출 없음 — Read/Edit/Write 툴로 직접 처리.

트리거 발화 패턴

  • "기억해 둬", "앞으로는 ~로 해"
  • "우리는 ~한다 / ~하지 않는다"
  • "remember that ...", "going forward ..."
  • "rule of thumb: ..."
  • 사용자가 당신의 디자인 선택을 명시적으로 교정

파일 포맷 (.omd/preferences.md)

frontmatter + 엔트리 시퀀스. 엔트리 하나당 ## <heading> + omd-meta 코드블록 + body.

---
schema: omd.preferences/v1
design_md_hash_at_creation: <hash 또는 빈 문자열>
---

# Preference Log

## 2026-04-30T17:48:00.000Z — ctas-never-uppercase

```omd-meta
id: pref_lqxk2_a3f9c1d4
timestamp: 2026-04-30T17:48:00.000Z
scope: components.button
signal: user-statement
confidence: explicit
status: pending
source_agent: claude-code
source_context: "src/components/Button.tsx"

CTAs are never uppercase


## 실행 절차

### Step 1 — note 정규화
사용자 발화를 한 문장 영문으로 요약 (예: "앞으로 CTA 대문자 쓰지마" → `CTAs are never uppercase`).

### Step 2 — scope 추론
note 내용에서 다음 매핑 우선순위 사용:

| 매칭 키워드 (정규식, case-i) | scope |
|---|---|
| `\b(buttons?\|ctas?\|btns?)\b` | `components.button` |
| `\b(cards?)\b` | `components.card` |
| `\b(dialogs?\|modals?)\b` | `components.dialog` |
| `\b(inputs?\|fields?\|forms?)\b` | `components.input` |
| `\b(nav\|navigation\|headers?\|menus?)\b` | `components.navigation` |
| `\b(badges?\|chips?\|pills?\|tags?)\b` | `components.badge` |
| `\b(tables?\|rows?\|cells?)\b` | `components.table` |
| `\b(dropdowns?\|selects?\|comboboxes?)\b` | `components.dropdown` |
| `\b(toasts?\|notifications?\|snackbars?)\b` | `components.toast` |
| `\b(tabs?)\b` | `components.tabs` |
| `\b(colors?\|palette\|hex\|hue\|saturation\|shades?\|tints?\|gradients?)\b` | `color` |
| `\b(font\|typography\|typeface\|weight\|leading\|tracking\|letter-?spacing)\b` | `typography` |
| `\b(spacing\|gap\|padding\|margin\|grid)\b` | `spacing` |
| `\b(voice\|tone\|copy\|microcopy\|wording\|language)\b` | `voice` |
| `\b(motion\|animation\|transition\|easing\|duration)\b` | `motion` |
| `\b(layout\|structure\|hierarchy)\b` | `layout` |
| `\b(theme\|aesthetic\|vibe\|mood\|look\|feel)\b` | `visualTheme` |
| (어느 것도 매칭 X) | `visualTheme` |

사용자가 명시적으로 scope를 지정했으면 그대로 사용.

### Step 3 — id 생성
형식: `pref_<base36 timestamp>_<8 hex chars>`. Bash로 한 줄:
```bash
node -e "console.log('pref_' + Date.now().toString(36) + '_' + require('crypto').randomBytes(4).toString('hex'))"

Step 4 — slug + heading

bash
node -e "console.log(process.argv[1].toLowerCase().replace(/[^a-z0-9]+/g,'-').replace(/^-+|-+$/g,'').slice(0,40) || 'entry')" "<note>"

heading: <ISO timestamp> — <slug>

Step 5 — 파일 read/append

  1. Read .omd/preferences.md — 없으면 frontmatter+header부터 만든다:
    ---
    schema: omd.preferences/v1
    design_md_hash_at_creation:
    ---
    
    # Preference Log
    
  2. 새 엔트리 블록을 파일 끝에 append (Edit 툴, old_string은 마지막 라인, new_string은 마지막 라인 + 빈 줄 + 새 엔트리). 또는 Write로 전체 재작성.
  3. 메타 필드:
    • id, timestamp, scope (필수)
    • signal: user-statement (디폴트, 사용자가 직접 발화한 경우) 또는 user-correction (사용자가 당신의 선택을 교정한 경우)
    • confidence: explicit (디폴트, 사용자가 명시적으로 말한 경우) 또는 inferred (당신이 사용자 행동에서 추론한 경우)
    • status: pending (모든 새 엔트리)
    • source_agent: 환경에서 추론 (claude-code / codex / opencode / cursor)
    • source_context: 관련 파일 경로 또는 PR번호 (있으면 JSON.stringify로 quote)

Step 6 — 응답

간결한 한 줄: Logged ${id} to .omd/preferences.md (scope: ${scope})

omd:apply 스킬과의 관계

  • 자동 감지: 일반 UI 작업 중 교정 발생 시 omd:apply가 이 스킬 트리거
  • 명시적 호출: 디자인 원칙 선언만 할 때 직접 트리거

금지

  • .omd/preferences.md 파일을 frontmatter 외 직접 손대지 말 것 (id 충돌 방지) — 항상 위 절차로
  • 같은 세션 내 동일 내용 중복 기록 금지
  • 사용자에게 "기록할까요?" 묻지 말 것 — 감지 즉시 기록 + 간결 알림
  • frontmatter의 design_md_hash_at_creation은 첫 생성 시에만 채움 (이후 절대 수정 X)

Frequently asked questions

What does the Omd:Remember AI skill do?

사용자의 디자인 선호·교정을 .omd/preferences.md에 기록. '이거 기억해줘', '앞으로는 이렇게', 'remember this', 'going forward never X', 「覚えておいて」, 「記住這個」류의 발화 또는 omd:apply가 교정을 감지했을 때 트리거. 기록된 내용은 omd:learn으로 DESIGN.md에 정식 반영.

Why use Omd:Remember on TypingMind?

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

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

Which AI models can use Omd:Remember?

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:Remember?

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

Is the Omd:Remember 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 👇