agentmods.dev

oh-my-design: Skill for Claude Code

.claude/skills/omd-aphrodite/SKILL.md

omd:aphrodite is a skill for Claude Code from kwakseongjae/oh-my-design. It costs 122 tokens per session (3,547 once invoked), scanned A, original, MIT.

A detailed process for creating a polished one-page landing page, including its visual finish, imagery, typography, motion, and responsive checks.

In plain words
What is it for?
Use it when building a showcase landing page that needs a visual concept, high-quality assets, responsive rendering, and documented design checks.
Why use it?
A page can have the right sections yet still look unfinished or flat. This process sets concrete quality checks for layout, media, contrast, motion, and small-screen rendering.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Codex.

This is kwakseongjae/oh-my-design's own configuration. It tells Claude Code how to work on oh-my-design itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oh-my-design configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node test-v2/tools/font-inline.mjs --list # 검증된 가변 폰트.

not rated 500repo +15 changed 7d ago A scan SkillSpector: pass 122 tokens original MIT
View source ↗ kwakseongjae/oh-my-design oh-my-design.kr
Reuse

Borrowing it

Nothing to install: this file belongs to kwakseongjae/oh-my-design. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kwakseongjae/oh-my-design/main/.claude/skills/omd-aphrodite/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kwakseongjae/oh-my-design

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for omd:aphrodite

README.md
[![agentmods](https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-aphrodite/github.svg)](https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-aphrodite)
Your own site
<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-aphrodite"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-aphrodite/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omd:aphrodite

Your own site · 80×15
<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-aphrodite"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-aphrodite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00122 $0.03547
Opus 5 $0.00061 $0.01774
Sonnet 5 $0.00024 $0.00709
Haiku 4.5 $0.00012 $0.00355

Measured 7d ago against content hash d3db3b42ecdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

omd:aphrodite scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/omd-aphrodite/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

omd:aphrodite — 와우 합격선

이 스킬은 omd:landing 의 대체가 아니라 그 위의 합격선이다. 구조(섹션 리듬·에셋 배치·밀도)는 omd:landing 과 같은 절차를 그대로 쓴다. 다른 것은 통과 조건과 마감·에셋의 등급이다. 일상 랜딩은 omd:landing, 자랑할 한 장은 이 스킬이다.

왜 있나

밀도만 채운 페이지는 여전히 밋밋했다. 2026-09-03 계측에서 우리 최고 산출물은 디스플레이 서체가 OS 기본이었고 그림자·글래스·마스크·블렌드·3D·클립패스·그레인이 전부 0이었다 (docs/reviews/landing-craft-gap-2026-09-03.md). 코덱스 LC-136 은 무엇을 어디에 놓는가만 규정했고 마감 층이 없었다. 그 층이 LC-3747 이고, 이 스킬은 그것을 강제한다.

합격선 (하나라도 미달이면 미완성 — 스스로 통과 선언 금지)

검사 조건
omd check landing LI-1~32 전 항목 ok. 특히 LI-24 화면 잉크 · LI-25 폴드 미디어 · LI-26 미디어 밀도 · LI-27 디스플레이 서체 · LI-28 깊이 · LI-29 메시/그레인 · LI-30 브라우저 기본값 · LI-31 미디어 색보정 · LI-32 alt 구체성
omd check contrast FAIL 0 · no-JS 숨김 0
omd check render 1440×900 · 390×844 양쪽 PASS
omd-designer-review BLOCK 0

검사를 못 돌리는 상황(브라우저 없음 등)은 통과가 아니라 실패다. 그 사실을 trace.md 에 적는다.

0. 채널 확인 (건너뛰지 않는다)

node scripts/omd-setup-detect.mjs (설치본: omd setup detect) 로 지금 쓸 수 있는 이미지·영상 채널을 확인하고 trace.md 첫 줄에 적는다. 채널이 바뀌면 결과의 등급이 바뀐다 — 나중에 왜 이 품질이 나왔는지 설명하려면 기록이 필요하다.

  • 영상 채널이 없으면 생성 영상을 포기하되 모션은 포기하지 않는다. CSS/SVG 로 만든 움직임 (마스크 리빌, 스크롤 연동 변형, SVG 경로 애니메이션, 그레인 셰이더 흉내)이 대안이며, 수상작 상당수가 실제로 이 방식이다. 「영상 없음」을 trace.md 에 사유와 함께 남긴다.
  • 잔액 소진(402)·키 없음은 조용히 건너뛰지 말고 사용자에게 알린다.

1. 서체 조달 (LC-47 — 이 단계를 빼면 합격선 못 넘는다)

node test-v2/tools/font-inline.mjs --list                        # 검증된 가변 폰트
node test-v2/tools/font-inline.mjs --family fraunces --out /tmp/display.css
  • 디스플레이 1종 + 본문 1종. 같은 종을 옵티컬 사이즈 축으로 나눠 써도 된다.
  • 산출된 @font-face 블록을 HTML <style> 안에 그대로 넣는다. 렌더 시 외부 요청 0건이 되어야 한다.
  • 큰 글자에는 font-variation-settings 의 opsz 를 크게, 본문에는 작게 준다 — 이 축이 "제대로 짠 조판"의 신호다.
  • 라이선스(OFL 계열, 임베딩 허용)를 확인하고 trace.md 에 적는다.
  • 금지: -apple-system·system-ui·Helvetica·Arial 로 디스플레이 헤딩을 쓰는 것.

1.5 라이브러리 정책 — 제로 베이스 금지

"렌더 시 네트워크 요청 0" 은 라이브러리 0 이 아니다. 라이선스가 허용하는 오픈소스는 minified 소스를 <script>/<style> 로 인라인한다. 검증된 조합은 docs/design-excellence/fx-library/ 에 있다 — 스크롤 안무는 scroll-gsap/(GSAP 3.15 + ScrollTrigger, 114.7KB, 라이선스 lib/LICENSES.md 인용 필수), CSS 효과는 INDEX.md 의 17종(전부 재배포 가능, 데모 콘솔 에러 0). 예산: 인라인 라이브러리 ≤ 120KB, 효과 종류 ≤ 7/페이지. 라이브러리 밖의 효과를 새로 쓰면 같은 구조(README+demo+snippet)로 fx-library 에 편입해 다음 런이 재사용하게 한다.

Read the full file on GitHub · 157 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed · +18 lines d3db3b42ecdb
  2. 9d ago First seen · 139 lines · 122 tokens per session scan A cf082fbe4d7c

Subscribe to this mod's changes

omd:aphrodite is a skill published in the GitHub repository kwakseongjae/oh-my-design (500 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session and 3,547 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

CSS and stylingDesign and UXFrontendclidesign-mddesign-systemdesign-tokensgoogle-stitchnextjs
Related

Other skills, from other repositories

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

brandmd

Extract a website's design system into a DESIGN.md file. Use when starting a new frontend project, rebuilding a site, or when the user wants AI-generated UI to match an existing brand.

yuvrajangadsingh/brandmd · 41 tokens

design-engineering

Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…

broomva/skills · 231 tokens

awesome-design-md-cn

A collection of Markdown design-system documents for AI design and coding agents. The documents describe a product or website’s colors, fonts, components, spacing, and visual hierarchy.

AvalonLee/AstraCraft-Program · 0 tokens

s2-docs

Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…

adobe/spectrum-design-data · 91 tokens

extract-design-system

Extract design primitives from a public website and generate starter token files for your project.

arvindrk/extract-design-system · 20 tokens