oh-my-design: Skill for Claude Code

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

omd:humanize is a skill for Claude Code, Codex from kwakseongjae/oh-my-design. It costs 129 tokens per session (1,879 once invoked), scanned A, original, MIT.

A writing editor for product documentation, user-interface text, and landing pages in Korean, English, Japanese, simplified Chinese, and traditional Chinese.

In plain words
What is it for?
It helps audit or rewrite confirmed problem areas and adapt Korean source copy naturally for supported languages without changing its meaning.
Why use it?
It removes awkward translation-like phrasing while preserving facts, numbers, commands, links, product names, and the intended brand voice.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present.

This is kwakseongjae/oh-my-design's own configuration. It tells Claude Code and Codex 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 →

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-humanize/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kwakseongjae/oh-my-design

Made for: Claude Code, Codex.

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:humanize

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-humanize"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,879 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 $0.00129 $0.01879
Opus 5 $0.00064 $0.00940
Sonnet 5 $0.00026 $0.00376
Haiku 4.5 $0.00013 $0.00188

Measured 11d ago against content hash 6c6221884cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omd:humanize 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 11d 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-humanize/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

omd:humanize

문장을 그럴듯하게 다시 쓰는 스킬이 아니다. 보존할 사실을 잠근 뒤, 대상 언어에서 반복되는 어색한 패턴만 국소적으로 고친다. 단어 하나를 보고 AI 문장으로 단정하지 않고, 같은 문서에서 여러 신호가 반복되거나 서로 겹칠 때만 수정 후보로 올린다.

지원 범위

  • 제품 문서, 온보딩, 도움말, 버튼·오류·빈 상태, 랜딩·릴리스 노트
  • 한국어 ko, 영어 en, 일본어 ja, 중국어 간체 zh-CN, 대만 번체 zh-TW
  • AUDIT: 문제 구간과 이유만 보고
  • REWRITE: 확인된 구간을 고치고 원문과 대조
  • LOCALE: 한국어 canonical의 뜻과 사실을 유지하며 대상 언어에서 새로 구성

맞춤법 검사, 일반 번역, 검색엔진용 대량 변형, AI 탐지기 우회는 대상이 아니다.

시작 전에 읽을 것

  1. 프로젝트 DESIGN.mdcontent-locales stable anchor와 .omd/preferences.md. 유효한 hash-bound profile: portable-core package가 있으면 graph.content_locales가 canonical이고, package가 없거나 invalid면 standalone DESIGN.md anchor를 사용한다. exact Core anchor가 전혀 없는 문서만 legacy compatibility input으로 읽어 의미 heading Voice & Tonecontent-locales로 매핑하며 숫자 section은 새 citation에 복사하지 않는다.
  2. 대상 파일과 같은 제품의 이미 승인된 카피
  3. references/locale-playbooks.md해당 locale 섹션만
  4. 출처와 차용 범위가 필요하면 references/sources.md

voice 우선순위는 사용자 지시 > 프로젝트 voice > 기존 제품 카피 > locale playbook이다.

핵심 계약

1. 보호 구간부터 잠근다

다음은 사용자가 명시적으로 허용하지 않으면 바꾸지 않는다.

  • 수치, 날짜, 단위, 가격, 버전, 품질 등급
  • 사람·회사·제품·기능명
  • URL, 파일 경로, CLI 명령, 코드, 환경 변수, skill/agent ID
  • 직접 인용, 법률·정책 문구, 측정 결과
  • 버튼이 수행하는 실제 동작과 제품 주장의 범위

보호 구간이 달라지면 자연스러워졌어도 실패다.

2. 단일 표현이 아니라 군집을 본다

수정 후보는 아래 중 하나를 충족해야 한다.

  • 강한 번역투·의미 중복·잘못된 locale 용어가 명확함
  • 같은 문장 구조·접속어·종결·대조법이 한 화면에서 반복됨
  • 추상적인 찬사가 기능·행동·근거를 대신함
  • 라벨과 실제 결과가 맞지 않음
  • 문장 리듬과 정보 순서가 독자의 행동을 방해함

대시, 3개짜리 목록, 수동태, 격식체처럼 문맥상 자연스러울 수 있는 특징은 단독으로 실패 처리하지 않는다.

3. 삭제보다 구체화한다

군더더기를 지운 자리에 원문에 이미 있는 기능, 행동, 조건을 앞으로 옮긴다. 원문에 없는 수치·사례·효과를 만들어 빈자리를 채우지 않는다. 근거가 없으면 더 작은 주장으로 줄인다.

4. locale은 독립 원고다

한국어 canonical의 thesis와 사실은 공유하지만 문장 순서·비유·주어·호흡까지 복제하지 않는다. zh-TWzh-CN을 번체자로 치환한 결과가 아니며, 일본어는 영어 문장의 조사만 바꾼 결과가 아니다.

실행 절차

  1. 범위 선언 — mode, target locale, 화면/문서, 독자, 보존할 동작을 한 줄로 적는다.
  2. 원문 스냅샷 — 보호 구간 목록과 문서의 핵심 주장 1–3개를 기록한다.
  3. 패턴 진단 — 구간마다 locale, clarity, rhythm, voice, action 중 해당 축과 근거를 붙인다. 모든 문장을 고치려 하지 않는다.
  4. 국소 수정 — 문제 구간만 고친다. 문단 전체 재작성은 정보 순서가 locale에서 어색할 때만 허용한다.
  5. 대조 검증 — 원문과 결과의 수치·명칭·URL·명령·인용·기능 범위를 직접 비교한다.
  6. 화면 검증 — UI 카피면 실제 locale route에서 줄바꿈, overflow, 버튼-결과 정합, 보조기술 label을 확인한다.
  7. 보고 — 무엇을 왜 고쳤는지와 일부러 남긴 표현을 짧게 남긴다.

Read the full file on GitHub · 124 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 124 lines · 129 tokens per session scan A 6c6221884cda

Subscribe to this mod's changes

omd:humanize is a skill published in the GitHub repository kwakseongjae/oh-my-design (498 stars, last pushed 4d ago), licensed MIT. It adds 129 tokens to every session and 1,879 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 2026-08-30.

Related

Other skills, from other repositories

dembrandt

A TypeScript command-line tool that renders a web page with Playwright and examines its actual styles. It turns colours, typography, spacing, borders, shadows, animation curves, components, and breakpoints into structured design tokens.

AvalonLee/AstraCraft-Program · 0 tokens

extract-design

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…

Manavarya09/design-extract · 98 tokens

ss-motion

Apply a named StyleSeed motion to a component — either one of the 5 personality seeds (Spring/Silk/Snap/Float/Pulse × entrance/exit/hover/press/layout) or a distinctive keyword move from the motion library (toggle-flip, toggle-curtain, reveal-blur, pop-in, shimmer, …). Translates vibe words into framer-motion code…

bitjaru/styleseed · 85 tokens

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

intake

The guided walkthrough for a codebase that has just installed montology (or has never written its vocabulary down) — phased questions served to the people who own the code as a clean one-question-at-a-time form in their browser (a local HTML file, no hosted service), answers returned to the agent on disk, each round…

shinyobjectz/montology · 157 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