brand-guide

brand-guide is a skill for Claude Code from crealwork/ai-marketing-kit. It costs 120 tokens per session (1,172 once invoked), scanned A, original, MIT.

A method for extracting a measurable brand system from a website, logo, presentation, or other materials. A brand system records colors, fonts, logo rules, spacing, visual styles, and writing tone in a form others can reuse.

In plain words
What is it for?
Use it to create design tokens, logo usage rules, typography and color specifications, shape and photo guidance, and examples of appropriate and inappropriate brand language.
Why use it?
It replaces subjective design impressions with specific values and usage rules. This helps agents and designers apply the same visual and writing choices consistently.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-marketing-kit plugin — 26 skills shipped together

Good fit Use it to create design tokens, logo usage rules, typography and color specifications, shape and photo guidance, and examples of appropriate and inappropriate brand language.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/crealwork/ai-marketing-kit/brand-guide
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add crealwork/ai-marketing-kit --skill brand-guide
Clone the repo
git clone --depth 1 https://github.com/crealwork/ai-marketing-kit

Made for: Claude Code.

Or install ai-marketing-kit, the plugin that ships this one along with the rest of its 26 skills.

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 brand-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/brand-guide/github.svg)](https://agentmods.dev/skills/crealwork/ai-marketing-kit/brand-guide)
Your own site
<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/brand-guide"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/brand-guide/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 brand-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/brand-guide"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/brand-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,172 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.
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 $0.00120 $0.01172
Opus 5 $0.00060 $0.00586
Sonnet 5 $0.00024 $0.00234
Haiku 4.5 $0.00012 $0.00117

Measured 9d ago against content hash ffe49f3f51e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

brand-guide 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 9d 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.

skills/brand-guide/SKILL.md · 64 lines

What it actually says

Brand Guide

사이트/로고/자료에서 측정 가능한 브랜드 시스템을 뽑아낸다. 산출물은 감상문이 아니라 다른 에이전트가 그대로 적용할 수 있는 토큰: hex 코드, 폰트 이름/웨이트, 간격 수치, 금지 규칙.

모델 권장: 팔레트 판정·보이스 추출·응용 규칙은 취향 판단이 대부분이라 frontier 모델(Claude Fable 5급)에서 돌리는 걸 권장. 작은 모델은 색을 평균내고 보이스를 뭉갠다.

Gates

G1 — 인테이크. 소스 확인: 라이브 사이트 URL? 로고 파일? 기존 덱/자료? 아무것도 없으면 브랜드 인터뷰(아래 §4)로 전환. 그리고 용도 확인: 에이전트용 토큰(DESIGN.md)만? 사람에게 전달할 가이드라인 문서(PDF)까지?

G2 — 캡처. 사이트가 있으면:

  • 주요 페이지 3–5개 풀페이지 스크린샷 (데스크톱+모바일) → 눈으로 READ.
  • CSS에서 실측: :root 변수, computed color 빈도 상위권, font-family/weight 실사용 조합, border-radius/shadow 패턴, 버튼·링크 상태.
  • 카피 수집: 히어로 헤드라인, CTA 문구, about 문단 — 보이스 추출 원료. 스크린샷 없이 CSS만 읽고 판정하지 않는다 — 렌더된 화면이 진실이다.

G3 — 토큰 증류. 측정 가능한 형태로만 기록:

  • 컬러: 역할별 hex — primary / accent / ink(본문) / background / muted. 역할당 1개, 전체 5–7개로 제한. "다양한 파란색들" 같은 기술은 실패.
  • 타이포: display/heading/body/mono 각각 폰트 이름 + 실제 웨이트 + 용례. 폰트 파일 소스(구글폰트 링크 등)까지.
  • 로고 룰: 최소 크기, 여백(clear space), 허용 배경(어두운 배경엔 어떤 버전), 금지 사례(늘리기, 색 변경, 그림자).
  • 형태 언어: radius 값, 그림자 유무/값, 보더 스타일, 사진 톤(있다면).

G4 — 보이스. 수집한 카피에서 추출:

  • 형용사 3개 (서로 긴장 관계가 있어야 좋다 — 예: "따뜻한 + 정확한").
  • Do/Don't 각 3–5개, 실제 문장 예시 쌍으로 ("이렇게 씀 → 이렇게 안 씀").
  • 톤 고정: 존댓말/반말, 이모지 정책, 문장 길이 경향.
  • 카피가 부족하면 유저 인터뷰로 보강 — 지어내지 않는다.

G5 — 산출.

  • DESIGN.md (필수): 위 토큰 전부, 에이전트가 파싱할 수 있는 구조로. 이 파일 하나로 카드뉴스·덱·사이트·영상 자막까지 브랜드 일관성이 유지되는 게 목표 (carousel-generator, ppt-slide-generator가 이 파일을 읽는다).
  • 가이드라인 문서 (요청 시): DESIGN.md를 사람용으로 조판 — 페이지당 규칙 하나, 실물 목업, do/don't 대비 스프레드.

4. 브랜드가 아직 없을 때 (인터뷰 모드)

기존 자산이 없으면 추출 대신 결정을 돕는다: 업종/타깃/경쟁사 3곳 → 무드 방향 2–3안(각각 팔레트+폰트 페어 시안) → 유저 선택 → G3–G5 동일. 시안 없이 말로만 "모던하고 미니멀" 같은 합의는 금지 — 눈에 보이는 안으로 고르게 한다.

Hard rules

  1. 모든 값은 실측 — 스크린샷/CSS에서 뽑은 hex, 실제 웨이트. 추정 금지.
  2. 역할 없는 컬러를 팔레트에 넣지 않는다 (어디 쓰는 색인지 없으면 삭제).
  3. 보이스 예시는 실제 카피 기반 — 없으면 유저에게 확인받은 문장으로.
  4. 산출 전 셀프테스트: DESIGN.md만 보고 SNS 카드 1장을 만들 수 있는가? 못 만들면 토큰이 부족한 것 — 돌아가서 채운다.
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. 9d ago First seen · 64 lines · 120 tokens per session scan A ffe49f3f51e6

Subscribe to this mod's changes

brand-guide is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,172 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

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens