ui-ux-auditor

ui-ux-auditor is a skill for Claude Code from Dannykkh/skill-olympus. It costs 129 tokens per session (6,237 once invoked), scanned A, original, MIT.

A workflow that audits a web project’s user interface and user experience across nine areas, then checks rendered screenshots and scores the results from zero to ten. It can also modify the code to address findings.

In plain words
What is it for?
Use it to review dark mode, responsive layouts, accessibility, loading states, form interactions, navigation, typography, animation, and overly generic AI-generated design.
Why use it?
It combines code checks with inspection of the actual rendered screen, which can reveal problems that source code alone does not show.

Skill for Claude Code

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

Part of the skill-olympus plugin — 98 skills, 7 commands, 42 agents, 5 MCP servers shipped together

Good fit Use it to review dark mode, responsive layouts, accessibility, loading states, form interactions, navigation, typography, animation, and overly generic AI-generated design.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dannykkh/skill-olympus/ui-ux-auditor
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 Dannykkh/skill-olympus --skill ui-ux-auditor
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code.

Or install skill-olympus, the plugin that ships this one along with the rest of its 98 skills, 7 commands, 42 agents, 5 MCP servers.

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 ui-ux-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/dannykkh/skill-olympus/ui-ux-auditor/github.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/ui-ux-auditor)
Your own site
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/ui-ux-auditor"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/ui-ux-auditor/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 ui-ux-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/ui-ux-auditor"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/ui-ux-auditor.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 6,237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 285
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 288
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.06237
Opus 5 $0.00064 $0.03119
Sonnet 5 $0.00026 $0.01247
Haiku 4.5 $0.00013 $0.00624

Measured 6d ago against content hash 7baa19535b3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ui-ux-auditor scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. 이미 실행 중인 dev server가 있으면 재사용 (헬스체크: `curl -s -o /dev/null -w "%{http_code}" http://localhost:{port}`)
skills/ui-ux-auditor/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Auditor — 9영역 감사 + 0-10 채점 + 자동 수정

프로젝트의 UI/UX를 9개 카테고리로 스캔하고, 영역별 0-10 점수를 매긴 뒤, 발견된 문제를 우선순위별로 분류한 뒤 코드를 직접 수정합니다.

세부 규칙 DB: references/ux-guidelines.csv — nextlevelbuilder/ui-ux-pro-max-skill(MIT)에서 흡수한 UX 이슈 99종(No/Category/Issue/Platform/Description/Do/Don't/Code Example Good/Code Example Bad/Severity). 아래 9영역 각각에 Category 컬럼으로 매핑돼 있으니, 채점 시 해당 영역 Category로 grep해 Do/Don't·코드 예시를 인용하세요. Web/Mobile/All/VisionOS로 플랫폼 태그가 붙어 있어 관련 없는 플랫폼 행은 건너뜁니다.

상호보완 관계:

  • design-plan의 네이티브 렌더 비평: 디자인 방향·계약 — "어떤 경험을 만들 것인가" (개발 전·중)
  • ui-ux-auditor (이 스킬): UI/UX 점검 + 수정 — "이게 문제니까 고쳐라" (개발 후)

적용 시점

  • /ui-ux-auditor 명시적 실행
  • "UI 점검해줘", "UX 감사해줘", "접근성 검사", "반응형 확인" 요청 시

Step 1: 프로젝트 스캔

프로젝트 구조를 파악합니다:

검사 대상 경로 패턴
페이지 라우트 src/app/, pages/, src/routes/
컴포넌트 src/components/, components/
스타일 시스템 globals.css, tailwind.config.*, *.module.css
UI 의존성 package.json → DaisyUI, shadcn, Radix, MUI, Chakra 등

프레임워크 자동 감지:

package.json → "next" → Next.js
package.json → "nuxt" → Nuxt
package.json → "@sveltejs/kit" → SvelteKit
package.json → "@remix-run" → Remix
package.json → "astro" → Astro
index.html + vite → Vite SPA

Step 2: 9영역 정적 스캔 (Grep — 1차 신호)

이 단계의 Grep 결과는 1차 신호입니다. 최종 채점은 Step 2.5의 시각 검증(렌더링 관찰)이 우선합니다.

2-1. 다크/라이트 모드 호환성

Grep 탐지 패턴:

# 하드코딩 색상 (다크모드에서 깨지는 패턴)
text-white|text-black|bg-white|bg-black
bg-zinc-[0-9]|bg-gray-[0-9]|bg-slate-[0-9]
text-zinc-[0-9]|text-gray-[0-9]|text-slate-[0-9]
border-zinc-|border-gray-|border-slate-
# 네이티브 폼 컨트롤 (다크모드 자주 깨짐 — color-scheme 누락)
<select|<option|color-scheme|::placeholder|appearance-none
검사 항목 기준
하드코딩 색상 text-white, bg-black 등 → 시맨틱 토큰으로 변환 필요
CSS 변수 충돌 :root vs [data-theme] 우선순위 충돌
테마 전환 next-themes, data-theme 속성 적용 여부
이미지/아이콘 다크모드에서 안 보이는 요소 (흰 배경 위 흰 아이콘 등)
select/option <select><option>이 OS 기본색으로 렌더 → 다크에서 깨짐. 루트 color-scheme: light dark + option 배경/글자색 명시 필요
컨테이너 div 배경 섹션/카드 div 배경색이 테마 토큰을 따르는지 (하드코딩 흰/검정 금지)
텍스트 반전 배경 반전 시 텍스트 색도 함께 반전되는지 (다크에서 검은 글자 잔존 금지)

Read the full file on GitHub · 461 lines

Files

What ships with it

1 file 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. 6d ago First seen · 461 lines · 129 tokens per session scan A 7baa19535b3f

Subscribe to this mod's changes

ui-ux-auditor is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 6,237 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.