design-audit
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDesign Audit Skill
设计审计Skill
<!-- dual-compat-start -->
<!-- dual-compat-start -->
Use When
使用场景
- Comprehensive UI/UX quality audit covering visual hierarchy, accessibility, AI slop detection, typography, colour, layout, interaction states, responsive behaviour, performance, and microcopy. Produces severity-rated findings with actionable...
- The task needs reusable judgment, domain constraints, or a proven workflow rather than ad hoc advice.
- 全面的UI/UX质量审计,涵盖视觉层级、可访问性、AI Slop检测、排版、色彩、布局、交互状态、响应式表现、性能和微文案。生成带有可操作建议的分级严重度审计结果……
- 任务需要可复用的判断逻辑、领域约束或成熟的工作流,而非临时建议。
Do Not Use When
不适用场景
- The task is unrelated to or would be better handled by a more specific companion skill.
design-audit - The request only needs a trivial answer and none of this skill's constraints or references materially help.
- 任务与无关,或更适合由更专业的配套Skill处理。
design-audit - 请求仅需要简单答案,本Skill的约束条件或参考内容无法提供实质性帮助。
Required Inputs
必要输入
- Gather relevant project context, constraints, and the concrete problem to solve.
- Confirm the desired deliverable: design, code, review, migration plan, audit, or documentation.
- 收集相关项目背景、约束条件以及需要解决的具体问题。
- 确认期望交付物:设计方案、代码、评审意见、迁移计划、审计报告或文档。
Workflow
工作流
- Read this first, then load only the referenced deep-dive files that are necessary for the task.
SKILL.md - Apply the ordered guidance, checklists, and decision rules in this skill instead of cherry-picking isolated snippets.
- Produce the deliverable with assumptions, risks, and follow-up work made explicit when they matter.
- 首先阅读本,然后仅加载完成任务所需的相关深度参考文件。
SKILL.md - 应用本Skill中的有序指导、检查清单和决策规则,而非随意挑选孤立片段。
- 生成交付物时,若相关的假设、风险和后续工作对任务有影响,需明确说明。
Quality Standards
质量标准
- Keep outputs execution-oriented, concise, and aligned with the repository's baseline engineering standards.
- Preserve compatibility with existing project conventions unless the skill explicitly requires a stronger standard.
- Prefer deterministic, reviewable steps over vague advice or tool-specific magic.
- 输出内容需以执行为导向、简洁明了,并与代码库的基础工程标准保持一致。
- 除非Skill明确要求更高标准,否则需保持与现有项目惯例的兼容性。
- 优先采用确定性、可评审的步骤,而非模糊建议或工具特定的“魔法操作”。
Anti-Patterns
反模式
- Treating examples as copy-paste truth without checking fit, constraints, or failure modes.
- Loading every reference file by default instead of using progressive disclosure.
- 将示例内容直接复制粘贴,而不检查是否适配、是否符合约束条件或存在失效模式。
- 默认加载所有参考文件,而非逐步按需披露。
Outputs
输出成果
- A concrete result that fits the task: implementation guidance, review findings, architecture decisions, templates, or generated artifacts.
- Clear assumptions, tradeoffs, or unresolved gaps when the task cannot be completed from available context alone.
- References used, companion skills, or follow-up actions when they materially improve execution.
- 符合任务要求的具体结果:实施指导、评审发现、架构决策、模板或生成的工件。
- 当仅靠现有上下文无法完成任务时,需明确说明假设条件、权衡方案或未解决的空白。
- 若能实质性提升执行效果,需列出使用的参考资料、配套Skill或后续行动。
Evidence Produced
生成的证据
| Category | Artifact | Format | Example |
|---|---|---|---|
| UX quality | Design audit report | Markdown doc covering visual hierarchy, typography, spacing, colour, and accessibility findings | |
| UX quality | Accessibility pass report | Markdown doc summarising WCAG conformance | |
| 分类 | 工件 | 格式 | 示例 |
|---|---|---|---|
| UX质量 | 设计审计报告 | 涵盖视觉层级、排版、间距、色彩和可访问性发现的Markdown文档 | |
| UX质量 | 可访问性评估报告 | 总结WCAG合规性的Markdown文档 | |
References
参考资料
- Use the links and companion skills already referenced in this file when deeper context is needed.
- 当需要更深入的上下文时,使用本文件中已引用的链接和配套Skill。
Plugins (Load Alongside)
插件(需同时加载)
| Companion Skill | When to Load |
|---|---|
| Detailed AI anti-pattern reference |
| Visual system rules to audit against |
| Animation quality standards |
| Microcopy quality standards |
| Responsive behaviour standards |
| Performance measurement targets |
| UX law compliance |
| Accessibility and usability principles |
| 配套Skill | 加载时机 |
|---|---|
| 需要详细的AI反模式参考时 |
| 需要对照视觉系统规则进行审计时 |
| 需要动画质量标准时 |
| 需要微文案质量标准时 |
| 需要响应式表现标准时 |
| 需要性能测量指标时 |
| 需要UX法则合规性检查时 |
| 需要可访问性和可用性原则时 |
1. Audit Process
1. 审计流程
Step 1: Gather Context
步骤1:收集上下文
Before auditing, understand:
- Who are the users? (age, tech literacy, use context)
- What's the purpose? (task completion, information display, commerce)
- What platform? (web, Android, iOS, cross-platform)
- What design system? (if any — tokens, components, patterns)
- What's the brand personality? (professional, playful, clinical)
审计前需了解:
- 用户群体?(年龄、技术素养、使用场景)
- 设计目的?(任务完成、信息展示、商业转化)
- 目标平台?(网页、Android、iOS、跨平台)
- 使用的设计系统?(如有——设计令牌、组件、模式)
- 品牌调性?(专业、活泼、严谨)
Step 2: Systematic Scan
步骤2:系统扫描
Evaluate across all 10 dimensions (Section 2). Score each dimension.
从10个维度(第2节)进行评估,为每个维度打分。
Step 3: Produce Report
步骤3:生成报告
Follow the report structure (Section 3). Prioritise findings by severity.
遵循报告结构(第3节),按严重度优先级整理发现的问题。
2. The 10 Audit Dimensions
2. 10个审计维度
Dimension 1: AI Slop Detection
维度1:AI Slop检测
The first check. Does this interface look machine-generated?
| Check | Look For |
|---|---|
| Typography | Inter/Roboto defaults, no hierarchy, title case everywhere |
| Colour | Cyan-on-dark, purple gradients, gradient text, pure black/white |
| Layout | Everything in cards, identical card grids, everything centred |
| Effects | Glassmorphism, decorative blur, glow borders, SVG blobs |
| Motion | Bounce/elastic easing, animation fatigue |
| Content | "Submit" buttons, "Loading..." text, corporate AI jargon |
Verdict: PASS (distinctive, intentional) / BORDERLINE (some generic choices) / FAIL (immediately recognisable as AI-generated)
首要检查项:该界面是否看起来是机器生成的?
| 检查项 | 检查要点 |
|---|---|
| 排版 | Inter/Roboto默认字体、无层级结构、全部使用标题大小写 |
| 色彩 | 深蓝/深青配色、紫色渐变、渐变文字、纯黑/纯白 |
| 布局 | 所有内容都放在卡片中、相同的卡片网格、所有内容居中 |
| 效果 | 毛玻璃效果、装饰性模糊、发光边框、SVG blob图形 |
| 动效 | 弹跳/弹性缓动、动画疲劳 |
| 内容 | “Submit”按钮、“Loading...”文本、企业AI术语 |
结论:通过(独特、有设计意图)/ 临界(存在一些通用化选择)/ 不通过(明显可识别为AI生成)
Dimension 2: Visual Hierarchy
维度2:视觉层级
| Check | Standard |
|---|---|
| Squint test | Most important element visible when blurred |
| Size hierarchy | Clear primary > secondary > tertiary sizing |
| Weight contrast | Bold for headings, regular for body (not medium/light) |
| Colour emphasis | Brand colour reserved for interactive elements |
| Whitespace | Generous spacing separates sections; tight spacing groups related items |
| Focal point | Each screen has one clear entry point for the eye |
| 检查项 | 标准 |
|---|---|
| 眯眼测试 | 模糊后仍能看到最重要的元素 |
| 尺寸层级 | 清晰的主 > 次 > 三级尺寸区分 |
| 字重对比 | 标题使用粗体,正文使用常规字重(避免中等/轻量字重) |
| 色彩强调 | 品牌色仅用于交互元素 |
| 留白 | 充足间距分隔不同区块;紧凑间距关联相关内容 |
| 视觉焦点 | 每个页面有一个清晰的视觉入口点 |
Dimension 3: Accessibility
维度3:可访问性
| Check | Standard | Severity |
|---|---|---|
| Text contrast | >= 4.5:1 (body), >= 3:1 (large text) | Critical |
| UI component contrast | >= 3:1 against background | Critical |
| Touch targets | >= 44x44px (48x48px preferred) | Critical |
| Keyboard navigation | Logical tab order, visible focus ring | Critical |
| Screen reader | Semantic HTML, ARIA labels, meaningful alt text | Critical |
| Colour independence | Never colour alone as indicator | High |
| Zoom support | Usable at 200% zoom | High |
| Reduced motion | | High |
| Focus management | Focus moves logically after interactions | Medium |
| 检查项 | 标准 | 严重度 |
|---|---|---|
| 文本对比度 | >= 4.5:1(正文),>= 3:1(大文本) | 关键 |
| UI组件对比度 | 与背景对比度 >= 3:1 | 关键 |
| 触摸目标 | >= 44x44px(推荐48x48px) | 关键 |
| 键盘导航 | 合理的Tab顺序、可见的焦点环 | 关键 |
| 屏幕阅读器 | 语义化HTML、ARIA标签、有意义的替代文本 | 关键 |
| 色彩独立性 | 绝不单独使用色彩作为提示 | 高 |
| 缩放支持 | 200%缩放时仍可正常使用 | 高 |
| 减少动效 | 遵循 | 高 |
| 焦点管理 | 交互后焦点移动符合逻辑 | 中 |
Dimension 4: Typography
维度4:排版
| Check | Standard |
|---|---|
| Font choice | Intentional, not default (matches brand personality) |
| Type scale | Consistent scale (Major Third or project-appropriate) |
| Body size | >= 16px (18px preferred) |
| Line height | 1.5-2.0 for body; decreasing for larger sizes |
| Line length | 40-80 characters (66 ideal) |
| Weight usage | Regular + Bold only (avoid thin/light/medium) |
| Alignment | Left-aligned body text (no justified, centre only for 1-2 lines) |
| Letter spacing | Decreased for large display text |
| 检查项 | 标准 |
|---|---|
| 字体选择 | 有设计意图,非默认字体(匹配品牌调性) |
| 字体比例 | 一致的比例(大三度或项目适配的比例) |
| 正文字号 | >= 16px(推荐18px) |
| 行高 | 正文1.5-2.0;字号越大行高越小 |
| 行长度 | 40-80字符(理想66字符) |
| 字重使用 | 仅使用常规+粗体(避免细体/轻量/中等字重) |
| 对齐方式 | 正文左对齐(不使用两端对齐,仅1-2行文本可居中) |
| 字间距 | 大尺寸展示文本需缩小字间距 |
Dimension 5: Colour
维度5:色彩
| Check | Standard |
|---|---|
| Tinted neutrals | No pure grey (#808080), black (#000), or white (#fff) |
| Palette structure | Primary + neutral + semantic + surface tokens |
| 60-30-10 rule | 60% neutral, 30% secondary, 10% accent |
| Semantic colour | Red=error, amber=warning, green=success, blue=info |
| Dark mode | Independently designed (not inverted), desaturated brand colours |
| Brand colour usage | Reserved for interactive elements only |
| System colour pairing | Always paired with icon (not colour alone) |
| 检查项 | 标准 |
|---|---|
| 中性色调整 | 不使用纯灰色(#808080)、纯黑(#000)或纯白(#fff) |
| 调色板结构 | 主色 + 中性色 + 语义色 + 表面色令牌 |
| 60-30-10法则 | 60%中性色、30%辅助色、10%强调色 |
| 语义色彩 | 红色=错误、琥珀色=警告、绿色=成功、蓝色=信息 |
| 深色模式 | 独立设计(非简单反转)、品牌色降低饱和度 |
| 品牌色使用 | 仅用于交互元素 |
| 系统色彩搭配 | 始终搭配图标使用(不单独使用色彩) |
Dimension 6: Layout & Spacing
维度6:布局与间距
| Check | Standard |
|---|---|
| Spacing system | Consistent token scale (4pt or 8pt based) |
| Spacing variation | Rhythm through varied spacing (not uniform everywhere) |
| Alignment consistency | Few alignment axes per screen |
| Content max-width | Text constrained to 40-80 character line length |
| Grid usage | Appropriate tool: Flexbox for 1D, Grid for 2D |
| Responsive | Mobile-first, content-driven breakpoints |
| Container queries | Used for reusable components |
| 检查项 | 标准 |
|---|---|
| 间距系统 | 一致的令牌比例(基于4pt或8pt) |
| 间距变化 | 通过多样化间距营造节奏感(非全局统一间距) |
| 对齐一致性 | 每个页面仅使用少量对齐轴 |
| 内容最大宽度 | 文本限制为40-80字符的行长度 |
| 网格使用 | 合适的工具:Flexbox用于一维布局,Grid用于二维布局 |
| 响应式设计 | 移动端优先、内容驱动的断点 |
| 容器查询 | 用于可复用组件 |
Dimension 7: Interaction States
维度7:交互状态
Every interactive element must have these states defined:
| State | Visual Treatment |
|---|---|
| Default | Base appearance |
| Hover | Subtle shift (colour, shadow, or position) |
| Focus | Visible ring ( |
| Active/Pressed | Distinct from hover (scale or colour change) |
| Disabled | Reduced opacity OR removed with explanation |
| Loading | Inline indicator with specific status text |
| Error | Red styling + icon + descriptive message |
| Success | Green styling + icon + confirmation message |
每个交互元素必须定义以下状态:
| 状态 | 视觉处理 |
|---|---|
| 默认 | 基础外观 |
| 悬停 | 细微变化(色彩、阴影或位置) |
| 焦点 | 可见的焦点环(仅键盘交互时使用 |
| 激活/按下 | 与悬停状态区分(缩放或色彩变化) |
| 禁用 | 降低透明度或隐藏并附带说明 |
| 加载 | 内联指示器+具体状态文本 |
| 错误 | 红色样式+图标+描述性消息 |
| 成功 | 绿色样式+图标+确认消息 |
Dimension 8: Motion & Animation
维度8:动效与动画
| Check | Standard |
|---|---|
| Purpose | Every animation serves a function (feedback, guide, connect) |
| Timing | Follows 100/300/500 rule for category |
| Easing | Exponential curves (ease-out-quart/quint), no bounce/elastic |
| GPU-only | Transform + opacity only (no layout property animation) |
| Reduced motion | |
| Performance | 60fps on mid-range devices |
| Restraint | Not everything animates (no animation fatigue) |
| 检查项 | 标准 |
|---|---|
| 目的 | 每个动画都有明确功能(反馈、引导、关联) |
| 时长 | 遵循100/300/500分类规则 |
| 缓动 | 指数曲线(ease-out-quart/quint),禁止弹跳/弹性缓动 |
| GPU加速 | 仅使用Transform + opacity(不带动画布局属性) |
| 减少动效 | 提供 |
| 性能 | 中端设备上保持60fps |
| 克制 | 并非所有元素都需要动画(避免动画疲劳) |
Dimension 9: Content & Microcopy
维度9:内容与微文案
| Check | Standard |
|---|---|
| Button labels | Verb + noun (no "Submit", "OK", "Yes/No") |
| Error messages | What happened + why + how to fix |
| Empty states | Acknowledge + explain value + action |
| Loading text | Names the operation ("Saving your draft...") |
| Link text | Descriptive (no "Click here", "Learn more") |
| Vocabulary | Consistent terms throughout |
| Tone | Matches moment (serious for errors, warm for onboarding) |
| 检查项 | 标准 |
|---|---|
| 按钮标签 | 动词+名词(禁止使用"Submit"、"OK"、"Yes/No") |
| 错误消息 | 说明问题+原因+修复方法 |
| 空状态 | 告知用户+说明价值+提供操作 |
| 加载文本 | 明确操作名称(如"Saving your draft...") |
| 链接文本 | 描述性文本(禁止使用"Click here"、"Learn more") |
| 词汇一致性 | 全程使用一致术语 |
| 语气 | 匹配场景(错误场景严肃,引导场景亲切) |
Dimension 10: Performance
维度10:性能
| Check | Standard |
|---|---|
| LCP | < 2.5s on mid-range mobile |
| INP | < 200ms |
| CLS | < 0.1 |
| Initial load | < 650 KB compressed total |
| Images | WebP/AVIF, srcset, lazy loading, explicit dimensions |
| Fonts | |
| 检查项 | 标准 |
|---|---|
| LCP | 中端移动设备上<2.5s |
| INP | <200ms |
| CLS | <0.1 |
| 初始加载 | 压缩后总大小<650 KB |
| 图片 | 使用WebP/AVIF格式、srcset、懒加载、明确尺寸 |
| 字体 | 使用 |
3. Report Structure
3. 报告结构
Header
头部
undefinedundefinedDesign Audit Report
Design Audit Report
Date: [Date]
Auditor: Claude (AI-assisted)
Target: [Screen/feature name]
Platform: [Web/Android/iOS]
Context: [Brief description of purpose and users]
undefinedDate: [Date]
Auditor: Claude (AI-assisted)
Target: [Screen/feature name]
Platform: [Web/Android/iOS]
Context: [Brief description of purpose and users]
undefinedAI Slop Verdict
AI Slop结论
undefinedundefinedAI Slop Verdict: [PASS / BORDERLINE / FAIL]
AI Slop Verdict: [PASS / BORDERLINE / FAIL]
[1-2 sentence summary of why]
undefined[1-2 sentence summary of why]
undefinedExecutive Summary
执行摘要
undefinedundefinedExecutive Summary
Executive Summary
- Overall Score: [X/100]
- Critical Issues: [count]
- High Issues: [count]
- Medium Issues: [count]
- Low Issues: [count]
- What's Working: [1-3 bullet points of strengths]
- Top Priority: [The single most impactful fix]
undefined- Overall Score: [X/100]
- Critical Issues: [count]
- High Issues: [count]
- Medium Issues: [count]
- Low Issues: [count]
- What's Working: [1-3 bullet points of strengths]
- Top Priority: [The single most impactful fix]
undefinedFindings by Severity
按严重度分类的发现
undefinedundefinedCritical (Must Fix Before Ship)
Critical (Must Fix Before Ship)
[Finding Title]
[Finding Title]
- Dimension: [Which of the 10 dimensions]
- Location: [Where in the interface]
- Issue: [What's wrong]
- Impact: [Who is affected and how]
- Fix: [Specific actionable fix]
- Standard: [Which standard it violates]
- Dimension: [Which of the 10 dimensions]
- Location: [Where in the interface]
- Issue: [What's wrong]
- Impact: [Who is affected and how]
- Fix: [Specific actionable fix]
- Standard: [Which standard it violates]
High (Fix Within Sprint)
High (Fix Within Sprint)
[Same structure]
[Same structure]
Medium (Fix Within Quarter)
Medium (Fix Within Quarter)
[Same structure]
[Same structure]
Low (Nice to Have)
Low (Nice to Have)
[Same structure]
undefined[Same structure]
undefinedSeverity Definitions
严重度定义
| Severity | Meaning |
|---|---|
| Critical | Blocks users, fails accessibility law, data loss risk |
| High | Significant UX degradation, frequent user confusion |
| Medium | Noticeable quality issue, occasional friction |
| Low | Minor polish, edge case, aesthetic preference |
| 严重度 | 含义 |
|---|---|
| Critical | 阻碍用户使用、违反可访问性法规、存在数据丢失风险 |
| High | UX体验显著下降、用户频繁困惑 |
| Medium | 明显的质量问题、偶尔产生摩擦 |
| Low | 细微的优化点、边缘场景、审美偏好 |
Positive Findings
积极发现
undefinedundefinedWhat's Working Well
What's Working Well
[List patterns and decisions that are effective and should be maintained]
undefined[List patterns and decisions that are effective and should be maintained]
undefinedRecommendations
建议
undefinedundefinedPrioritised Recommendations
Prioritised Recommendations
- [Highest impact fix] — addresses [N] critical/high issues
- [Second priority] — addresses [N] issues
- [Third priority] — addresses [N] issues
---- [Highest impact fix] — addresses [N] critical/high issues
- [Second priority] — addresses [N] issues
- [Third priority] — addresses [N] issues
---4. Scoring Guide
4. 评分指南
| Score | Meaning |
|---|---|
| 90-100 | Production-ready. Minor polish only. |
| 75-89 | Good foundation. Fix high-priority issues before shipping. |
| 60-74 | Significant issues. Needs focused remediation sprint. |
| 40-59 | Major redesign areas. Multiple dimensions failing. |
| < 40 | Fundamental problems. Start with structure and hierarchy. |
| 分数 | 含义 |
|---|---|
| 90-100 | 可投入生产。仅需细微优化。 |
| 75-89 | 基础良好。上线前修复高优先级问题。 |
| 60-74 | 存在显著问题。需要集中整改迭代。 |
| 40-59 | 存在重大 redesign 需求。多个维度不达标。 |
| <40 | 存在根本性问题。需从结构和层级重新设计。 |
Dimension Weights
维度权重
| Dimension | Weight | Rationale |
|---|---|---|
| Accessibility | 20% | Legal requirement, blocks users |
| Visual Hierarchy | 15% | Foundation of usability |
| Interaction States | 12% | Functional completeness |
| Content & Microcopy | 12% | User comprehension |
| Typography | 10% | Readability |
| Colour | 8% | Communication and mood |
| Layout & Spacing | 8% | Structure and scannability |
| Performance | 6% | Speed and responsiveness |
| Motion | 5% | Polish and feedback |
| AI Slop | 4% | Distinctiveness (binary pass/fail) |
| 维度 | 权重 | 理由 |
|---|---|---|
| 可访问性 | 20% | 法律要求、阻碍用户使用 |
| 视觉层级 | 15% | 可用性基础 |
| 交互状态 | 12% | 功能完整性 |
| 内容与微文案 | 12% | 用户理解度 |
| 排版 | 10% | 可读性 |
| 色彩 | 8% | 沟通与氛围 |
| 布局与间距 | 8% | 结构与可扫描性 |
| 性能 | 6% | 速度与响应性 |
| 动效 | 5% | 优化与反馈 |
| AI Slop | 4% | 独特性(二元通过/不通过) |
5. Quick Audit Checklist (10-Minute Version)
5. 快速审计清单(10分钟版)
For rapid checks when a full audit isn't needed:
- AI Slop: Does this look machine-generated? (fonts, colours, layout)
- Hierarchy: Squint test passes — primary element is clear
- Contrast: Body text >= 4.5:1, UI components >= 3:1
- Touch targets: >= 44x44px on touch devices
- Keyboard: Tab through the page — focus visible, logical order
- States: Hover, focus, active, error, loading all defined
- Buttons: All use verb + noun labels
- Errors: All show what, why, how to fix
- Empty states: No blank screens
- Responsive: Works on mobile without horizontal scroll
- Performance: Loads in < 3s on mobile
- Motion: No bounce easing, reduced motion handled
Sources: Impeccable audit and critique skills (Bakaus, 2025); WCAG 2.2 AA; Nielsen Norman Group heuristic evaluation framework.
当不需要完整审计时,可进行快速检查:
- AI Slop:界面是否看起来是机器生成的?(字体、色彩、布局)
- 层级结构:眯眼测试通过——核心元素清晰可见
- 对比度:正文文本>=4.5:1,UI组件>=3:1
- 触摸目标:触摸设备上>=44x44px
- 键盘导航:按Tab键遍历页面——焦点可见、顺序合理
- 交互状态:悬停、焦点、激活、错误、加载状态均已定义
- 按钮:全部使用动词+名词标签
- 错误提示:全部说明问题、原因及修复方法
- 空状态:无空白页面
- 响应式:移动端可正常使用,无横向滚动
- 性能:移动端加载时间<3s
- 动效:无弹跳缓动、已处理减少动效需求
资料来源:无懈可击的审计与评审技能(Bakaus, 2025);WCAG 2.2 AA;尼尔森诺曼集团启发式评估框架。