audit-ai-design-slop

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Audit AI Design Slop

审核AI冗余设计（AI Design Slop）

Run a diagnostic, evidence-backed audit. Identify the smallest set of removals or corrections that would improve the interface while preserving its existing direction.

开展基于证据的诊断式审核。找出最精简的移除或修改方案，在保留现有设计方向的前提下优化界面。

Boundaries

边界规则

Do not guess whether AI made the design.
Do not assign a numeric slop score.
Do not reject a visual technique in isolation. A gradient, serif, dark theme, glass effect, card, animation, or single-font system can be intentional.
Do not prescribe a new font, palette, layout, design system, or art direction unless the user explicitly asks for one.
Do not turn an audit into an implementation task.
Mark anything outside the visible or provided evidence as unknown.

不要猜测设计是否由AI生成。
不要给冗余内容（Slop）打分数值评分。
不要孤立地否定某种视觉技术。渐变、衬线字体、深色主题、毛玻璃效果、卡片、动画或单一字体系统都可能是有意设计的。
除非用户明确要求，否则不要指定新字体、调色板、布局、设计系统或艺术方向。
不要将审核转化为实施任务。
任何超出可见或提供证据范围的内容都标记为未知。

Audit the Evidence

审核证据

Inspect the artifact available in the request:

screenshots and recordings
rendered pages and relevant viewports
interaction and state changes
source code, tokens, assets, and copy
console or runtime failures when they affect the experience

For every finding, cite a concrete location, component, behavior, or line of copy. Do not report a generic tendency without evidence in the artifact.

For a full-page or full-site review, read ../no-ai-design-slop/ARTICLE.md and use only the catalog sections relevant to the inspected artifact. Do not turn every checklist match into a finding. Group symptoms by root cause and report the highest-impact evidence.

检查请求中提供的工件：

截图和录屏
渲染页面及相关视口
交互和状态变化
源代码、设计令牌、资源和文案
影响用户体验的控制台或运行时错误

每一项发现都要引用具体位置、组件、行为或文案内容。不要在工件中没有证据的情况下报告通用趋势。

若进行整页或全站审查，请阅读../no-ai-design-slop/ARTICLE.md，仅使用与被审核工件相关的目录章节。不要将每个符合检查清单的项都列为发现。按根本原因对症状进行分组，并报告影响最大的证据。

Classify Findings

分类发现

Use one of these classes:

Quality defect: an established usability, accessibility, content, responsive, or runtime problem.
Slop pattern: a repeated default, decorative layer, or generated-looking convention with no useful role.

使用以下分类之一：

质量缺陷： 已确认的可用性、可访问性、内容、响应式或运行时问题。
冗余模式： 重复的默认项、装饰层或看似生成的无意义惯例。

What to Flag

需标记的问题

Decorative stacking

装饰堆叠

Flag combinations of glow, gradient text, glass, borders, shadows, grids, particles, beams, noise, floating shapes, or browser chrome when multiple layers perform the same decorative job or compete with the content.

当发光、渐变文字、毛玻璃、边框、阴影、网格、粒子、光束、噪点、浮动形状或浏览器界面元素等组合出现多层执行相同装饰功能或与内容产生冲突时，标记此类问题。

Component and template repetition

组件与模板重复

Flag:

card treatment applied to nearly every content block
repeated icon-heading-description tiles with interchangeable content
nested rounded containers that do not communicate hierarchy
generic landing-page sequences unrelated to the product's buying or usage journey
headings, labels, pills, or CTA blocks that restate nearby information

标记以下情况：

几乎每个内容块都使用卡片样式
内容可互换的重复图标-标题-描述模块
无法传达层级关系的嵌套圆角容器
与产品购买或使用流程无关的通用着陆页序列
重复附近信息的标题、标签、胶囊按钮或CTA块

Typography and copy clutter

排版与文案杂乱

Flag:

duplicate text or unnecessary labels
empty superlatives, vague category claims, and generated filler
decorative type treatments that obscure hierarchy or readability
long centered paragraphs, awkward forced line breaks, or hard-to-scan text
inconsistent type roles that look accidental rather than expressive

标记以下情况：

重复文本或不必要的标签
空洞的最高级表述、模糊的类别声明以及生成式填充内容
模糊层级或影响可读性的装饰性文字样式
长居中段落、生硬的强制换行或难以阅读的文本
字体角色不一致，看起来是意外而非有意设计的

Motion theater

无效动效

Flag motion that delays access, repeats mechanically, distracts from reading, moves targets, blocks input, or lacks respect for reduced-motion preferences. Preserve motion that communicates state, causality, hierarchy, or spatial change.

标记以下动效：延迟访问、机械重复、分散阅读注意力、移动目标元素、阻挡输入，或未考虑减少动效偏好的动效。保留用于传达状态、因果关系、层级或空间变化的动效。

Fake proof

虚假证据

Flag invented or unverifiable metrics, customers, testimonials, awards, ratings, activity, dashboards, charts, logos, and portraits when they are presented as evidence.

标记被当作证据展示的虚构或无法验证的指标、客户、推荐语、奖项、评分、活动数据、仪表盘、图表、标志和肖像。

Established UI failures

已确认的UI问题

Flag:

unclear or competing primary actions
low contrast or unreadable content
clipping, overflow, overlap, or broken responsive behavior
broken assets, links, scripts, or controls
essential information available only on hover
missing states required by the observed flow
unclear labels, roles, feedback, or keyboard focus
accidental inconsistency in spacing, type, color, radius, or icons
visual hierarchy that contradicts task importance

标记以下情况：

不明确或相互冲突的主要操作
对比度低或无法阅读的内容
内容裁剪、溢出、重叠或响应式行为失效
失效的资源、链接、脚本或控件
仅在悬停时显示的关键信息
观察到的流程中缺失必要的状态
标签、角色、反馈或键盘焦点不明确
间距、字体、颜色、圆角或图标存在意外不一致
视觉层级与任务重要性不符

Use the Removal Test

移除测试流程

For every candidate:

State what information, state, action, hierarchy, or brand meaning it provides.
Ask whether removing it would improve clarity without losing that role.
If yes, recommend removal or consolidation.
If no, recommend the smallest correction using the existing system.
Suggest a replacement only when deletion would create a real loss.

Default to subtraction. A replacement should inherit the product's existing language rather than introduce a new visual concept.

针对每个待评估项：

说明它提供了哪些信息、状态、操作、层级或品牌含义。
询问移除它是否能在不丢失上述作用的前提下提升清晰度。
如果是，建议移除或合并。
如果否，建议使用现有系统进行最小幅度的修改。
仅当删除会造成实际损失时，才建议替换。

默认优先选择移除。替换方案应沿用产品现有设计语言，而非引入新的视觉概念。

Prioritize

优先级划分

P0: blocks completion, creates a severe accessibility issue, or presents deceptive proof
P1: materially harms comprehension, trust, navigation, or interaction
P2: repeated slop or inconsistency that weakens hierarchy and identity
P3: minor polish issue with limited user impact

Return the five to eight highest-impact findings by default. Group repeated instances into one systemic finding.

P0： 阻碍任务完成、造成严重可访问性问题，或呈现欺骗性证据
P1： 对理解、信任、导航或交互造成实质性损害
P2： 重复的冗余内容或不一致性，削弱了层级和品牌辨识度
P3： 对用户影响有限的细微优化问题

默认返回5-8个影响最大的发现。将重复实例归为一个系统性发现。

Output

输出格式

undefined

undefined

Verdict

One concise paragraph about the dominant problems and what should be removed first.

Checked scope

Artifact, screen, state, and viewport actually inspected

Artifact, screen, state, and viewport actually inspected

Findings

Priority	Class	Pattern	Evidence	Harm	Remove or fix
P1	Slop pattern	Repeated ornamental containers	Feature area uses the same layered card treatment for unrelated content	Flattens hierarchy and adds noise	Remove outer shells; retain grouping only where it communicates interaction

Priority	Class	Pattern	Evidence	Harm	Remove or fix
P1	Slop pattern	Repeated ornamental containers	Feature area uses the same layered card treatment for unrelated content	Flattens hierarchy and adds noise	Remove outer shells; retain grouping only where it communicates interaction

Unknowns

Important states or behavior that could not be verified


Keep the report compact. Omit empty sections.

Important states or behavior that could not be verified


保持报告简洁。省略空章节。

Feedback Rules

反馈规则

Lead with concrete evidence, not taste claims.
Name the pattern and its harm.
Recommend removal before restyling.
Avoid generic compliments and exhaustive low-impact nitpicks.
Preserve useful product-specific detail and intentional character.
Do not cite a standard unless it directly supports the finding.
Do not describe an aesthetic as universally bad.
If the user explicitly asks for design swaps, place an optional replacement after the removal recommendation and keep it consistent with the existing system.
End with the single removal or correction that would produce the largest improvement.

以具体证据为先，而非主观品味判断。
明确指出模式及其危害。
优先建议移除，而非重新设计样式。
避免泛泛的赞美和详尽的低影响细节挑剔。
保留有用的产品特定细节和有意设计的特色。
除非标准直接支持发现，否则不要引用标准。
不要将某种美学风格描述为普遍糟糕。
如果用户明确要求替换设计，在移除建议后附上可选替换方案，并确保其与现有系统一致。
以能带来最大改善的单一移除或修改建议收尾。