frontend-design-review
microsoft/skills
根据设计质量标准和设计系统规范审查 UI 实现,或从零开始创建独特且符合生产环境标准的前端界面。
...展开全部前端设计评审
根据设计质量标准和您的设计体系,审查UI实现效果;或者从零开始创建独特且符合生产级标准的前端界面。
两种模式
模式 1:设计评审
评估现有UI是否符合设计系统规范、三大质量支柱(无摩擦、精工细作、值得信赖)、无障碍性及代码质量。
模式 2:创意前端设计
打造独具特色的前端界面,避免千篇一律的“AI粗制滥造”美学,确立清晰的概念方向,并精准实现。
创意前端设计
在编写代码之前,需确定美学方向:
- 目的:这能解决什么问题?目标用户是谁?
- 风格:极简、极繁、复古未来主义、有机、奢华、俏皮、编辑风格、粗野主义、装饰艺术、柔和/粉彩、工业风等。
- 限制条件:框架、性能、无障碍要求。
- 差异化:是什么让它独具特色且契合使用场景?
美学指南
- 排版:选用能提升美感的独特字体。将展示字体与精致的正文字体搭配使用。避免使用 Inter、Roboto、Arial 和 Space Grotesk。
- 色彩与主题:使用 CSS 变量构建统一的配色方案。主色调 + 鲜明点缀 > 怯懦且均匀分布的配色方案。
- 动态效果:优先采用纯CSS实现。通过错落有致的渐显效果,打造一次精心编排的页面加载体验 > 避免零散的微交互。
- 空间构图:不对称、重叠、对角线流动、打破网格的元素、充裕的负空间或受控的密度。
- 背景:渐变网格、噪点纹理、几何图案、分层透明效果、戏剧性阴影、颗粒叠加。
应避免:过度使用的字体、陈词滥调的配色方案、可预测的布局、缺乏情境特质的千篇一律设计。
让实现复杂度与设计愿景相匹配。极繁主义 = 复杂的代码。极简主义 = 克制与精准。
设计评审
设计系统工作流
实施前:
- 在 Storybook 或组件库中审查组件的 API 及用法
- 使用 Figma 开发模式获取精确规格(间距、设计令牌、属性)
- 使用设计系统组件 + 设计令牌进行实现
审核阶段:
- 将实现结果与 Figma 设计进行对比
- 验证是否使用了设计令牌(而非硬编码值)
- 检查所有变体/状态是否已正确实现
- 标记偏差(需设计审核)
如果组件不存在:
- 检查现有组件是否可进行适配
- 联系设计部门创建新组件
- 在代码中记录例外情况及理由
审核流程
- 确定用户任务
- 在设计系统中查找匹配的模式
- 评估美学方向
- 确定范围(组件、功能或流程)
- 评估各支柱
- 对问题进行评分并排序(阻塞型/重大/轻微)
- 结合设计系统示例提供建议
核心原则
- 任务完成:点击次数最少。每个界面都要回答“我能做什么?”和“接下来会发生什么?”
- 操作层次结构:每个视图包含1-2个主要操作。次要操作采用渐进式披露。
- 入门引导:在介绍阶段说明功能。优先采用智能默认值而非配置选项。
- 导航:明确的入口/出口。始终提供“返回”/“取消”选项。对于深度流程,应使用面包屑导航。
质量支柱
1. 无缝衔接洞察与行动
评估:任务能否在≤3次交互内完成?主要操作是否显而易见且唯一?
警示信号:点击次数过多、多个主要按钮相互冲突、操作被埋没、流程陷入死胡同。
2. 质量源于匠心
评估:
- 设计系统合规性:符合 Figma 规范,使用设计令牌
- 美学方向:独特的排版、协调的配色、精心设计的动效
- 无障碍性:最低 C 级(WCAG 2.1 A),理想为 B 级(WCAG 2.1 AA)
红旗警告:千篇一律的AI美学、硬编码值、实现与Figma不符、排版错乱、缺少焦点指示器。
3. 值得信赖的构建
评估:
- AI透明度:AI生成内容的免责声明
- 错误透明度:提供可操作的错误提示
红旗:缺少AI免责声明,错误信息不透明且缺乏指导。
评审输出格式
请参阅 references/review-output-format.md 以获取完整的评审模板。
评审类型修饰符
请参阅 references/review-type-modifiers.md 以了解针对不同场景的评审重点领域(PR、创意、设计、无障碍性)。
快速检查清单
请参阅 references/quick-checklist.md,了解涵盖设计系统合规性、美学品质、无摩擦体验、精湛工艺和可信赖性等核心要素的审批前核查清单。
模式示例
请参阅 references/pattern-examples.md,了解前端创意及设计系统评审工作的优秀与劣例。
致谢
创意前端原则受 Anthropic 的前端设计技能启发。设计评审原则和质量支柱框架由 @Quirinevwm 创建,用于系统化的 UI 评估。
---
name: frontend-design-review
description: Review UI implementations against design quality standards and design system compliance, or create distinctive, production-grade frontend interfaces from scratch.
---
# Frontend Design Review
Review UI implementations against design quality standards and your design system **OR** create distinctive, production-grade frontend interfaces from scratch.
## Two Modes
### Mode 1: Design Review
Evaluate existing UI for design system compliance, three quality pillars (Frictionless, Quality Craft, Trustworthy), accessibility, and code quality.
### Mode 2: Creative Frontend Design
Create distinctive interfaces that avoid generic "AI slop" aesthetics, have clear conceptual direction, and execute with precision.
---
## Creative Frontend Design
Before coding, commit to an aesthetic direction:
- **Purpose**: What problem does this solve? Who uses it?
- **Tone**: minimal, maximalist, retro-futuristic, organic, luxury, playful, editorial, brutalist, art deco, soft/pastel, industrial, etc.
- **Constraints**: Framework, performance, accessibility requirements.
- **Differentiation**: What makes this distinctive and context-appropriate?
### Aesthetics Guidelines
- **Typography**: Distinctive fonts that elevate aesthetics. Pair a display font with a refined body font. Avoid Inter, Roboto, Arial, Space Grotesk.
- **Color & Theme**: Cohesive palette with CSS variables. Dominant colors + sharp accents > timid, evenly-distributed palettes.
- **Motion**: CSS-only preferred. One well-orchestrated page load with staggered reveals > scattered micro-interactions.
- **Spatial Composition**: Asymmetry, overlap, diagonal flow, grid-breaking elements, generous negative space OR controlled density.
- **Backgrounds**: Gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, grain overlays.
**AVOID**: Overused fonts, cliched color schemes, predictable layouts, cookie-cutter design without context-specific character.
Match implementation complexity to vision. Maximalist = elaborate code. Minimalist = restraint and precision.
---
## Design Review
### Design System Workflow
**Before implementing:**
1. Review component in your Storybook / component library for API and usage
2. Use Figma Dev Mode to get exact specs (spacing, tokens, properties)
3. Implement using design system components + design tokens
**During review:**
1. Compare implementation to Figma design
2. Verify design tokens are used (not hardcoded values)
3. Check all variants/states are implemented correctly
4. Flag deviations (needs design approval)
**If component doesn't exist:**
1. Check if existing component can be adapted
2. Reach out to design for new component creation
3. Document exception and rationale in code
### Review Process
1. Identify user task
2. Check design system for matching patterns
3. Evaluate aesthetic direction
4. Identify scope (component, feature, or flow)
5. Evaluate each pillar
6. Score and prioritize issues (blocking/major/minor)
7. Provide recommendations with design system examples
### Core Principles
- **Task completion**: Minimum clicks. Every screen answers "What can I do?" and "What happens next?"
- **Action hierarchy**: 1-2 primary actions per view. Progressive disclosure for secondary.
- **Onboarding**: Explain features on introduction. Smart defaults over configuration.
- **Navigation**: Clear entry/exit points. Back/cancel always available. Breadcrumbs for deep flows.
---
## Quality Pillars
### 1. Frictionless Insight to Action
**Evaluate:** Task completable in ≤3 interactions? Primary action obvious and singular?
**Red flags:** Excessive clicks, multiple competing primary buttons, buried actions, dead ends.
### 2. Quality is Craft
**Evaluate:**
- Design system compliance: matches Figma specs, uses design tokens
- Aesthetic direction: distinctive typography, cohesive colors, intentional motion
- Accessibility: Grade C minimum (WCAG 2.1 A), Grade B ideal (WCAG 2.1 AA)
**Red flags:** Generic AI aesthetics, hardcoded values, implementation doesn't match Figma, broken reflow, missing focus indicators.
### 3. Trustworthy Building
**Evaluate:**
- AI transparency: disclaimer on AI-generated content
- Error transparency: actionable error messages
**Red flags:** Missing AI disclaimers, opaque errors without guidance.
---
## Review Output Format
See [references/review-output-format.md](references/review-output-format.md) for the full review template.
## Review Type Modifiers
See [references/review-type-modifiers.md](references/review-type-modifiers.md) for context-specific review focus areas (PR, Creative, Design, Accessibility).
## Quick Checklist
See [references/quick-checklist.md](references/quick-checklist.md) for the pre-approval checklist covering design system compliance, aesthetic quality, frictionless, quality craft, and trustworthy pillars.
## Pattern Examples
See [references/pattern-examples.md](references/pattern-examples.md) for good/bad examples of creative frontend and design system review work.
---
## Acknowledgments
Creative frontend principles inspired by [Anthropic's frontend-design skill](https://github.com/anthropics/skills/tree/main/skills/frontend-design). Design review principles and quality pillar framework created by [@Quirinevwm](https://github.com/Quirinevwm) for systematic UI evaluation.





首页
