Ui critique coach
评审网页、App、后台系统、表单、原型或截图的用户任务、信息层级、交互状态、可访问性、响应式行为和视觉一致性,输出按 P0-P3 严重度排序的证据化修改建议。适用于 UI/UX 评审、页面改版、截图分析、设计验收、移动端检查和“这个界面哪里有问题”。From its SKILL.md
npx -y skills add linxumoney/ui-critique-coach --skill ui-critique-coachAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.2 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
UI 评审教练
从用户是否能完成任务开始评审,再讨论视觉表现。每条意见必须指向可观察证据和实际影响,避免“更高级”“更有呼吸感”这类无法执行的反馈。
输入
可使用截图、设计稿、页面链接、代码或文字描述。尽量确定:
- 目标用户。
- 页面核心任务。
- 设备和主要视口。
- 当前设计系统或品牌约束。
- 已知数据、错误和业务规则。
缺少信息时根据界面做保守推断,并标注假设。
评审顺序
1. 任务路径
检查用户能否识别:我在哪里、可以做什么、下一步是什么、完成后发生什么。优先发现阻断、误导和不可恢复操作。
2. 信息层级
检查标题、主要动作、次要动作、状态和辅助信息是否有清晰优先级。页面不应让装饰、营销文案或重复卡片压过核心任务。
3. 交互与状态
覆盖:
- 默认、悬停、焦点、按下和禁用。
- 加载、空、成功、错误、部分成功和离线。
- 表单校验、撤销、确认和危险操作。
- 权限不足、数据过期和并发冲突。
4. 可访问性
检查语义、键盘顺序、焦点可见性、标签、错误关联、替代文本、颜色对比、缩放、动态内容提示和减少动画偏好。
不只依赖颜色传达状态。不确定是否满足标准时建议使用自动化工具和人工键盘/读屏测试复核。
5. 响应式与内容压力
检查窄屏、长文本、国际化、动态数字、图片失败、浏览器缩放和软键盘。固定格式控件应有稳定尺寸,文本不能重叠或溢出。
6. 视觉一致性
最后检查间距、字体、颜色、图标、边框、圆角、阴影和组件复用。遵循已有设计系统,不为了“创新”制造新样式。
严重度
P0 阻断:核心任务无法完成、数据丢失、严重安全或无障碍障碍。P1 高:大量用户可能误操作、无法理解或在常见设备失败。P2 中:增加认知负担、降低效率或造成明显不一致。P3 低:视觉细节和轻微打磨。
严重度基于影响和发生概率,不基于个人喜好。
输出格式
总体判断:一句话说明核心任务是否清楚可完成
问题清单:
| 严重度 | 位置 | 观察证据 | 用户影响 | 建议修改 | 验证方式 |
缺失状态:
- 状态 + 需要的反馈
响应式风险:
- 视口/内容条件 + 风险
优先改三项:
1. 修改 + 原因
保留项:
- 已经有效、不应在改版中丢失的设计
边界
- 不因为流行趋势强行改掉现有品牌和组件系统。
- 不把个人审美写成可用性事实。
- 不在看不到交互时假装验证过完整流程。
- 不忽略错误、空状态和移动端。
- 不建议欺骗性设计、隐藏费用或阻碍用户退出。
What ships with it: 1 file
312 B alongside SKILL.md
agents/
- openai.yaml312 B
Gives 0 of the 12 instructions most design frontend skills give in ~1.1k tokens
Counted across 1,169 of the 1,878 authors here whose files we hold, read 2026-08-07
- Use CSS variables for color consistencyin 72 of 1169, across 23 files
- Commit to one bold aesthetic direction before codingin 72 of 1169, across 27 files
- Match implementation complexity to the aesthetic visionin 70 of 1169, across 20 files
- Add atmospheric background effects and texturesin 57 of 1169, across 9 files
- Use unexpected spatial compositions and layoutsin 56 of 1169, across 8 files
- Implement real working codein 55 of 1169, across 7 files
- Vary themes and aesthetics across different designsin 48 of 1169, across 7 files
- Launch chromium in headless modein 47 of 1169, across 4 files
- Close the browser when donein 47 of 1169, across 4 files
- Run provided scripts with help flag firstin 47 of 1169, across 4 files
- Wait for network idle statein 47 of 1169, across 4 files
- Use descriptive selectors for elementsin 47 of 1169, across 4 files
Said here and by no other author read
- start review from user task completion
- base every opinion on observable evidence
- evaluate user task paths first
- review interaction and error states
- assign severity by impact and probability
- output a severity-sorted issue table
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.