Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhnpx agentmods add skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-maxWrote 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.
[](https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-max)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-max"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-max/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.
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-max"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/ui-ux-pro-max.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00297 | $0.12648 |
| Opus 5.5 | $0.00119 | $0.05059 |
| Sonnet 5.5 | $0.00059 | $0.02530 |
| Haiku 4.5 | $0.00030 | $0.01265 |
Grade B, and why
ui-ux-pro-max scanned grade B 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install python3 How it starts
The opening of the file, as written. The whole thing — 660 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Pro Max - 设计智能指南
全面的设计指南，适用于 Web 和移动应用。包含 50+ 种风格、161 种配色方案、57 种字体搭配、161 种带推理规则的产品类型、99 条 UX 准则和 25 种图表类型，覆盖 10 大技术栈。支持搜索的数据库，提供基于优先级的推荐。
何时使用
当任务涉及 UI 结构、视觉设计决策、交互模式或用户体验质量控制 时，应使用此技能。
必须使用
在以下情况下必须调用此技能：
- 设计新页面（落地页、仪表盘、管理后台、SaaS、移动应用）
- 创建或重构 UI 组件（按钮、模态框、表单、表格、图表等）
- 选择配色方案、字体系统、间距标准或布局系统
- 审查 UI 代码的用户体验、无障碍性或视觉一致性
- 实现导航结构、动画或响应式行为
- 做出产品级别的设计决策（风格、信息层级、品牌表达）
- 改善界面的感知质量、清晰度或可用性
推荐使用
在以下情况下推荐使用此技能：
- UI 看起来"不够专业"但原因不明确
- 收到关于可用性或体验的反馈
- 发布前的 UI 质量优化
- 跨平台设计对齐（Web / iOS / Android）
- 构建设计系统或可复用组件库
无需使用
在以下情况下不需要此技能：
- 纯后端逻辑开发
- 仅涉及 API 或数据库设计
- 与界面无关的性能优化
- 基础设施或 DevOps 工作
- 非可视化脚本或自动化任务
决策标准：如果任务会改变功能的 外观、感觉、动效或交互方式，则应使用此技能。
按优先级排列的规则类别
供人类/AI 参考：按优先级 1→10 决定首先关注哪个规则类别；需要时使用 --domain <Domain> 查询详情。脚本不读取此表。
| 优先级 | 类别 | 影响 | 领域 | 关键检查（必须有） | 反模式（避免） |
|---|---|---|---|---|---|
| 1 | 无障碍性 | 关键 | ux |
对比度 4.5:1、替代文本、键盘导航、Aria 标签 | 移除焦点环、无标签的纯图标按钮 |
| 2 | 触控与交互 | 关键 | ux |
最小尺寸 44×44px、8px+ 间距、加载反馈 | 仅依赖悬停、瞬时状态变化（0ms） |
| 3 | 性能 | 高 | ux |
WebP/AVIF、懒加载、预留空间（CLS < 0.1） | 布局抖动、累积布局偏移 |
| 4 | 风格选择 | 高 | style, product |
匹配产品类型、一致性、SVG 图标（不用 emoji） | 随机混合扁平与拟物化、用 emoji 作为图标 |
| 5 | 布局与响应式 | 高 | ux |
移动优先断点、Viewport meta、无横向滚动 | 横向滚动、固定 px 容器宽度、禁用缩放 |
| 6 | 排版与颜色 | 中 | typography, color |
基础 16px、行高 1.5、语义化颜色令牌 | 正文文本 < 12px、灰底灰字、组件中使用原始 hex |
| 7 | 动画 | 中 | ux |
持续时间 150–300ms、动效传达意义、空间连续性 | 纯装饰性动画、动画 width/height、无 reduced-motion |
| 8 | 表单与反馈 | 中 | ux |
可见标签、错误靠近字段、帮助文本、渐进式披露 | 仅用占位符作标签、错误仅在顶部、一开始就堆砌信息 |
| 9 | 导航模式 | 高 | ux |
可预测的返回、底部导航 ≤5 项、深度链接 | 导航过载、返回行为异常、无深度链接 |
| 10 | 图表与数据 | 低 | chart |
图例、工具提示、无障碍颜色 | 仅依靠颜色传达意义 |
快速参考
1. 无障碍性（关键）
color-contrast- 普通文本最小对比度 4.5:1（大文本 3:1）；Material Designfocus-states- 交互元素上可见的焦点环（2–4px；Apple HIG, MD）alt-text- 有意义的图片需要描述性替代文本aria-labels- 纯图标按钮使用 aria-label；原生端使用 accessibilityLabel（Apple HIG）keyboard-nav- Tab 顺序与视觉顺序一致；完整键盘支持（Apple HIG）form-labels- 使用 label 配合 for 属性skip-links- 为键盘用户提供跳转到主内容的链接heading-hierarchy- 顺序使用 h1→h6，不跳级color-not-only- 不要仅靠颜色传达信息（添加图标/文本）dynamic-type- 支持系统文字缩放；避免文字增长时被截断（Apple Dynamic Type, MD）reduced-motion- 尊重 prefers-reduced-motion；请求时减少/禁用动画（Apple Reduced Motion API, MD）voiceover-sr- 有意义的 accessibilityLabel/accessibilityHint；VoiceOver/屏幕阅读器的逻辑阅读顺序（Apple HIG, MD）escape-routes- 在模态框和多步骤流程中提供取消/返回选项（Apple HIG）keyboard-shortcuts- 保留系统和无障碍快捷键；为拖放提供键盘替代方案（Apple HIG）
What ships with it
2 files 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.
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.
- 2mo ago First seen · 660 lines · 297 tokens per session scan B 9fef643b39b3
ui-ux-pro-max is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (57 stars, last pushed 7mo ago), licensed MIT. It adds 297 tokens to every session and 12,648 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
ui-ux-pro-max compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ui-ux-pro-maxL-LesterYu/OpenClaw-hot-skills-zh | Skill | 57 | 7mo ago | MIT | B | 297 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 47 | Claude Code |