Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sanhuang520-ship-it/awesome-chinese-ai-tools --skill chinese-design-mdgit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote 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/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-design-md)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-design-md"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-design-md/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/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-design-md"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 97 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00106 | $0.01422 |
| Opus 5 | $0.00053 | $0.00711 |
| Sonnet 5 | $0.00021 | $0.00284 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
chinese-design-md scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中式 DESIGN.md
DESIGN.md 是给 AI 编程工具读的设计系统文档。 放到项目根目录， AI 生成界面时就照着里面的颜色、字体、组件规则来，不用你每次描述一遍。
这个技能提供 8 套中式设计系统，格式与社区通行的 DESIGN.md 一致。
什么时候用
要做中国风网页 / 国风 H5 / 中式品牌页；或者你只是不想让 AI 又生成一个 「紫色渐变 + 圆角卡片」的通用界面。
怎么用
# 1. 挑一套，复制到项目根目录
cp skills/chinese-design-md/design-md/ink/DESIGN.md ./DESIGN.md
# 2. 告诉你的 AI 编程工具
按照项目根目录 DESIGN.md 里的设计规范，实现这个页面
就这两步。Claude Code、Codex、Cursor 都能读。
8 套怎么选
| 主题 | 气质 | 适合 |
|---|---|---|
水墨 ink |
宣纸、墨色层次、大留白 | 长文阅读、文化内容、需要安静的界面 |
青绿 azurite |
石青石绿矿物色、装饰性强 | 文旅、展览、需要贵气的场景 |
宋韵 song |
素雅克制、青瓷灰绿 | 茶饮、书店、高端服务 |
敦煌 dunhuang |
土红石青、斑驳壁画质感 | 文化 IP、叙事型页面 |
朱砂 vermilion |
雅红、暖白底 | 节日、活动页、转化页 |
新中式 neo |
木色暖灰、低饱和 | 家居、生活方式、品牌官网。最百搭 |
竹韵 bamboo |
竹青素白、清爽 | 健康、教育、环保 |
夜宴 night |
深色底 + 暖金。唯一深色 | 影音、夜间模式、高端活动 |
拿不准就用 新中式。
每份 DESIGN.md 里有什么
YAML frontmatter（语义化 color token，AI 直接读）+ 这些章节：
Overview（含出处）· Colors（含逐项对比度实测）· Typography（中文排版规则） · Layout · Elevation · Shapes · Components · Do's and Don'ts · Responsive · Iteration Guide · Known Gaps
⭐ 关键差异：中文排版
这是多数设计系统缺的一块。西文 DESIGN.md 的 Typography 章节讲的是字重、 字距、x-height —— 搬到中文页面上基本不适用。
每份文件里写死了这些：
| 规则 | 值 | 为什么 |
|---|---|---|
| 行高 | 1.75 | 中文字面率高，1.5 会挤 |
| 行宽 | 38em | 中文每行 30–40 字最舒服 |
| 对齐 | left，不用 justify | 中文没有词间空格，两端对齐会拉出难看的字距 |
| 断行 | line-break: strict |
CJK 避头尾：。，、）」 不能出现在行首 |
| 强调 | text-emphasis: dot |
中文不用斜体 —— 系统中文字体没有真正的意大利体 |
| 中英间距 | 加空格 | 「使用 AI 工具」比「使用AI工具」易读 |
而且不依赖任何商业字体，全部用系统自带中文字体——不会出现「设计稿好看、上线糊掉」。
对比度是实测的，不是声称的
每份文件里有一张实测表（用 WCAG 相对亮度公式算的），并且标出了不达标的项：
- 8 套的正文与标题对比度全部通过 AA（9.40:1 – 17.10:1）
song的辅助文字色 4.23:1、主色 2.83:1 未达 AA —— 文件里写明了只能用于色块和大字neo的主色 4.46:1 略低于 AA —— 同样标注了
标出自己不达标的地方，比笼统说一句「全部通过」有用。
这个技能不做的事
- 不做西文设计系统 —— 要 Stripe、Linear 那种风格，去用社区里现成的 74 份
- 不保证「像某个具体品牌」 —— 这 8 套是美学传统的提炼，不是对任何公司视觉的复刻
- 不提供商业字体 —— 只用系统字体，这是刻意的
- 色值不代表传统色的权威标准 —— 传统色在不同文献里本就有出入，这是本设计系统自己的实现
What ships with it
8 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.
- 12d ago First seen · 98 lines · 106 tokens per session scan A 4e915ee112b4
chinese-design-md is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 106 tokens to every session and 1,422 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.
prototype
Build a self-contained local prototype at .turbo/prototypes/ .html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Use when the user asks to "prototype this", "build a prototype", "mock this up", "show me what it would look like", "let me try the interaction first", or when a decision…
user-experience
Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path through it holds together, using the Understanding, Bridging, and Flowing contexts. Use when scoping, planning, or assessing any change that affects what a user sees or does. Loaded as a lens during planning and…
flowchart-creator
Create HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes. Use when users request flowcharts, process diagrams, workflow visualizations, or decision trees.
design-swarm
Orchestrate a team of 10 design agents for holistic UI audit, ideation, and implementation. Use when: "design swarm", "holistic audit", "design review with all lenses", "full design analysis". Modes: audit, ideate, implement (any combination). Targets: screenshots, URLs, file paths, or text briefs.
diagram
Generate modern reviewable diagrams (system architecture, workflow, data flow, sequence, ER, state-machine, C4) via OpenRouter image-gen or LLM-emitted SVG. Auto-classifies diagram type from prompt; --type to override. Default scratch output goes to the resolved workbench visuals path; --versioned writes git-trackable…