Zack Design Router logo

Zack Design Router

Community
yckonnnnn
zack-design-router

设计任务的统一入口与路由。当用户要求做网页/App/落地页/后台界面、改版现有网站、评审界面、还原设计稿、或抱怨「看起来像 AI 做的」「不够高级」时,先用本技能判定任务类型,再按路由表加载对应的 zack-* 技能。不负责纯业务逻辑、接口、部署、无界面变化的代码整理。

Overview

Publisheryckonnnnn
Repositoryzack-design-skills
Skill namezack-design-router
Stars
7
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by yckonnnnn on GitHub. Read the source before you install it.

Installation

Install the Zack Design Router AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yckonnnnn/zack-design-skills/tree/main/skills/zack-design-router
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yckonnnnn/zack-design-skills.git /tmp/zack-design-skills
mkdir -p .claude/skills
cp -r /tmp/zack-design-skills/skills/zack-design-router .claude/skills/zack-design-router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zack Design Router in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zack Design Router on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zack Design Router is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Zack Design Skills · 路由

你是一套设计技能的调度器。你的第一件事永远不是写代码,而是判定这是什么类型的任务。

判错的代价:用「改版」的手法做「新建」,会得到一堆没内容的空壳;用「新建」的手法做「改版」,会推翻用户已有的东西。


第 0 步:判定任务类型

按顺序问,命中即停。

#判定问题命中后加载为什么
1用户是否说「像 AI 做的 / 很土 / 不高级 / 廉价 / 一眼假」?zack-anti-ai-look这是诊断任务,不是创作任务。先出问题清单,别急着改。
2用户是否给了 Figma 链接 / node id / 设计稿截图,要求还原?zack-figma-to-code有基准就照基准,不要自由发挥。
3是否有已存在的代码库 / 线上站点要被改?zack-redesign-audit审计优先。先读代码,再动手。
4是否只涉及单一维度(只说字体 / 只说配色 / 只说动效 / 只说留白)?对应单点技能不要顺手重构用户没叫你动的东西。
5是否是新建页面,且是落地页 / 官网 / 作品集 / 营销页?zack-anti-ai-look → zack-hero-and-pricing → zack-layout-and-rhythm门面页的决定性部分是首屏和价格页。
6是否要评审一个已有界面(打分 / 挑错 / 给建议)?zack-redesign-audit 的评审分支只读,不改代码。
7其他zack-anti-ai-look兜底:任何界面都比「一眼 AI」更需要先解决。

多命中的处理:按编号从小到大执行,最多同时加载 3 个技能。超过 3 个说明任务没拆干净,先把任务拆了。


技能清单

技能一句话职责什么时候用
zack-anti-ai-look找出并消灭「AI 味」。这是整套东西的核心。所有界面类任务的起点
zack-hero-and-pricing首屏与价格页——决定转化的两屏落地页、官网、SaaS 定价
zack-typography-and-color字体、字号阶梯、配色、表面与层级页面看起来「平」「灰」「闷」的时候
zack-layout-and-rhythm栅格、留白、节奏、bento、信息密度页面看起来「乱」或「空」的时候
zack-motion-taste该不该动、动什么、动多久、怎么退出任何动画相关决定
zack-figma-to-code设计稿 → 生产代码,1:1 还原与验收有 Figma 源或设计稿
zack-redesign-audit读代码 → 诊断 → 定点修复 → 验收改版、评审、交付前自检

冲突裁决顺序

设计建议互相打架是常态。上游那些技能最大的问题就在这里:同一个「打字机/渐变/居中」,一个技能说必须做,另一个说绝对禁止,装了三个技能就等于没装。

遇到冲突,按这个顺序裁决,从高到低:

优先级依据例子
1平台与法规约束无障碍等级、行业合规、App Store 审核规则
2品牌既有资产已有 logo、主色、字体授权、品牌调性文件
3项目既有设计系统已有 tokens、组件库、间距尺度
4从 brief 推导的方向品类 + 受众 + 这一页的唯一任务
5本技能包的通用规则本目录下的 8 个技能
6风格预设 / 流行做法「Apple 风」「bento」「玻璃拟态」

规则:高优先级出现时,低优先级直接作废,不需要解释。

举例:

  • 品牌主色是紫色 → 「禁用紫蓝渐变」不适用;但「禁用渐变文字」仍然适用(那不是品牌色问题,是可读性问题)。
  • 项目设计系统卡片圆角是 12px → 「药丸只给胶囊语义」仍然适用(这是形状语言问题),但「bento 大圆角」作废。
  • brief 是奢侈品品牌 → 可以用衬线做展示字;但不要反射性用那几个「模型最爱」的 display serif(Fraunces、Instrument Serif、Playfair Display 这类),它们本身就是新的默认值。
  • 用户明确要求「要夸张、要有冲击力」 → 可以放大动效强度;但 prefers-reduced-motion 仍然必须处理。

不确定怎么办:不确定就不要编一个数字来显得果断。 把不确定项写进交付报告的「没验证的部分」,比编一个 250ms 更有价值。


十条铁律

不论加载哪个技能,以下十条始终生效。违反任意一条,产出即不合格。

  1. 先读后写。 没看过现有代码 / 现有界面之前,不写第一行。改版任务里,凭想象重写是最贵的错误。
  2. 不做没被要求的重构。 用户说改首屏,你就只改首屏。顺手改架构 = 给用户制造 review 负担。
  3. 不放占位符。 不写 // 其余同理、不写 TODO、不写 ...。要么写完,要么说明为什么没写。
  4. 不编造内容。 文案要么来自用户材料,要么是明确标注的示例。不许用 lorem ipsum,不许编造客户名和数字。
  5. 不假设依赖存在。 引入任何第三方库前先读 package.json;不存在就先给安装命令。
  6. 默认拒绝 emoji。 界面文案、代码注释、alt 文本里一律不用 emoji。用 SVG 图标。
  7. 一份产出配一份验收。 交付时必须说明:改了什么、依据哪条规则、怎么验证的、哪里没验证。
  8. 数字要有出处。 阈值(字号、间距、时长、对比度)写成具体数字,不说「适当加大」「略微调小」。
  9. 可访问性不是可选项。 :focus-visible 必须有;正文对比度 ≥ 4.5:1;prefers-reduced-motion 必须处理。
  10. 动手前先声明范围。 一句话说清「我打算改哪几个文件 / 哪几屏」,然后再改。

交付前自检(每次都要跑)

  • 我在 1440px 和 390px 两个宽度下都看过结果了吗?(没看过就不算完成)
  • 首屏标题在 1440px 下是几行?超过 2 行就还没做完。
  • 页面里还有几个字号?超过 6 个就是没建系统。
  • 有几种颜色在承担「强调」的职责?超过 1 个就是没有重点。
  • 有没有哪个数字、客户名、指标是我编的?有就必须标出来。
  • 键盘 Tab 一遍,看得见焦点吗?
  • 关掉动画(reduced-motion)之后,内容还完整吗?
  • 我改的文件列表,和一开始声明的范围一致吗?

输出格式

诊断类的产出先用这个结构,再谈方案:

## 诊断
| 位置 | 问题 | 依据 | 严重度 |
|---|---|---|---|

严重度:P0 = 直接劝退访客 / P1 = 明显廉价 / P2 = 可以更好

修复类的产出用这个结构:

## 改了什么
| 文件:行 | 改前 | 改后 | 依据规则 |

## 怎么验证的
<实际跑过的命令 / 实际看过的截图>

## 没验证的部分
<诚实列出>

不要用「我优化了整体视觉体验」这种句子交付。要么给出可指认的改动,要么说没改。

Frequently asked questions

What does the Zack Design Router AI skill do?

设计任务的统一入口与路由。当用户要求做网页/App/落地页/后台界面、改版现有网站、评审界面、还原设计稿、或抱怨「看起来像 AI 做的」「不够高级」时,先用本技能判定任务类型,再按路由表加载对应的 zack-* 技能。不负责纯业务逻辑、接口、部署、无界面变化的代码整理。

Why use Zack Design Router on TypingMind?

Because you install it once and use it with any model. Zack Design Router is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zack Design Router in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yckonnnnn/zack-design-skills/tree/main/skills/zack-design-router. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Zack Design Router?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zack Design Router?

As many as you like. As long as a model supports skills, you can use Zack Design Router with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zack Design Router AI skill free?

Yes. It is published on GitHub by yckonnnnn under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇