Lab Graphic Design logo

Lab Graphic Design

Community
haorantang97
lab-graphic-design

做研究驱动的视觉识别:从对象里找到一个具体事实,长出定制字形和一条主导网格规则,层级靠位置与尺度,每件只留一处可追溯的张力,跨媒介保留规则和材料逻辑。用于文化机构、展览、出版、带工艺背景的品牌的识别、海报、导视、书、网站。不用于复刻某个已有项目外观的任务。

Overview

Publisherhaorantang97
RepositoryLabArt
Skill namelab-graphic-design
Stars
292
Forks
15
Bundled files
1
LicensePolyForm-Noncommercial-1.0.0
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by haorantang97 on GitHub. Read the source before you install it.

Installation

Install the Lab Graphic Design 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/haorantang97/LabArt/tree/main/plugins/lab-graphic-design/skills/lab-graphic-design
  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/haorantang97/LabArt.git /tmp/LabArt
mkdir -p .claude/skills
cp -r /tmp/LabArt/plugins/lab-graphic-design/skills/lab-graphic-design .claude/skills/lab-graphic-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lab Graphic Design 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 Lab Graphic Design 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 Lab Graphic Design 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.

Lab 平面设计

这种风格的辨识度不在某种固定的外观:每个项目看起来都不同,相同的是下面这条路径。按六步执行,每一步都有产出和检查。

0. 立场(先读)

  • 对象优先:识别的形式从对象(机构、艺术家、物件、场所、档案)里找,不从设计师口味里来。
  • 双向:设计受对象影响,也反过来改变对象的自我认识。研究要和客户/艺术家一起做。
  • 安静,慢慢显露:第一眼不喊,第二眼有东西可看。最少的手段,最大的效果。
  • 书是物件,墙是材料:纸、布、线、压印、刻痕都是表达手段,不是"制作阶段"的事。
  • 功能兜底:怪癖和俏皮只有在东西仍然好用时才保留。

1. 立论点

做法

  1. 研究四类来源,各列 3–5 个具体事实:场所/建筑、物件/工具、材料/工艺、档案(文件、旧标签、照片、账本)。
  2. 从中选一个能指着看的事实作为种子(一条屋脊、一个扫帚柄、一根经线、一只眼睛、一种晶体)。可再选一个次要事实提供颜色或材料。
  3. 写一句话论点:"X 是 Y,所以所有元素都 Z。" Z 必须能直接推出一处字形和一条版式规则。

检查

  • 这句话里有没有一个具体名词?只有形容词(现代、开放、温暖)就退回重来。
  • 把机构名换成另一个,论点还成立吗?成立就太泛了。
  • 能不能从这句话画出一个字母?能不能推出一条网格规则?两个都要能。

2. 字体层级

层内容规则
L0定制字形:整套字、一个 logo 或只改一个字母必须从种子事实里推出;规模看预算,但至少一处
L1展示:L0 放大用于标题只用大写或只用一种形态,≤ 3 个词
L2正文与导视:一款安静的现成字一个字重为主,不用粗体;"退后但有性格"
L3第二声音(可选):古典衬线或斜体只在需要"另一个时代/另一个说话者"时出现(档案引文、历史文本)
  • 层级靠位置、尺度、透明度,不靠粗细。一件东西里除 L1 外最多两个字号。
  • 尺度反差要大(展示 : 最小字 ≥ 15 : 1)。
  • 选现成字的理由要写出来(为什么它不和 L0 抢)。

3. 网格

两层:

  • 主导规则:一条从种子事实推出的规则,例如一条线(钉板线、潮位线)、一种栏(单栏通高)、一种框架(展架的格子)。它必须能在纸、墙、屏幕上都执行,最好有一个固定比例或固定物理尺寸(如格式高度的 5/8、离地 1530 mm)。
  • 日常分栏:普通的 4–6 栏,承载日期、地址、说明。

检查:遮掉所有文字,只看元素的位置,能认出主导规则吗?能 → 合格。

4. 受控张力

可用的张力来源(每件只选一处做主导):

  • 尺度:一个巨大元素 vs 很小的文字;巨大元素被画面边缘裁掉。
  • 破格:一个元素越过主导规则(图像穿过单栏、形体超出它的区域)。
  • 异质材料:醋酸、布、glassine、压印、刻痕。
  • 意外的单色:一个来自对象的强颜色,只用在一个元素上。
  • 观看反转:图像回看观者;图底可以两读。

规则:张力来源也必须能追溯到研究(颜色来自材料,裁切来自对象的尺度),说不出来源的张力删掉。其余一切服从秩序。

5. 跨媒介测试

至少做:识别总图、海报、导视、网站首屏、书封。每种媒介:

  • 保留主导规则和 L0,不必保留同一版面。
  • 选一种与论点相关的工艺:刻、压、织、钉、喷砂、丝印。导视尽早与建筑一起规划。
  • 写下这件东西里唯一的张力来源是什么。

6. 原创性与一致性评估

逐条打分(0–2)并写理由:

检验问题
替换测试换一个机构名,这套形式还成立吗?(应该不成立)
来源测试每个形式决定能说出来自哪个研究事实吗?
规则测试遮掉文字后,五件东西能看出同一条主导规则吗?
克制测试第一眼安静吗?第二眼有细节吗?
张力测试每件是否只有一处主导张力?
功能测试导视读得清吗?网站信息找得到吗?书名认得出吗?
相似测试是否像某个已有项目或名作?(像就是失败——要的是方法,不是外观)
时间测试规则能否扩展到十年后的新展、新空间?

总分低于 12/16,回到第 1 步换种子事实,而不是改装饰。

规则

  • 每个项目至少一处定制字形,来自种子事实。
  • 颜色从材料里取,写出来源("氧化铜""烧过的黏土"),不从色轮挑。
  • 一个强调色,每件只用在一个元素上。
  • 正文不用粗体;黑色用对象里的深色代替纯黑。
  • 摄影:自然光、低饱和、材料特写;没有照片时用标明内容的占位,不用插画代替。
  • 导视是建筑的一部分:刻、压、喷砂、丝印在材料里,不是贴上去的牌子。

禁忌

  • 不复刻已有项目的字形或版面,包括研究和参考里看到的案例;只复用"取形→成字→成规则"的路径。
  • 不用 Gill Sans 一类"显而易见的英国现代主义"现成字装英国感。
  • 不做满版喧闹的海报;不堆叠多种张力。
  • 不写抽象形容词式论点;不为美观加不能追溯的元素。
  • 不让俏皮细节损害功能。

用到新项目的流程(速查)

  1. 列四类来源的事实(每类 3–5 条),选种子。
  2. 写一句话论点,画出 L0 的一个字母和主导规则的示意。
  3. 定 L2/L3 现成字,写理由;定 3–5 个来自材料的颜色,标出唯一强调色。
  4. 做识别总图 → 海报 → 导视 → 网站 → 书封,每件写出唯一张力来源和工艺。
  5. 用第 6 步的 8 条打分,低于 12 回第 1 步。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lab Graphic Design AI skill do?

做研究驱动的视觉识别:从对象里找到一个具体事实,长出定制字形和一条主导网格规则,层级靠位置与尺度,每件只留一处可追溯的张力,跨媒介保留规则和材料逻辑。用于文化机构、展览、出版、带工艺背景的品牌的识别、海报、导视、书、网站。不用于复刻某个已有项目外观的任务。

Why use Lab Graphic Design on TypingMind?

Because you install it once and use it with any model. Lab Graphic Design 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 Lab Graphic Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/haorantang97/LabArt/tree/main/plugins/lab-graphic-design/skills/lab-graphic-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lab Graphic Design?

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 Lab Graphic Design?

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

Is the Lab Graphic Design AI skill free?

Yes. It is published on GitHub by haorantang97 under the PolyForm-Noncommercial-1.0.0 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 👇