彩色图
Colorfigures

原始链接: https://april-zhu.com/colorfigures

Colorfigures 是一种技能,它教会 AI 创建日常机器与设备的单个交互式 HTML 图。用户用自然语言描述对象;AI 构建可旋转、透明的模型,并标注可动部件,例如口香糖机、唱片机、水壶和包裹柜。它在安装八个小组件后可与 Claude Code、Codex 或 Gemini CLI 一起使用;无需编程。图在浏览器本地运行,无追踪或外部请求。每个图大约需要 15–30 分钟和 200,000–400,000 个 token,主要用于建模和检查。用户可通过色板、抖动滑块或请求调整颜色。该技能采用 MIT 许可证,图可用于商业用途,安装仅复制文件,无依赖。最适合有可按压部件的机器;不适合柔软的有机主题。

Hacker News 讨论了 Colorfigures,一个 Claude 生成的“手绘”插图项目。评论者开玩笑说手和墨水都是虚拟的,争论下载并解压文件是否有风险,因为其中包含 AI 可能执行的 Python 脚本,并要求提供托管的源代码。用户指出了类似的图解工具和项目。有人报告免费版 Claude 因预算拒绝生成“仓鼠轮洗衣机”。其他人批评缺少功能细节,尤其是浓缩咖啡机蒸汽的路由方式,并建议添加暂停按钮和验证。一条讽刺评论称机器外壳本身就能引导蒸汽。总体而言,反应混杂着娱乐、技术怀疑和小众赞赏。
相关文章

原文

Turn it round. See inside.

Every figure turns all the way round: drag it. See-through shows the real machine at work inside, and Labels name each part, lighting up while it runs.

Try all 26 in the demo →

Try these prompts

Copy one, paste it into your AI, open the file it makes.

a gumball machine where I can put in a coin and turn the crank

a record player: put on a record, drop the needle and it plays

a kettle that boils and clicks off by itself — show how it knows when to stop

how does a toaster know when to pop? make it a Colorfigure

a bike pump filling a tyre, with a see-through valve

a parcel locker wall: type a code and the right door pops open

Questions

What is a skill?

A small folder of instructions and templates that teaches an AI how to do one job well. It isn't an app and doesn't run by itself; the AI reads it when you ask for something it covers.

The AI isn't using it

Restart the app (Claude Code, Codex or Gemini CLI), then mention it by name: "use the colorfigures skill to draw a gumball machine". To check it's installed, run ls ~/.claude/skills/colorfigures (or ~/.codex/skills, ~/.gemini/skills); you should see SKILL.md, README.md, LICENSE, assets and scripts.

What kinds of objects work best?

Everyday machines and devices with parts you can press: appliances, vending and arcade machines, toys, signs, kiosks. Every figure turns all the way round, and machines get a See-through switch that shows the real working parts inside, labelled and moving with the buttons. Soft, organic things (people, animals, plants) don't suit the style.

How long does a figure take, and how many tokens?

About 15 to 30 minutes and roughly 200,000 to 400,000 tokens per figure in Claude Code. Most of that goes on modelling the object from every side and building its see-through from how the real machine works; then the AI checks it from several angles, in see-through and on a phone, and fixes what it finds. On a fresh test run a parking meter with a see-through of about 20 labelled parts took around 15 minutes and 230,000 tokens; a dense machine or a scene with several objects takes longer. Changes you ask for afterwards in the same chat are much quicker. On a Claude plan this counts toward your usage; on the API it's billed per token.

Can I change the colours?

Yes. Every figure has body-colour swatches (tomato, mustard, mint, cobalt, blush) and a hand-drawn wobble slider. You can also ask the AI for a particular colour.

Is it safe to install?

It's eight small plain-text files (about 220 KB): the instructions, the drawing engine, three example figures, a build script, a readme and a licence. Installing only copies them; nothing runs, and there are no packages or dependencies. Each figure the AI makes is a single HTML file that runs in your browser like any web page, with no tracking, accounts or outside requests. Want to look first? Download the .zip and open SKILL.md in any text editor.

Can I use it for commercial work?

Yes. The skill is MIT licensed, and the figures you make with it are yours to use, including in paid and client work. For custom figures made for your product, email [email protected].

Do I need to code?

No. Describe the object in plain words. If you want changes, say so in the same chat: "make the door open further", "add a coin return".

联系我们 contact @ memedata.com