Duotone Press Collage logo

Duotone Press Collage

Community
FANzR-arch
duotone-press-collage

把文章主题、判断句或工作流小节编译成「双色套印拼贴」提示词——纯色平涂底上,实物被处理成粗网点双色套印剪影、带白色刀切描边贴上去,画面里必须有一件可见的连接物把关系画出来,角上配裁切线、套版十字线和色条,右下挂一个黑底白字的中文标签块。用户提到套印拼贴、双色套印、印厂拼贴、网点剪贴、撕纸拼贴封面、复古印刷拼贴、letterpress collage、duotone halftone collage,或要给一篇文章做「一张封面 + 若干章节配图」的成套配图时使用。先定连接物再选器物和色寄存器,然后编译单条确定性提示词。不用于写实摄影、3D 渲染、扁平矢量插画或纯字体海报。

Overview

PublisherFANzR-arch
RepositoryPhil-design-skills
Skill nameduotone-press-collage
Stars
106
Forks
6
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

    Published by FANzR-arch on GitHub. Read the source before you install it.

Installation

Install the Duotone Press Collage 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/FANzR-arch/Phil-design-skills/tree/main/duotone-press-collage
  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/FANzR-arch/Phil-design-skills.git /tmp/Phil-design-skills
mkdir -p .claude/skills
cp -r /tmp/Phil-design-skills/duotone-press-collage .claude/skills/duotone-press-collage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Duotone Press Collage 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 Duotone Press Collage 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 Duotone Press Collage 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.

Duotone Press Collage(双色套印拼贴)

把一个主题编译成一条可直接生图的提示词。媒介锁死、器物和配色可换:纯色平涂底上贴一组粗网点双色套印的实物剪影,每件带白色刀切描边,一件可见的连接物把它们串成一句话。

核心原则:网点只长在剪贴物上。 平涂色场必须绝对干净——这是这套风格既有印刷质感又不脏的唯一原因,也是最常见的失手。模型的默认行为是把全画面统一成一种质感,不显式排除就一定会长满。

第二原则:关系要画出来。 并置不等于关系,观众不会自己推断。每张图必须有一件可见的连接物——绳、线、纸带、杠杆、落下的东西、颜色的断点。没有连接物的画面是素材摆拍,不是论点。

画幅

交付物比例sizequality
文章封面横幅5:23200×1280high
章节配图16:92560×1440high

quality 一律 high。网点密度、套印偏移、器物上的小字都吃分辨率,medium 以下网点糊成灰块、刻度和命令行烂掉。

方图不可用——这套风格靠横向的物件调度和层压叙事,压成方图会挤死。

风格 DNA(八项,换任何主题不变)

  1. 双色套印半调:每件实物是照片翻成粗网点,黑版 + 一个专色版,专色相对黑版偏移 1–2px,全尺寸下错位清晰可见。这是本风格的定义特征。
  2. 白色刀切描边:每件剪贴物外围一圈 3px 白色贴纸描边 + 一道极浅硬投影。描边只跟剪贴物,不跟平涂色块、不跟背景纸片以外的东西。
  3. 锐边不被纹理侵蚀,且锐点必须逐个点名——尖端、边角、硬转折写进 Key details,不点名会被整体质感抹平。
  4. 网点作用域只有剪贴物与纸片。平涂色场无网点。纸纤维覆盖全画面,这是唯一的全域纹理。
  5. 五角色色板,一色一职:ground(平涂底)、纸质中性(pulp off-white / kraft)、单一专色(只给连接物和第二色版)、器物金属色(brass ochre 或 steel grey)、黑(几何装饰 + 文字块)。
  6. 印刷生产装饰语汇:裁切角线、套版十字线、六格色条、胶带、订书钉。每张只取 2–3 件,全上就变素材墙。
  7. 标签块规格固定:黑色实心矩形 + 左缘一条专色竖条 + 右上角切角 + 白色重量级中文,2–4 字。
  8. 器物限定在工坊 / 度量 / 检验家族:印刷器具、量具、仪器、票据、纸品、老式机械。跨出这个家族(复古家电、机器人、地球仪、盆栽)风格立刻塌成通用复古素材。

第 4 条最容易丢,第 8 条其次。

质感四维(一维一答,不留空)

维度本风格取值
形体简化度不简化。保留照片轮廓,靠网点降信息量。不是几何化、不是 low-poly
边缘处理刀切锐边 + 3px 白描边 + 浅硬投影。边缘绝不被纹理侵蚀
纹理性质粗网点双色套印(网点肉眼可见 + 版间偏移)+ 纸纤维
纹理作用域网点只在剪贴物与纸片;纸纤维全域;平涂色场无网点

四维互相联动。修质感必须整段重写,不逐词打补丁。

Read

  • 编译提示词:读 references/compile-contract.md(铁律 + 锁死基座全文 + 成品骨架 + 迭代纪律)。
  • 选色寄存器 / 器物 / 连接物 / 装饰:读 references/module-library.md。
  • 要成品参考、或看成组产出怎么排:读 references/examples.md(两套完整实例,含首图实测记录)。

Input

从用户输入推断,不要求填表:

  1. 主题:决定器物、连接物和文字。
  2. 这一节的判断:一句话说清这张图要成立的是什么主张——决定连接物怎么选。用户没给就从上下文提。
  3. 标签文字:2–4 字中文,用户原文照抄,不润色。
  4. 色寄存器:用户没指定就按主题气质选;成组产出时逐张换,不重复。

Workflow

  1. 先写这一节的判断(一句话)。跳过这步会得到一堆好看但不说话的复古器物。
  2. 选连接物——绳 / 线 / 纸带 / 杠杆 / 落下的东西 / 颜色断点 / 物理反常。连接物决定构图骨架。
  3. 选器物:一个有内部结构的主物件 + 一到两个配角。主物件必须能被叫出名字。
  4. 选色寄存器 + 专色。成组时先把整组抽取结果列成表,确认背景色和专色都不重复再编译。
  5. 点名锐点:这张图里哪几处必须保持锐利,逐个写进 Key details。
  6. 量测占比:主体横向占宽、上下缘落在画面高度百分之几、旋转角度,写进 Composition。不靠印象估。
  7. 编译:按 compile-contract.md 的七段骨架输出,基座逐字带全,无占位符、无菜单、正文零中文(渲染文字除外)。
  8. 过 Quality Gates。

成组产出时:Key details / Constraints 两段基座必须逐字写进每一条提示词——模型只看得见单条,共享规则不会自动继承。只有 Scene 的色彩变量、Subject 的器物和情节、Composition 的占比、Text 变。

Quality Gates

出图后逐条核:

  • 背景无网点。平涂色场上出现任何点、颗粒、纹理即失败,这是第一失败点。
  • 套印偏移可见。全尺寸下看得到黑版与专色版的错位;看不到就是这一维没生效。
  • 描边归属。白色刀切边只在剪贴物轮廓上,没有爬到平涂色块或背景上。
  • 锐点还在。点名过的尖端、边角、刻度线没有被网点糊掉。
  • 连接物成立。能一眼看出谁连着谁、朝哪个方向。看不出就是这张图没说话。
  • 专色归位。专色只在连接物和第二色版上,没有跑到背景或器物金属上。
  • 标签块规格:黑矩形 + 专色左竖条 + 右上切角 + 白字,四项齐。
  • 文字逐字对。命令行、URL、数字、刻度必须逐字符核,错一个即重出。
  • 器物没有回滑:没有出现复古家电、机器人、地球仪、洒水壶这类通用复古素材。
  • 本 skill 只产出提示词,不编造已生成的图片结果。

状态与已知风险

首图已实测(2026-08-01,5:2 封面「一眼就假」,成图见 assets/preview.png)。

首图验证成立:平涂底全程干净无网点、双色套印偏移清晰、白色刀切描边只跟剪贴物、放大镜下的粗网点与全图网点形成两档密度差、四角裁切线与底部色条到位、中文标题与副标题全部逐字渲染正确。

首图暴露一点,已回写:「放大镜下网点更粗」这类局部密度差要显式写成"比全图粗几倍",只写 magnified 会得到一个普通放大效果,看不出机械感。

风险状态 / 怎么修
背景长满网点高危。Constraints 基座已封堵。仍犯则把 flat colour field carries no dots 提到 Key details 段首
套印偏移糊掉整张双色是新增维度,出图糊了先只删这一维再看,不要整段重写质感
同形状复制多份退化成纹理堆积类主体(一堆铅字、一沓票据)必须点名保住每一件的轮廓线。仍糊则减数量,不加修饰
器物滑回通用复古素材Constraints 基座按名封堵。成组时把上一版用过的器物也追加进封堵清单
中文标签块字形首图已验证 5:2 封面标题与标签正常。16:9 章节图的小字标签块未单独验证
长命令 / URL 印错必须逐字符核。连续失败就缩短到最短可辨识片段,不要拆字形描述
成组撞脸背景色、专色、连接物三张表每张重抽,不重复

Guardrails

  • 风格用视觉特征描述,不指名艺术家。
  • 器物是泛型物件,不复刻真实品牌标识;确需真 logo 的场合走 gpt-image-prompt-spec 的全量还原路径(点名品牌与版本,不拆字形、不留白后期合成)。
  • 出图偏差先怀疑 Subject 槽点名不足,不要动 DNA 固定块;一轮只改一处,质感维度例外(整段同改)。
  • 效果不对时先删修饰再加修饰。修饰词过多会互相竞争。
  • 已验证有效的提示词不为了合规去改。回退到最近的已知良好版本是合法且常常最优的动作。

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 Duotone Press Collage AI skill do?

把文章主题、判断句或工作流小节编译成「双色套印拼贴」提示词——纯色平涂底上,实物被处理成粗网点双色套印剪影、带白色刀切描边贴上去,画面里必须有一件可见的连接物把关系画出来,角上配裁切线、套版十字线和色条,右下挂一个黑底白字的中文标签块。用户提到套印拼贴、双色套印、印厂拼贴、网点剪贴、撕纸拼贴封面、复古印刷拼贴、letterpress collage、duotone halftone collage,或要给一篇文章做「一张封面 + 若干章节配图」的成套配图时使用。先定连接物再选器物和色寄存器,然后编译单条确定性提示词。不用于写实摄影、3D 渲染、扁平矢量插画或纯字体海报。

Why use Duotone Press Collage on TypingMind?

Because you install it once and use it with any model. Duotone Press Collage 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 Duotone Press Collage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FANzR-arch/Phil-design-skills/tree/main/duotone-press-collage. 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 Duotone Press Collage?

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 Duotone Press Collage?

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

Is the Duotone Press Collage AI skill free?

It is published on GitHub by FANzR-arch. Check the repository for licensing terms. 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 👇