Quiet Paper Specimen logo

Quiet Paper Specimen

Community
FANzR-arch
quiet-paper-specimen

把主题、句子、物件、情绪或文章摘要编译成「安静纸面标本」封面提示词:大留白陈纸背景、单一可想象的主体(十大意象家族任选)、中文手写大标题、一个落在主体上的高饱和色点、复印/网点/铅笔/凸版/扫描纸质感。用户提到纸面标本、留白封面、陈纸封面、单物件封面、手写标题封面、极简纸感海报、安静编辑设计、quiet paper specimen,或要把随笔、情绪、记忆向主题做成安静留白封面时使用。先内部选模块,再输出一条确定性提示词,不展示模块菜单。不用于满版商业海报、信息密集封面或其他设计流派。

Overview

PublisherFANzR-arch
RepositoryPhil-design-skills
Skill namequiet-paper-specimen
Stars
106
Forks
6
Bundled files
3
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.

  • 3 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 Quiet Paper Specimen 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/quiet-paper-specimen
  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/quiet-paper-specimen .claude/skills/quiet-paper-specimen
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Quiet Paper Specimen 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 Quiet Paper Specimen 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 Quiet Paper Specimen 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.

Quiet Paper Specimen(安静纸面标本)

把主题、句子、物件、情绪或文章摘要,编译成一条可直接交给图像模型的「安静纸面标本」封面提示词。

风格钉子:一件被单独摊在陈纸上的标本——大面积留白、单一可想象的主体、克制排版、一个高饱和色点、印刷/扫描纸质感。

核心原则:风格锁死,方案放开;默认输出已决策的成品 prompt;用户要模板时,输出中文可改字段在前、英文固定风格在后的复制即用结构。

留白是主角,不是背景。这个 skill 的全部张力来自「空」和「一个安静的点」之间的关系,任何把画面填满、加多主体、加多颜色、加大段文字的冲动都要压住。

Read

按任务读取:

  • 生成提示词:读 references/compile-contract.md 和 references/module-library.md。
  • 用户要示例或主题灵感:读 references/examples.md(如存在)。

Input

优先从用户输入推断,不要求填表:

  1. 输入模式:文字主题、一句话、一个物件、一种情绪、文章摘要,或对现有图的风格评价。
  2. 核心意象:必须落到一个可想象的主体或小视觉簇,从 module-library.md 的核心意象库里选,主体占画面 12-25%、能在缩略图尺寸看清。抽象概念要先转译成库里的具体物件(一只豁口搪瓷杯、一枚被拉直的回形针、一片蝉蜕,而不是「成长」「连接」)。不要反复用叶子、旧照片、硬币、纸船这几样——那只是意象库的一角。
  3. 文字:主标题默认中文手写大字(笔刷/钢笔/铅笔手写,字高约画面高 10-18%,缩略图可读),另可加一行存档式微文本或小副标题。用户指定中文时必须保留原中文,不默认改成英文;次要文字保持安静稀疏,但主标题必须清楚——糊进纸里的标题算缺陷。
  4. 画幅:默认 3:5 竖版(纸页天然竖向)。用户指定其他比例时优先遵循;横板、方版也允许,但仍保持大留白逻辑。

Workflow

  1. 识别输入:判断是文字生成、单物件、情绪向、文章封面,还是风格评价。
  2. 提取一个核心意象:从用户内容里只抽一个可视化想法,去核心意象库里挑对应物件。宁可安静,也不要塞多个元素;但安静不等于看不见。
  3. 选择模块:从 module-library.md 选择布局、锚点、标题、排版、纹理、色点和情绪。多张图时每张的核心意象必须来自不同家族,另外至少再变三类模块。
  4. 编译提示词:按 compile-contract.md 输出。默认输出已决策的英文美术指导,不留下 {}、斜杠菜单、either/or 布局、未决选项。用户明确要求「复制即用模板 / reusable template / 文章提示词结构」时,输出中文输入字段在前、英文风格锚定在后的模板。
  5. 输出:已选模块 + 一条完整提示词 + 一句选型理由。用户只要 prompt 时,可以省略解释,只保留模块摘要和完整提示词。

Routing Rules

  • 一句话 / 一个词:优先极简标本式布局,主体单一、留白到位,排版只留一行贴边微文本;主体仍要看得清。
  • 情绪 / 记忆 / 随笔向:优先褪色照片、半透明几何、纹理窗口这类柔软锚点,色点偏低饱和暖调,纹理偏复印柔和或扫描陈纸。
  • 文章封面:默认给中文手写大标题;可再加一行小副标题(存档微文本或短句贴边),副标必须明显小于主标题,不做信息密集封面。
  • 具体物件:保留物件轮廓和最可识别的一两个细节,简化成安静的手绘/印刷标本,不做商品广告冲击力。
  • 上传图重绘:保留原主体身份和轮廓,退成陈纸上的单一标本,去掉原图的场景、光效和背景杂物。

Output Format

默认成品 prompt:

markdown
## 已选模块
- 输入模式:
- 核心意象(家族):
- 布局模块:
- 锚点模块:
- 标题模块:
- 排版模块:
- 纹理模块:
- 色点模块:
- 情绪模块:

## 完整提示词
```text
...
```

## 选型理由
...

复制即用模板:

markdown
```text
文章主题或摘要:
{输入文章主题、标题、摘要,或直接粘贴文章内容}

用途和比例:
{例如:文章封面,竖版 3:5}

指定主标题或微文本:
{可选;没有就写:自动判断}

指定副标题文字:
{可选;没有就写:自动判断或不加}

特殊要求:
{指定核心意象、色点颜色、不能出现的元素;没有就写:无}

Create a quiet paper-specimen editorial cover from the theme above.

Style lock:
...
```

模板里不要加入「你只需要改这里」「以下内容不用改」之类说明行。字段本身已经足够清楚。

Quality Gates

  • 必须是安静的纸面标本 / 独立杂志编辑逻辑,不是满版海报、商业广告或信息图。
  • 陈纸留白必须是画面主角:负空间占 70%-80%,主体占 12%-25%。
  • 安静不等于看不见:主体、色点、标题三样都必须在缩略图尺寸下认得出。糊进纸里的主体或标题算缺陷,不算高级。
  • 必须只有一个可想象的核心意象或小视觉簇,不堆多主体;意象要从核心意象库里选,不要总落回叶子/旧照片/硬币/纸船。
  • 必须只有一个高饱和色点,占画布约 1.5%-2.5%,且落在主体身上而不是飘在空纸上;其余画面是纸色、墨色和低饱和灰调。
  • 主标题默认中文手写大字:用户原文、字高约画面高 10%-18%、笔触有真实手写不规则感;不用电脑手写体字库,不做粗黑印刷标题霸屏。
  • 次要文字保持稀疏安静:碎片字母、贴边微文本、存档标签、幽灵文字最多一两处。幽灵化和碎片化只对次要文字用,绝不用在主标题上。
  • 用户要求中文时必须使用用户指定原文;避免假中文、乱码字、随机标签。
  • 副标题只能一行,明显小于主标题;中文建议 6-12 字,英文 2-6 词。
  • 纹理必须像真实印刷/扫描材料:复印、网点、丝网晕散、胶片颗粒、凸版压痕、陈纸斑驳、铅笔灰;不是后期脏滤镜或数字做旧。
  • 成组输出时每张的核心意象必须来自不同家族,另外至少再有三项模块明显不同。五张全是纸片和植物标本,即使布局不同也算失败。
  • 禁止:满版场景、商业海报冲击力、3D/霓虹/卡通/渐变、多物体、多颜色、大段正文、现代 UI 干净矢量感、影棚打光、写实产品渲染。
  • 不编造已经生成的图片结果;本 skill 只产出提示词或风格评价。

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 Quiet Paper Specimen AI skill do?

把主题、句子、物件、情绪或文章摘要编译成「安静纸面标本」封面提示词:大留白陈纸背景、单一可想象的主体(十大意象家族任选)、中文手写大标题、一个落在主体上的高饱和色点、复印/网点/铅笔/凸版/扫描纸质感。用户提到纸面标本、留白封面、陈纸封面、单物件封面、手写标题封面、极简纸感海报、安静编辑设计、quiet paper specimen,或要把随笔、情绪、记忆向主题做成安静留白封面时使用。先内部选模块,再输出一条确定性提示词,不展示模块菜单。不用于满版商业海报、信息密集封面或其他设计流派。

Why use Quiet Paper Specimen on TypingMind?

Because you install it once and use it with any model. Quiet Paper Specimen 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 Quiet Paper Specimen in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FANzR-arch/Phil-design-skills/tree/main/quiet-paper-specimen. 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 Quiet Paper Specimen?

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 Quiet Paper Specimen?

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

Is the Quiet Paper Specimen 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 👇