Paper Collage Ppt logo

Paper Collage Ppt

Community
Jane-xiaoer
paper-collage-ppt

「小耳 PPT 风格馆」——生成多风格横向翻页网页 PPT 与微信公众号文章。当前提供:小耳剪纸风、好奇果冻 3D、顽趣实验室 3D、小耳几何风,并提供好奇 3D 卡通公众号排版、几何风小红书卡片与公众号排版,以及可编辑 PPTX 导出。用户说“小耳剪纸风”“剪纸 PPT”“好奇 3D”“果冻 3D PPT”“顽趣实验室 3D”“怪物实验室 PPT”“角色驱动 3D 发布会”“3D 演示”“3D 卡通公众号”“几何风 PPT”“包豪斯风格 PPT”“瑞士风格排版”“色块 PPT”“几何风小红书”“选择 PPT 风格”“paper collage deck”“playful lab deck”“geo collage”时使用。

Overview

PublisherJane-xiaoer
Repositorypaper-collage-ppt
Skill namepaper-collage-ppt
Stars
68
Forks
6
Bundled files
128
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.

  • 128 bundled files

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

  • Open source

    Published by Jane-xiaoer on GitHub. Read the source before you install it.

Installation

Install the Paper Collage Ppt 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/Jane-xiaoer/paper-collage-ppt/tree/main
  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/Jane-xiaoer/paper-collage-ppt.git \
  .claude/skills/paper-collage-ppt
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paper Collage Ppt 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 Paper Collage Ppt 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 Paper Collage Ppt 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.

小耳 PPT 风格馆 · Xiaoer Deck Styles

把一份大纲或文章变成拥有完整视觉语言的网页 PPT。当前支持小耳剪纸风、好奇果冻 3D、顽趣实验室 3D 与小耳几何风;每种风格各自拥有独立模板、素材、动效和设计约束,不能只换颜色假装成另一种风格。

Step 0 · 选择风格

用户已明确风格就直接进入对应工作流;没有明确时给两个选择:

  1. 小耳剪纸风 — 温暖、手作、叙事感,入口 assets/template.html,继续按下文 Step 1–7。

  2. 好奇果冻 3D — 年轻、明亮、设计感,入口 styles/haoqi-3d/demo.html。先读 styles/haoqi-3d/README.md 与 styles/haoqi-3d/PPTX_EXPORT_PROTOCOL.md;根据用户内容决定页数,禁止照搬示例的 20 页数量。允许创建新的 Three.js 模型、文字、粒子或导入 GLTF,并按协议注册需要在 PowerPoint 中独立编辑的 3D 对象。

  3. 顽趣实验室 3D — 疯狂、角色化、商业广告感,入口 styles/playful-lab-3d/demo.html。先读该目录的 SKILL.md、design-tokens.json 与 references/;为内容分配红蓝绿人格,混合软胶、毛绒、黏土和实验室道具,保持原创并按协议导出可编辑 PPTX。

  4. 小耳几何风 — 冷静、秩序、有气场,入口 styles/geo-collage/demo.html。先读 styles/geo-collage/SKILL.md 与 references/grid-layouts.md;从 20 种网格版式里整段粘贴改文案,遵守「硬边五铁律」(零阴影零渐变零圆角 / 格子咬合 / 留白成块 / 几何族 ≤4 / 至少一处出血)。同一套色板还能出小红书 3:4 卡片与公众号排版。

用户想先看效果时,打开 style-gallery.html。新增其他风格时遵守 styles/README.md。用户要把好奇 3D 用于公众号时,读取 styles/haoqi-3d/wechat/SKILL.md,并按其引用的微信组件、配图和检查清单执行。

工作流 B:好奇果冻 3D

  1. 按受众、时长与信息量规划页数;不设固定页数,不以 20 页示例作为输出要求。
  2. 从 styles/haoqi-3d/demo.html 继承视觉系统和运行时,根据内容增删 PAGES。
  3. 自由创建主题所需的 Three.js 对象。对每个需要在 PPTX 中单独移动、缩放或删除的 THREE.Object3D 调用 registerPptx3D(object, id, { pages });组整体编辑就注册 Group,部件分开编辑就分别注册。
  4. 保持精确文案为 #txt 下的真 HTML,普通素材放入 #stk 或 #txt,不要把文字烤进 3D 图或背景。
  5. 预览并检查所有页面后,默认同时导出可编辑 PPTX:
bash
python3 scripts/export-haoqi-pptx-editable.py path/to/deck.html \
  -o path/to/deck-editable.pptx --scheme plus
  1. 验证 PPTX 页数与 HTML 运行时报告的页数完全一致;确认存在真文本框、独立图片对象和原生形状,并回渲代表页检查视觉。
  2. 同时交付 deck.html 与 deck-editable.pptx。说明 WebGL 材质与光影属于背景,注册的 3D 主体作为透明独立对象,文字与结构可继续在 PowerPoint 中编辑。

详细协议与扩展示例见 styles/haoqi-3d/PPTX_EXPORT_PROTOCOL.md。


工作流 A:小耳剪纸风

把一份大纲或文章变成「剪纸拼贴」风格的单文件网页 PPT:所有内容像剪好的纸片一张张贴在纸面上,翻页时逐格「贴」上来(定格动画手感),需要画面的页面配 nano 生成的手工纸艺插画。

血统:视觉体系来自 paper-collage-ad(剪纸广告视频 skill)的实战配方——「实拍纸艺 diorama」美学、克制调色板、暖光投影;工程骨架借鉴 guizang-ppt-skill 的单文件 HTML 路线。两条硬教训直接继承:①AI 渲染文字必乱码,精确内容一律真 HTML;②工艺正确 ≠ 好看,美感层(光/色/主次/留白)绝不能省。

何时用 / 不用

合适:分享会、课程、产品故事、手作/生活方式主题、任何想要「温暖、手工、有记忆点」的演讲;公众号文章改讲稿。 不合适:大表格/密集图表(用常规 PPT)、严肃商务汇报(风格太俏皮)、需要多人协作编辑的场合。

工作流

Step 1 · 对齐(动手前,最多 3 问)

用户给了完整大纲/文章 → 跳过直接 Step 2。只给了主题 → 最多问 3 个问题:①讲给谁听、什么场合?②时长(定页数:10 分钟≈8-10 页,20 分钟≈12-16 页)?③有没有现成素材/硬约束?其余自己做合理假设并在回复里说明。

Step 2 · 大纲与节奏

按叙事弧搭骨架:钩子 → 定调 → 主体 → 转折 → 收束(页数分配见 references/layouts.md 尾部)。同时列出每页的底色节奏(field / deep / ink),规则在 layouts.md「页面节奏规划」——无连续 3 页同底色,每 3-4 页一个深底呼吸页。大纲 + 节奏表先给用户确认再动手写 HTML。

Step 3 · 定初始主题(14 套艺术史配色,内置换肤+滑杆)

读 references/themes.md 总表,按内容气质推荐初始主题,把模板 <body class="tN"> 换成对应编号即可——14 套变量和左下角「✂ 风格」换肤面板都内置在模板里,观众/用户随时一键切换(深色主题的 dark-field 由脚本自动处理)。不接受自定义 hex、不许混搭;用户给参考图 → 按图逐要素提色加成 t15+(方法在 themes.md 开头)。

Step 4 · 拷模板 + 填布局

bash
mkdir -p "项目/XXX/ppt/images"
cp <SKILL_DIR>/assets/template.html "项目/XXX/ppt/index.html"

template.html 完整可运行,内置 7 个示例页展示全部工艺。然后:

  1. 立刻替换 <title> 等 [必填] 占位
  2. 打开 references/layouts.md,按大纲从 20 种布局骨架里挑,整段粘贴改文案——不要从零写 slide,不要发明新类名
  3. 纸片工艺(手剪轮廓/pin 包裹/剪贴字/撕边/山景/data-drop 入场)的规矩在 layouts.md 顶部「手工感五铁律」和 references/paper-craft-css.md 六条铁律,写每页时遵守
  4. 微调只改 inline style(vw/vh 单位)

Step 5 · 配插画(可选)

先拍板配色,再生成插画:排版出来后让用户用左下换肤面板实景试 14 套、定下最终主题,然后再生成插画——插画调色板是生成时烤死的,不会跟着换肤,这个顺序能保证图和版面永远同色系。之后读 references/image-prompts.md,用 nano-image-generator 按「实拍纸艺 diorama」七段配方生成。要点:封面是居中海报式不放图,插画主要落位在 L5 左文右图/幕封;先出第一张插画 reroll 到美并锁为风格锚,后续图带锚做参考;调色板跟主题联动(themes.md 底部对照表);prompt 负面块必须含 no text。没有 GEMINI key 或用户不要图 → 全 deck 纯排版也成立(模板的纸片体系不依赖插画)。

Step 6 · 自检

逐项过 references/checklist.md(P0 全过才能交)。跑一遍自检命令,并用无头 Chrome 截 2-3 页人眼看一遍美感:

bash
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --headless --disable-gpu \
  --window-size=1600,900 --virtual-time-budget=5000 \
  --screenshot=/tmp/check.png "file://$(pwd)/index.html#3"

Step 7 · 交付

open index.html 直接帮用户打开(不要给路径让用户自己找);说明操作:键盘 ←→ / 滚轮 / 触屏滑动 / 底部圆点,URL 带 #页号 可直达。

要 PPTX? 用户要 PowerPoint 文件时:

bash
python3 <SKILL_DIR>/scripts/export-pptx-editable.py deck.html --theme t15 -o 分享.pptx

三层分解导出:背景=底纹装饰截图;每张纸片=独立图片形状(可选中/拖动/拉伸,纹理跟着变);文字=真文本框(位置/字号/颜色/旋转对位)。所以在 PowerPoint/Keynote 里:改字 ✅、挪纸片 ✅、文字变长把纸片拉大 ✅——版式可以继续调。边界:换配色/加新页回 HTML 重导;纯 CSS 色块元素(轻量版少数)仍烤在背景;马克笔垫色不跟随文字。依赖 python-pptx + 本机 Chrome。

资源导览

text
paper-collage-ppt/
├── style-gallery.html            ← 多风格选择入口
├── SKILL.md                      ← 你在读
├── styles/
│   ├── README.md                 ← 新增风格规范
│   ├── haoqi-3d/                 ← 好奇果冻 3D 模板、素材与运行时
│   ├── playful-lab-3d/           ← 顽趣实验室 3D 模板、token 与参考
│   └── geo-collage/              ← 小耳几何风模板、小红书卡片、参考与脚本
├── assets/
│   └── template.html             ← 剪纸风完整可运行模板
├── scripts/
│   ├── export-pptx.py            ← HTML deck → 16:9 PPTX(逐页截图,可 --theme 指定配色)
└── references/
    ├── themes.md                 ← 14 套艺术史配色总表 + 换肤/滑杆机制 + 插画调色板联动表
    ├── layouts.md                ← 20 种布局骨架 + 节奏规划 + 手工感五铁律
    ├── paper-craft-css.md        ← 剪纸 CSS 工艺分解(v2) + 六条不许动的铁律
    ├── image-prompts.md          ← nano 纸艺 diorama 配方(PPT 版,强制 no text)
    └── checklist.md              ← P0/P1/P2 交付检查清单

加载顺序:SKILL.md → (Step 2 后) themes.md → layouts.md → 动手写页 → (要配图) image-prompts.md → checklist.md。paper-craft-css.md 在需要微调样式或加组件时查。

设计哲学

  1. 一页一件事 — 每页一个论点、一个视觉动作;贪多就拆页
  2. 文字是内容,插画是气氛 — 真 HTML 文字承载全部信息,拿掉所有插画 deck 依然成立
  3. 手工感来自不完美 — 微旋转、逐格入场、胶带纸屑;但不完美是设计出来的,五档旋转之外的随意才是真乱
  4. 克制优于堆料 — 一套调色板、留白 ≥40%、每页手工痕迹 ≤3 种
  5. 工艺正确只是及格,美感层才是分数 — 光的方向、色的克制、主次与留白,每页都要过美感自检

Bundled files

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

and 68 more files.

Frequently asked questions

What does the Paper Collage Ppt AI skill do?

「小耳 PPT 风格馆」——生成多风格横向翻页网页 PPT 与微信公众号文章。当前提供:小耳剪纸风、好奇果冻 3D、顽趣实验室 3D、小耳几何风,并提供好奇 3D 卡通公众号排版、几何风小红书卡片与公众号排版,以及可编辑 PPTX 导出。用户说“小耳剪纸风”“剪纸 PPT”“好奇 3D”“果冻 3D PPT”“顽趣实验室 3D”“怪物实验室 PPT”“角色驱动 3D 发布会”“3D 演示”“3D 卡通公众号”“几何风 PPT”“包豪斯风格 PPT”“瑞士风格排版”“色块 PPT”“几何风小红书”“选择 PPT 风格”“paper collage deck”“playful lab deck”“geo collage”时使用。

Why use Paper Collage Ppt on TypingMind?

Because you install it once and use it with any model. Paper Collage Ppt 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 Paper Collage Ppt in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jane-xiaoer/paper-collage-ppt/tree/main. 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 Paper Collage Ppt?

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 Paper Collage Ppt?

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

Is the Paper Collage Ppt AI skill free?

Yes. It is published on GitHub by Jane-xiaoer 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 👇