Hand Drawn Chapter Slides logo

Hand Drawn Chapter Slides

Organization
studio-yebisu
hand-drawn-chapter-slides

Generate elegant chapter divider / section separator slides in PowerPoint (.pptx) featuring hand-drawn doodle-style illustrations with thick black outlines on muted colored backgrounds. ALWAYS use this skill when the user mentions any of: 类手绘风格PPT, 手绘风格ppt, 手绘插画PPT, 涂鸦风格幻灯片, 手绘章节页, 分隔页, hand-drawn slides, doodle-style slides, sketch-style chapter pages, illustrated dividers, section separators, minimalist illustrated slides, chapter title cards, or any request combining "手绘/hand-drawn/doodle/sketch" with "PPT/slides/幻灯片/演示文稿". Also trigger when user wants slides with thick black line illustrations on colored backgrounds, pen-and-ink style slide art, whimsical chapter pages, or any request that references a similar style to what was previously generated. Even if the user simply says "再生成几页那种风格的PPT" or "make more slides like those", use this skill.

Overview

Publisherstudio-yebisu
Repositoryyaoyorozu-ai-toolbox-slides
Skill namehand-drawn-chapter-slides
Stars
10
Forks
2
Bundled files
1
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 studio-yebisu on GitHub. Read the source before you install it.

Installation

Install the Hand Drawn Chapter Slides 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/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/hand-drawn-showcase/upstream/hand-drawn-chapter-slides
  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/studio-yebisu/yaoyorozu-ai-toolbox-slides.git /tmp/yaoyorozu-ai-toolbox-slides
mkdir -p .claude/skills
cp -r /tmp/yaoyorozu-ai-toolbox-slides/examples/repositories/hand-drawn-showcase/upstream/hand-drawn-chapter-slides .claude/skills/hand-drawn-chapter-slides
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hand Drawn Chapter Slides 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 Hand Drawn Chapter Slides 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 Hand Drawn Chapter Slides 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.

Hand-Drawn Chapter Slides

Create sophisticated chapter divider slides with minimalist serif typography and hand-drawn doodle-style illustrations. Each slide features a full-bleed muted color background, a chapter label + large serif title in the lower-left, a page number in the bottom-right, and a symbolic hand-drawn illustration in the center-right area.

Design System

Canvas Size

Standard widescreen: 13.333" x 7.5" (12192000 x 6858000 EMU). When using pptxgenjs, set a custom layout:

js
pres.defineLayout({ name: "CUSTOM_16x9", width: 13.333, height: 7.5 });

Color Palette

Use sophisticated, muted, desaturated colors. Never use bright or saturated tones. Each slide gets a unique background color. Generate a cohesive palette before starting.

Example palette (15 colors): #D97756 Terracotta, #788B5D Sage Green, #C46685 Mauve Rose, #9B8AC6 Lavender, #6A9BCC Sky Blue, #BBD1C9 Mint, #E2DACC Warm Beige, #D4A0A0 Dusty Rose, #7B9EB2 Steel Blue, #C9A96E Warm Ochre, #5D9B8F Muted Teal, #A88DB5 Soft Plum, #8E9EAB Slate Gray, #B8C4A0 Warm Sage, #DEB89C Soft Peach

Additional palette: #8B7D6B Warm Brown-Grey, #7A9E7E Forest Sage, #9B8EC4 Soft Purple, #C4866E Clay, #6B8FA3 Steel Blue, #7EA388 Forest Green, #B07BAC Muted Purple, #C4956A Warm Clay, #9B9E78 Muted Olive

Typography — EXACT specifications

ElementFontSizeColorPosition (inches)Size (inches)
Chapter labelCalibri14pt#141413x=1.0, y=5.0w=4.0, h=0.3
Chapter titleGeorgia40pt#141413x=1.0, y=5.3w=9.0, h=1.0
Page numberCalibri14pt#141413x=12.3, y=7.0w=0.5, h=0.25

Important: Chapter label uses Calibri (sans-serif), NOT Georgia. Title uses Georgia (serif), regular weight (NOT bold).

Illustration Style

All illustrations follow this exact aesthetic:

  • Stroke: Thick black outlines, ~5-7px in SVG (stroke color #141413)
  • Fill: Flat off-white #FAF8F2 — NO gradients, NO shadows, NO textures
  • Curves: Slightly irregular, organic (hand-drawn feel)
  • Content: Symbolic, simplified, iconic — not realistic
  • Aesthetic: Casual pen-and-ink doodle — like whiteboard sketches
  • Placement: Center-right area of the slide (x≈5.0", y≈0.4", w≈8.0", h≈5.5")

NEVER use: pure black #000000, pure white #FFFFFF, shadows, gradients, 3D effects, realistic illustrations, emoji, or Unicode symbols.

Workflow

Step 1: Gather Requirements

Ask the user for:

  • Number of slides needed
  • Chapter titles/topics for each slide
  • Whether cover slides are needed (no chapter number, larger title)
  • Starting page/chapter number (default: 1)

Step 2: Generate Color Palette

Pick N muted colors from the palettes above or generate new ones. Ensure:

  • No two adjacent slides have similar colors
  • Mix warm and cool tones
  • All colors are desaturated/muted

Step 3: Choose Illustrations

For each chapter topic, pick a symbolic illustration. Read the illustration library in scripts/illustrations.md for a catalog of ready-to-use SVG illustrations.

Common topic → illustration mappings:

  • Fundamentals / Basics → Open book
  • Planning / Design → Ruler
  • Testing / Iteration → Ascending stairs
  • Search / Discovery → Magnifying glass
  • Communication / Feedback → Speech bubbles
  • Cost / Finance → Coin stack
  • Launch / Deployment → Rocket
  • Collaboration / Team → Two people figures
  • Security / Safety → Lock or shield
  • Ideas / Creativity → Lightbulb
  • Data / Analytics → Bar chart
  • Connections / Network → Connected nodes
  • Problem-solving → Puzzle piece
  • Innovation → Gears
  • Time / Context → Hourglass
  • Navigation → Compass

Step 4: Generate Slides with pptxgenjs

Install dependencies:

bash
npm install pptxgenjs sharp  # in current working directory

Use this pattern for each slide:

javascript
const pptxgen = require("pptxgenjs");
const sharp = require("sharp");

async function svgToBase64Png(svgString, width, height) {
  const pngBuffer = await sharp(Buffer.from(svgString))
    .resize(width, height, { fit: 'contain', background: { r: 0, g: 0, b: 0, alpha: 0 } })
    .png()
    .toBuffer();
  return "image/png;base64," + pngBuffer.toString("base64");
}

const pres = new pptxgen();
pres.defineLayout({ name: "CUSTOM_16x9", width: 13.333, height: 7.5 });
pres.layout = "CUSTOM_16x9";

// For each slide:
const slide = pres.addSlide();
slide.background = { color: "HEX_WITHOUT_HASH" };

// Illustration (SVG → PNG → base64)
const svgStr = buildSvg(topic); // see illustrations.md
const imgData = await svgToBase64Png(svgStr, 900, 750);
slide.addImage({ data: imgData, x: 5.0, y: 0.4, w: 8.0, h: 5.5 });

// Chapter label
slide.addText("Chapter N", {
  x: 1.0, y: 5.0, w: 4.0, h: 0.3,
  fontSize: 14, fontFace: "Calibri", color: "141413",
  bold: false, margin: 0, valign: "bottom"
});

// Title
slide.addText("Title text", {
  x: 1.0, y: 5.3, w: 9.0, h: 1.0,
  fontSize: 40, fontFace: "Georgia", color: "141413",
  bold: false, margin: 0, valign: "top"
});

// Page number
slide.addText("1", {
  x: 12.3, y: 7.0, w: 0.5, h: 0.25,
  fontSize: 14, fontFace: "Calibri", color: "141413",
  align: "right", margin: 0, valign: "bottom"
});

Step 5: Cover Slide Variation (optional)

The first slide (cover) uses a different layout:

  • Larger title (54pt+ Georgia) in the upper-left area
  • No "Chapter N" label
  • No full illustration — just a small decorative sparkle mark

Step 6: QA

Convert to images and visually inspect:

bash
python <pptx-skill-path>/scripts/office/soffice.py --headless --convert-to pdf output.pptx
pdftoppm -jpeg -r 150 output.pdf slide

Check: text not cut off, illustration properly positioned, colors match, no overlaps.

SVG Illustration Template

All illustrations share this structure — a 600x500 viewBox, off-white fill, thick black strokes, organic curves:

svg
<svg xmlns="http://www.w3.org/2000/svg" width="600" height="500" viewBox="0 0 600 500">
  <!-- Main shape with thick outline -->
  <path d="..." fill="#FAF8F2" stroke="#141413" stroke-width="6" stroke-linejoin="round"/>
  <!-- Interior detail lines -->
  <path d="..." fill="none" stroke="#141413" stroke-width="3" stroke-linecap="round"/>
</svg>

When creating new illustrations, follow these rules:

  1. Use Q (quadratic) or C (cubic) Bezier curves for organic, hand-drawn feel
  2. Avoid perfectly straight lines or geometric perfection
  3. Keep it simple: 2-5 main shapes per illustration
  4. Fill color is always #FAF8F2, stroke is always #141413
  5. Main outlines: stroke-width 5-7; detail lines: stroke-width 2.5-3.5

See scripts/illustrations.md for the full illustration library with copy-paste SVGs.

Quality Checklist

Before finishing, verify each slide:

  • Background is full-bleed solid muted color
  • Text color is #141413 (not pure black)
  • Illustration fill is #FAF8F2 (not pure white)
  • Chapter label is Calibri 14pt (NOT Georgia)
  • Title is Georgia 40pt regular (NOT bold)
  • Page number is Calibri 14pt right-aligned
  • Canvas is 13.333" x 7.5"
  • No overlap between text and illustration
  • Page/chapter numbers are sequential and correct

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 Hand Drawn Chapter Slides AI skill do?

Generate elegant chapter divider / section separator slides in PowerPoint (.pptx) featuring hand-drawn doodle-style illustrations with thick black outlines on muted colored backgrounds. ALWAYS use this skill when the user mentions any of: 类手绘风格PPT, 手绘风格ppt, 手绘插画PPT, 涂鸦风格幻灯片, 手绘章节页, 分隔页, hand-drawn slides, doodle-style slides, sketch-style chapter pages, illustrated dividers, section separators, minimalist illustrated slides, chapter title cards, or any request combining "手绘/hand-drawn/doodle/sketch" with "PPT/slides/幻灯片/演示文稿". Also trigger when user wants slides with thick black line illust...

Why use Hand Drawn Chapter Slides on TypingMind?

Because you install it once and use it with any model. Hand Drawn Chapter Slides 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 Hand Drawn Chapter Slides in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/hand-drawn-showcase/upstream/hand-drawn-chapter-slides. 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 Hand Drawn Chapter Slides?

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 Hand Drawn Chapter Slides?

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

Is the Hand Drawn Chapter Slides AI skill free?

It is published on GitHub by studio-yebisu. 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 👇