Textbook To Presentation Generator logo

Textbook To Presentation Generator

Community
dmccreary
textbook-to-presentation-generator

Generates a lecture PowerPoint from an intelligent textbook using pptxgenjs — visual design, 4-act storytelling structure, and speaker notes. Use when converting a textbook into slides for classroom delivery.

Overview

Publisherdmccreary
Repositoryibook-skills
Skill nametextbook-to-presentation-generator
Stars
109
Forks
21
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by dmccreary on GitHub. Read the source before you install it.

Installation

Install the Textbook To Presentation Generator 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/dmccreary/ibook-skills/tree/main/skills/archived/textbook-to-presentation-generator
  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/dmccreary/ibook-skills.git /tmp/ibook-skills
mkdir -p .claude/skills
cp -r /tmp/ibook-skills/skills/archived/textbook-to-presentation-generator .claude/skills/textbook-to-presentation-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Textbook To Presentation Generator 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 Textbook To Presentation Generator 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 Textbook To Presentation Generator 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.

Presentation Generator

Version: 1.0

Generate a lecture-ready PowerPoint presentation from an intelligent textbook project. The presentation is designed for live delivery — visual, story-driven, with progressive disclosure, audience interaction beats, and speaker notes that script the entire performance.

Core Philosophy: The Medium IS the Message

The presentation doesn't teach about communication or subject-matter frameworks. It is the framework in action. The audience should experience principles before being told about them. Every slide must answer: "Is this slide itself an example of the principle it discusses?"

This means:

  • When teaching structure, the presentation IS structured (Pyramid Principle — governing thought in minute 2, not minute 55)
  • When teaching brevity, the slide has seven words maximum
  • When teaching storytelling, the lecture IS a story (4-act arc)
  • When teaching about cognitive load, no slide overloads the audience
  • Meta-moments: The speaker reveals "what I just did was [framework name]" AFTER demonstrating it. The audience learns through experience, then gets the vocabulary.

When to Use This Skill

Use when:

  • An intelligent textbook exists (MkDocs project with chapters, course-description.md, learning graph)
  • The user wants a lecture presentation for live delivery
  • The user wants to convert textbook content into a slide deck
  • The user says "create a presentation", "make slides", "build a deck", "lecture slides"

Do NOT use when:

  • No textbook content exists yet (use course-description-analyzer and chapter generators first)
  • The user wants a document, not a presentation (use docx skill)
  • The user wants to edit an existing presentation (use the pptx editing workflow)

Prerequisites

  • Node.js installed
  • npm install pptxgenjs (install locally in the output directory)
  • An intelligent textbook project with:
    • docs/course-description.md
    • docs/chapters/ with chapter content
    • CLAUDE.md with project conventions (optional but helpful)

Workflow

Step 1: Read the Textbook

Read these files to understand the content:

  1. Course description (docs/course-description.md) — extract title, audience, key topics, learning outcomes
  2. CLAUDE.md — extract tone, style, color palette, mascot info
  3. Chapter index files — scan docs/chapters/*/index.md for chapter titles, key concepts, and the pedagogical flow
  4. Student feedback (if available in input-knowledge/) — what resonated with prior audiences
  5. Original lecture notes (if available) — the speaker's natural flow and stories

Step 2: Design the Presentation Structure

Design a 4-act structure following Klein's storytelling model applied to the lecture itself:

ActPurposeSlidesTime
I: The Wake-Up CallHook, establish stakes, live challenge6-8~10 min
II: The ToolkitCore frameworks with before/after demos10-14~20 min
III: The Power ToolsAdvanced techniques, persuasion, AI6-10~12 min
IV: The CloseAction plan, textbook link, final quote4-6~8 min

Target: 25-35 slides for a 50-60 minute lecture. At ~1.5 min/slide average. Fewer slides = more speaker time per slide = more engaging.

Present the proposed structure to the user for approval before generating.

Step 3: Design the Visual System

Extract or create a color palette from the textbook's CLAUDE.md:

javascript
const C = {
  primary: "XXXXXX",      // From CLAUDE.md palette
  primaryDark: "XXXXXX",
  primaryLight: "XXXXXX",
  accent: "XXXXXX",       // Highlight color
  white: "FFFFFF",
  offWhite: "F5F5F5",
  black: "212121",
  gray: "757575",
  red: "C62828",           // For "before" / negative examples
  green: "2E7D32",         // For "after" / positive examples
};

Typography:

  • Title font: Georgia (or serif from CLAUDE.md)
  • Body font: Calibri (or sans-serif from CLAUDE.md)
  • Title size: 32-44pt
  • Body size: 14-20pt (never below 13pt)

Layout rules:

  • No more than 7 words per line of body text
  • One idea per slide
  • Dark backgrounds (primary dark) for section dividers, title, close
  • Light backgrounds (white) for content slides
  • Accent color for emphasis bars, numbers, highlights

Step 4: Generate the Presentation

Create a Node.js script that uses pptxgenjs to generate the .pptx file. Read references/slide-patterns.md for the reusable slide pattern library.

Slide categories and their patterns:

  1. Title slide — dark bg, large title, subtitle, author, accent bar
  2. Section divider — dark bg, large text, subtitle, accent bar
  3. Big number — dark bg, one massive stat (80-120pt), context below
  4. Before/After comparison — two columns, red accent (before) vs green (after)
  5. Framework visual — shapes/diagrams illustrating a model (pyramid, stages, pillars)
  6. Evidence stack — 3 cards with accent bars showing research findings
  7. Interactive beat — light bg, challenge prompt in a card, instructions
  8. Quote — dark bg, large italic text, attribution
  9. Action items — numbered circles with titles and descriptions
  10. Resource/CTA — textbook link, QR code placeholder, stats

Step 5: Write Speaker Notes

Every slide gets detailed speaker notes. These are the real script — the slides are just visual anchors. Notes include:

  • TIMING: Cumulative minutes (e.g., "TIMING: 15:00")
  • SAY: The exact narrative to deliver (2-4 sentences, conversational)
  • META-MOMENT: Where the speaker reveals the framework AFTER demonstrating it (e.g., "Notice what I just did? That was Klein's Dilemma stage.")
  • TRANSITION: The bridge sentence to the next slide
  • AUDIENCE PULSE: When to pause, ask a question, or let silence work

Step 6: Generate and Verify

  1. Run the Node.js script to generate the .pptx
  2. Verify slide count matches the design
  3. Extract text with python -m markitdown output.pptx to confirm content
  4. Report the result to the user with slide count and timing estimate

Output

The presentation file should be saved to:

{project-root}/presentation/{kebab-case-title}.pptx

Along with the generation script:

{project-root}/presentation/generate.js

Adapting for Different Subjects

This skill works for ANY intelligent textbook, not just communication. The key adaptations:

  • Subject-specific stories: Open with a story from the textbook's domain (engineering, science, business)
  • Framework names: Use whatever frameworks the textbook teaches (not just Minto, Klein, etc.)
  • Color palette: Derive from the textbook's CLAUDE.md
  • Audience: Match the course-description.md target audience
  • Interactive beats: Design exercises relevant to the subject matter

The 4-act structure and McLuhan principle remain constant regardless of subject.

References

  • references/slide-patterns.md — Reusable pptxgenjs code patterns for each slide type
  • references/speaker-notes-guide.md — How to write effective speaker notes

Best Practices

  1. Cut aggressively: If a slide doesn't change understanding, delete it. The Dilution Effect applies to slide decks too.
  2. Story first, framework second: Always demonstrate a principle through a story or example before naming the framework.
  3. One idea per slide: If you need two sentences to explain what a slide is about, split it into two slides.
  4. Speaker notes ARE the presentation: The slides are visual anchors. The speaker's narrative, pauses, and meta-moments are where learning happens.
  5. Test the McLuhan principle: For every slide, ask "Is this slide itself an example of what it teaches?" If not, redesign it.

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 Textbook To Presentation Generator AI skill do?

Generates a lecture PowerPoint from an intelligent textbook using pptxgenjs — visual design, 4-act storytelling structure, and speaker notes. Use when converting a textbook into slides for classroom delivery.

Why use Textbook To Presentation Generator on TypingMind?

Because you install it once and use it with any model. Textbook To Presentation Generator 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 Textbook To Presentation Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dmccreary/ibook-skills/tree/main/skills/archived/textbook-to-presentation-generator. 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 Textbook To Presentation Generator?

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 Textbook To Presentation Generator?

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

Is the Textbook To Presentation Generator AI skill free?

It is published on GitHub by dmccreary. 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 👇