Book Media Generator

Version: 1.0

Overview

This meta-skill generates static media for intelligent textbooks — slides, illustrations, sourced images, and audio. It consolidates six skills into a single entry point with on-demand loading of specific media guides.

FIRST: Slides Disambiguation Rule

Two routes make slide decks. Before routing any "make slides / a presentation / a deck" request, decide:

• Published on the site / embedded / web deck / shareable link → references/marp-deck-guide.md (MARP → self-contained HTML in docs/slides/, iframe-embedded, added to the slides gallery and nav)
• Downloadable file / classroom lecture / "PowerPoint" / .pptx → references/pptx-lecture-guide.md (pptxgenjs → .pptx with 4-act storytelling and speaker notes)
• Ambiguous (just "make slides for chapter 3") → ask ONE question: "Published on the site as a web deck, or a downloadable PowerPoint for classroom use?"

When to Use This Skill

Use this skill when users request:

• A slide deck or presentation from a topic, chapter, or document (see disambiguation rule above)
• An illustrated story / graphic novel about a scientist or historical figure (docs/stories/)
• Adding freely-licensed maps and photos to chapters (Wikimedia Commons, US government archives)
• Text-to-speech audio, voiceovers, or spoken narration (ElevenLabs)
• A "Pronounce" button with an MP3 pronunciation for a glossary term

Step 1: Identify Media Type

Routing Table

Decision Tree

Slides or a presentation?
  → Apply the Slides Disambiguation Rule (top of this file)

Narrative with illustrated panels about a person or case study?
  → YES: story-guide.md

Poster/infographic containing numeric claims or cited data?
  → NOT this skill: the fact-verified poster route lives in the
    microsim-generator skill (references/verified-infographic-guide.md)
  (purely decorative image with no factual claims → consider
   the cover-image feature in book-installer instead)

Real photos/maps sourced from archives (not AI-generated)?
  → YES: chapter-images-guide.md

Audio from text?
  → Single glossary term pronunciation → pronounce-button-guide.md
  → Anything else (narration, voiceover, app) → text-to-speech-guide.md

Step 2: Load the Matched Guide

Read the corresponding guide file from references/ and follow its workflow.

Audio Routes: ElevenLabs API Key

Both audio routes (text-to-speech-guide.md, pronounce-button-guide.md) call the ElevenLabs API and need ELEVENLABS_API_KEY set in the environment. Check for it before starting; if missing, point the user at references/tts-installation.md.

Supporting Files

• references/marp-mkdocs-integration.md, references/marp-authoring-guide.md, assets/marp/template.md — MARP route
• references/pptx-slide-patterns.md, references/pptx-speaker-notes-guide.md — PowerPoint route
• references/story-index-template.md, scripts/story/ (generate-images.py, verify-images.py, fix-references.py, uncomment-images.sh) — story route
• references/tts-installation.md, references/tts-streaming.md, references/tts-voice-settings.md — TTS route
• scripts/audio/generate-pronunciation.py — pronounce-button route

Examples

Example 1: Web Deck

User: "Turn chapter 4 into a presentation on the site" Routing: "presentation" + "on the site" → references/marp-deck-guide.md Action: Read marp-deck-guide.md; produce docs/slides// + gallery entry + nav

Example 2: Classroom PowerPoint

User: "I need a PowerPoint to lecture from for chapter 4" Routing: "PowerPoint" + "lecture" → references/pptx-lecture-guide.md Action: Read pptx-lecture-guide.md; generate the .pptx with speaker notes

Example 3: Ambiguous Slides

User: "Make slides for chapter 4" Routing: Ambiguous → ask: web deck or downloadable PowerPoint? Then route accordingly.

Example 4: Story

User: "Add a graphic novel story about Ada Lovelace to the Stories section" Routing: "graphic novel story" → references/story-guide.md Action: Read story-guide.md; write index.md with panel prompts; run scripts/story/generate-images.py

Example 5: Fact-Checked Poster (routes elsewhere)

User: "Create an infographic about remote-work productivity statistics" Routing: NOT this skill — fact-verified posters moved to microsim-generator → references/verified-infographic-guide.md Action: Load the microsim-generator skill instead; it owns claim verification, the poster pipeline, and the gallery thumbnail script

Example 6: Pronounce Button

User: "Create a pronounce button for the term Mitochondria" Routing: "pronounce button" → references/pronounce-button-guide.md Action: Read pronounce-button-guide.md; run scripts/audio/generate-pronunciation.py; insert the button into glossary.md