Paper Slide Deck Generator

Transform academic papers and content into professional slide deck images with automatic figure extraction.

Usage

/paper-slide-deck path/to/paper.pdf
/paper-slide-deck path/to/paper.pdf --style academic-paper
/paper-slide-deck path/to/content.md --style sketch-notes
/paper-slide-deck path/to/content.md --audience executives
/paper-slide-deck path/to/content.md --lang zh
/paper-slide-deck path/to/content.md --slides 10
/paper-slide-deck path/to/content.md --outline-only
/paper-slide-deck  # Then paste content

Setup (one-time)

The TypeScript scripts (merge-to-*, detect-figures, extract-figure, apply-template) need Node dependencies. Install them once:

cd ${SKILL_DIR}/scripts && npm install

This installs canvas, pdfjs-dist, pptxgenjs, and pdf-lib (a package-lock.json pins versions). If a script exits with missing Node dependency "<name>", run the command above. The Python generator (generate-slides.py) auto-installs google-genai on first run.

Also install PyMuPDF (pip install pymupdf) — it is the reliable fallback for extracting figures from pages that embed bitmaps (X-rays, CAM heatmaps, photographs), where the pdfjs + canvas path in extract-figure.ts fails with Error: Image or Canvas expected. For medical-imaging papers this is the common case, not the exception, so treat PyMuPDF as required, not optional.

Image generation & no-API-key path

Image generation needs either a GOOGLE_API_KEY/GEMINI_API_KEY (Gemini API) or the Gemini Web skill. If no key and no web option is available, the skill still works in a degraded mode — do not abort:

1. Run with --outline-only to produce the outline + prompts (no images).
2. For a source PDF, extract real figures/tables with detect-figures.ts + extract-figure.ts + apply-template.ts (no API key needed — pure rendering).
3. Merge whatever slides exist (extract-sourced pages) into PPTX/PDF, and hand the prompts/ back to the user to generate images later when a key is available.

Script Directory

Important: All scripts are located in the scripts/ subdirectory of this skill.

Agent Execution Instructions:

1. Determine this SKILL.md file's directory path as SKILL_DIR
2. Script path = ${SKILL_DIR}/scripts/<script-name>.ts
3. Replace all ${SKILL_DIR} in this document with the actual path

Script Reference:

Options

Style Gallery

Auto Style Selection

Academic-signal caution: When the content matches academic-paper signals (paper/thesis/neurips/cvpr/icml/…), this skill still bakes text into an image, so equations, result tables, and exact numbers may be garbled. Extract real figures/tables from the source PDF (Source: extract) rather than letting the model redraw them, and if the deck needs faithful, editable formulas/data, tell the user to use scholar-slides instead.

Layout Gallery

Optional layout hints for individual slides. Specify in outline's // LAYOUT section.

Slide-Specific Layouts

Infographic-Derived Layouts

Academic-Specific Layouts

Usage: Add Layout: <name> in slide's // LAYOUT section to guide visual composition.

Design Philosophy

This deck is designed for reading and sharing, not live presentation:

• Each slide must be self-explanatory without verbal commentary
• Structure content for logical flow when scrolling
• Include all necessary context within each slide
• Optimize for social media sharing and offline reading

File Management

Output Directory

Each session creates an independent directory named by content slug:

slide-deck/{topic-slug}/
├── source-{slug}.{ext}    # Source files (text, images, etc.)
├── outline.md
├── outline-{style}.md     # Style variant outlines
├── prompts/
│   └── 01-slide-cover.md, 02-slide-{slug}.md, ...
├── 01-slide-cover.png, 02-slide-{slug}.png, ...
├── {topic-slug}.pptx
└── {topic-slug}.pdf

Slug Generation:

1. Extract main topic from content (2-4 words, kebab-case)
2. Example: "Introduction to Machine Learning" → intro-machine-learning

Conflict Resolution

If slide-deck/{topic-slug}/ already exists:

• Append timestamp: {topic-slug}-YYYYMMDD-HHMMSS
• Example: intro-ml exists → intro-ml-20260118-143052

Source Files

Copy all sources with naming source-{slug}.{ext}:

• source-article.md (main text content)
• source-diagram.png (image from conversation)
• source-data.xlsx (additional file)

Multiple sources supported: text, images, files from conversation.

Workflow

Step 1: Analyze Content

1. Save source content (if pasted, save as source.md)

2. Follow references/analysis-framework.md for deep content analysis

3. Determine style (use --style or auto-select from signals)

4. Detect languages (source vs. user preference)

5. Plan slide count (--slides or dynamic)

6. For academic papers (PDF with figures): Run automatic figure detection:

   npx -y bun ${SKILL_DIR}/scripts/detect-figures.ts --pdf source-paper.pdf --output figures.json
   

   This outputs a JSON file with all detected figures/tables, their page numbers, and captions.

   Caption detection is heuristic — verify, especially the first-page teaser. The line-anchored Figure N matcher reliably finds captions that sit on their own line (single-column layouts), but misses figures whose caption is interleaved with body text on a two-column first page — which is often the paper's most important architecture/overview figure. After running detect-figures, cross-check the source's Figure 1 explicitly: if the paper's text references a Figure N that is absent from figures.json, add it manually via an // IMAGE_SOURCE block and extract it with the PyMuPDF fallback. Do not assume figures.json is complete.

Step 2: Generate Outline Variants

1. Generate 3 style variant outlines based on content analysis
2. Follow references/outline-template.md for structure
3. Auto-populate IMAGE_SOURCE for academic papers:
   • Read figures.json from Step 1
   • Map figures to slides using rules in references/analysis-framework.md Section 8
   • Automatically add // IMAGE_SOURCE blocks to appropriate slides:
     • Architecture/pipeline figures → Methods slides (Source: extract)
     • Results tables → Quantitative results slides (Source: extract)
     • Comparison images → Qualitative results slides (Source: extract)
     • Conceptual/simple diagrams → Leave for AI generation (Source: generate or omit)
4. Save as outline-{style}.md for each variant

Step 3: User Confirmation

Single AskUserQuestion with all applicable options:

After selection:

• Copy selected outline-{style}.md to outline.md
• Regenerate in different language if requested
• User may edit outline.md for fine-tuning

If --outline-only, stop here.

Step 4: Generate Prompts

1. Read references/base-prompt.md
2. Combine with style instructions from outline
3. Add slide-specific content
4. If Layout: specified in outline, include layout guidance in prompt:
   • Reference layout characteristics for image composition
   • Example: Layout: hub-spoke → "Central concept in middle with related items radiating outward"
5. Save to prompts/ directory

Step 5: Image Generation Method Selection

Before generating images, ask user to choose generation method:

Use AskUserQuestion with options:

Based on selection:

Option 1: Gemini API (Python)

1. Verify API key: Check GOOGLE_API_KEY or GEMINI_API_KEY environment variable
2. Run generation script:

   python3 ${SKILL_DIR}/scripts/generate-slides.py <slide-deck-dir>
   

   The default model is gemini-3-pro-image (Nano Banana Pro, GA). Override with --model <id> if needed. The older gemini-3-pro-image-preview id is deprecated.

Script Features:

• Auto-installs google-genai package if missing
• Reads prompt files as *.md (or *.txt) from prompts/
• Errors out (non-zero) if no prompt files are found — no silent "nothing to do"
• Retry logic with exponential backoff (3 retries)
• Sets response_modalities=["IMAGE"] so the model returns image parts
• Skips already-generated slides (> 10KB, any image extension)
• Writes each slide to the deck root (e.g. 01-slide-cover.png), the same place extracted-figure slides land — so one merge step picks up both
• Saves with the real image extension (Gemini often returns JPEG even when PNG is requested → saved as .jpg, never a mislabeled .png)
• Supports custom model via --model flag

Troubleshooting:

• If server disconnection errors occur, script auto-retries
• For persistent failures, re-run the script (it skips completed slides)
• Check API quota if many failures occur

Option 2: Gemini Web Skill

1. Consent Check: Read consent file at:

   • Windows: $APPDATA/baoyu-skills/gemini-web/consent.json
   • macOS: ~/Library/Application Support/baoyu-skills/gemini-web/consent.json
   • Linux: ~/.local/share/baoyu-skills/gemini-web/consent.json

2. If no consent or version mismatch, display disclaimer and ask:

   ⚠️ DISCLAIMER: This uses a reverse-engineered Gemini Web API (NOT official).
   Risks: May break anytime, no support, possible account risk.
   

3. For each slide, run:

   npx -y bun ${GEMINI_WEB_SKILL_DIR}/scripts/main.ts \
     --promptfiles prompts/01-slide-cover.md \
     --image 01-slide-cover.png \
     --sessionId slides-{topic-slug}-{timestamp}
   

   Where GEMINI_WEB_SKILL_DIR = path to baoyu-danger-gemini-web skill directory.

4. Proxy support: If user is in restricted network, prepend:

   HTTP_PROXY=http://127.0.0.1:7890 HTTPS_PROXY=http://127.0.0.1:7890
   

Step 5.5: Process IMAGE_SOURCE (Automatic Figure Extraction)

For academic presentations, IMAGE_SOURCE metadata was auto-populated in Step 2 based on figure detection from Step 1.

Automatic Execution:

1. Parse outline to identify slides with Source: extract

2. Create figures directory: mkdir -p figures

3. For each extract slide, automatically:

   • Read the Figure number, Page, and Caption from metadata
   • Run figure extraction script:

     npx -y bun ${SKILL_DIR}/scripts/extract-figure.ts \
       --pdf source-paper.pdf \
       --page <page-number> \
       --output figures/figure-<N>.png
     

     Note: extract-figure.ts renders the entire page to a high-resolution PNG — it does not auto-detect or crop a single figure's bounding box. On a two-column page you will get both columns. To isolate one figure, either pass --crop "x,y,width,height" (pixels in the rendered/scaled page) or open the PNG, confirm it visually, and crop manually before applying the template.
   • Run template application script:

     npx -y bun ${SKILL_DIR}/scripts/apply-template.ts \
       --figure figures/figure-<N>.png \
       --title "<slide-headline>" \
       --caption "Figure <N>: <caption-text>" \
       --output <NN>-slide-<slug>.png
     

   • Report: "Extracted: Figure N → slide NN"

4. For slides with Source: generate (or no IMAGE_SOURCE):

   • Proceed to Step 6 for AI generation

Note: Source PDF must be saved as source-paper.pdf in output directory.

Troubleshooting:

• If figure detection missed a figure: manually add // IMAGE_SOURCE block to outline
• If wrong figure mapped: edit the Figure: and Page: values in outline
• If extraction fails: check PDF page number (1-indexed)

PyMuPDF Fallback for Page Extraction: If extract-figure.ts fails with "Image or Canvas expected" error (common with complex PDFs), use PyMuPDF:

import fitz
doc = fitz.open("source-paper.pdf")
page = doc[page_num - 1]  # 0-indexed
mat = fitz.Matrix(3, 3)  # 3x scale for high resolution
pix = page.get_pixmap(matrix=mat)
pix.save(f"extracted/page-{page_num}.png")

Then apply template using apply-template.ts.

Step 6: Generate Images

1. Use selected method from Step 5
2. Skip slides already processed in Step 5.5 (those with Source: extract)
3. Generate session ID: slides-{topic-slug}-{timestamp}
4. Generate each remaining slide with same session ID
5. Report progress: "Generated X/N"
6. Auto-retry once on generation failure

Step 6.5: Proofread Generated Images (Content Integrity)

Text-to-image bakes text into pixels and will garble spelling, math symbols, and numbers — this is the single biggest risk of this skill. Do not ship unchecked.

For every generated slide (especially any with equations, tables, key numbers, or non-Latin text), use Read to open the PNG and visually check:

1. Spelling / wording — headline and body text match the outline, no invented or mangled words.
2. Math & symbols — equations, subscripts, Greek letters, operators are correct (or absent). Assume the model got them wrong until you confirm otherwise.
3. Numbers & units — any figure that carries data matches the source exactly.

If garbling is found:

• Regenerate that slide with a corrected/simplified prompt (spell risky terms phonetically, reduce text density, move exact numbers to a caption). Max 2 retries.
• If it still fails after 2 retries, flag the slide [CHECK] in the Step 8 summary and recommend one of:
  • Replace with an extracted figure/table from the source PDF (Source: extract), or
  • Simplify the slide to remove the fragile text, or
  • For a deck that genuinely needs faithful, editable formulas/data, switch to scholar-slides.

Never silently deliver a slide with garbled math or data — always surface it.

Step 7: Merge to PPTX and PDF

npx -y bun ${SKILL_DIR}/scripts/merge-to-pptx.ts <slide-deck-dir>
npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts <slide-deck-dir>

Step 8: Output Summary

Slide Deck Complete!

Topic: [topic]
Style: [style name]
Location: [directory path]
Slides: N total

- 01-slide-cover.png ✓ Cover
- 02-slide-intro.png ✓ Content
- 04-slide-results.png ⚠ [CHECK] math/numbers — verify or use scholar-slides
- ...
- {NN}-slide-back-cover.png ✓ Back Cover

Outline: outline.md
PPTX: {topic-slug}.pptx
PDF: {topic-slug}.pdf

List any [CHECK]-flagged slides (from Step 6.5) explicitly so the user knows which slides may contain garbled text/math/data and how to remediate them.

Slide Modification

See references/modification-guide.md for:

• Edit single slide workflow
• Add new slide (with renumbering)
• Delete slide (with renumbering)
• File naming conventions

Image Generation Dependencies

Gemini API (Option 1 - Recommended)

Requires:

• GOOGLE_API_KEY or GEMINI_API_KEY environment variable
• Python 3.8+ with pip
• google-genai package (auto-installed by script)

Model: gemini-3-pro-image (default; Nano Banana Pro, GA). The older gemini-3-pro-image-preview id is deprecated — override with --model only if needed.

Gemini Web Skill (Option 2)

Requires:

• baoyu-danger-gemini-web skill installed at .claude/skills/baoyu-danger-gemini-web
• Google Chrome browser with logged-in Google account
• User consent for reverse-engineered API disclaimer

PDF Figure Extraction

Requires (install via cd ${SKILL_DIR}/scripts && npm install):

• Primary: pdfjs-dist npm package (use legacy build for Node.js)
• canvas npm package for extract-figure.ts / apply-template.ts
• Fallback: pymupdf Python package (more reliable for complex PDFs)

References

Notes

Image Generation

• Nano Banana Pro API: Recommended. Stable, reliable, requires API key
• Gemini Web: No API key needed, but uses reverse-engineered API with account risk
• Generation time: 10-30 seconds per slide
• Auto-retry once on generation failure
• Maintain style consistency via session ID

Content Guidelines

• Use stylized alternatives for sensitive public figures
• Both methods use the same underlying Gemini model for image generation

Extension Support

Custom styles and configurations via EXTEND.md.

Check paths (priority order):

1. .paper-skills/paper-slide-deck/EXTEND.md (project)
2. ~/.paper-skills/paper-slide-deck/EXTEND.md (user)

If found, load before Step 1. Extension content overrides defaults.