Skip to main content

​
Overview

The PPTX skill enables comprehensive PowerPoint manipulation including creating slide decks from scratch, editing existing presentations, extracting content, and working with templates, layouts, speaker notes, and comments. Use this skill any time a .pptx file is involved as input or output.
Trigger this skill whenever working with “deck,” “slides,” “presentation,” or .pptx files - whether reading, creating, editing, combining, or splitting slide files.

​
Quick Reference

TaskGuide
Read/analyze contentpython -m markitdown presentation.pptx
Edit or create from templateRead editing.md
Create from scratchRead pptxgenjs.md

​
Reading Content

​
Text Extraction

# Extract all text content
python -m markitdown presentation.pptx

# Visual overview (thumbnail grid)
python scripts/thumbnail.py presentation.pptx

# Raw XML access
python scripts/office/unpack.py presentation.pptx unpacked/

​
Editing Workflow

For editing existing presentations:
  1. Analyze template with thumbnail.py
  2. Unpack → manipulate slides → edit content → clean → pack
Read the skill’s editing.md file for complete editing workflow details.

​
Creating from Scratch

When no template or reference presentation is available, create presentations programmatically using pptxgenjs.
Read the skill’s pptxgenjs.md file for full creation details and API reference.

​
Design Principles

Don’t create boring slides. Plain bullets on a white background won’t impress anyone. Every slide needs visual interest.

​
Before Starting

Pick a bold, content-informed color palette:
  • The palette should feel designed for THIS specific topic
  • If swapping colors into a different presentation would still “work,” you haven’t made specific enough choices
Dominance over equality:
  • One color should dominate (60-70% visual weight)
  • Use 1-2 supporting tones and one sharp accent
  • Never give all colors equal weight
Dark/light contrast:
  • Dark backgrounds for title + conclusion slides, light for content (“sandwich” structure)
  • Or commit to dark throughout for a premium feel
Commit to a visual motif:
  • Pick ONE distinctive element and repeat it
  • Examples: rounded image frames, icons in colored circles, thick single-side borders
  • Carry it across every slide

​
Color Palettes

​
For Each Slide

Every slide needs a visual element - image, chart, icon, or shape. Text-only slides are forgettable. Layout options:
  • Two-column (text left, illustration right)
  • Icon + text rows (icon in colored circle, bold header, description below)
  • 2x2 or 2x3 grid (image on one side, grid of content blocks on other)
  • Half-bleed image (full left or right side) with content overlay
Data display:
  • Large stat callouts (big numbers 60-72pt with small labels below)
  • Comparison columns (before/after, pros/cons, side-by-side options)
  • Timeline or process flow (numbered steps, arrows)
Visual polish:
  • Icons in small colored circles next to section headers
  • Italic accent text for key stats or taglines

​
Typography

Choose an interesting font pairing - don’t default to Arial:
Header FontBody Font
GeorgiaCalibri
Arial BlackArial
CalibriCalibri Light
CambriaCalibri
Trebuchet MSCalibri
ImpactArial
PalatinoGaramond
ConsolasCalibri
Size guidelines:
ElementSize
Slide title36-44pt bold
Section header20-24pt bold
Body text14-16pt
Captions10-12pt muted

​
Spacing

  • 0.5” minimum margins
  • 0.3-0.5” between content blocks
  • Leave breathing room - don’t fill every inch

​
Common Mistakes to Avoid

Don’t make these mistakes:
  • Don’t repeat the same layout - vary columns, cards, and callouts
  • Don’t center body text - left-align paragraphs and lists; center only titles
  • Don’t skimp on size contrast - titles need 36pt+ to stand out from body text
  • Don’t default to blue - pick colors reflecting the specific topic
  • Don’t mix spacing randomly - choose consistent gaps (0.3” or 0.5”)
  • Don’t style one slide and leave the rest plain - commit fully or keep simple
  • Don’t create text-only slides - add images, icons, charts, or visual elements
  • Don’t forget text box padding - account for it when aligning shapes
  • Don’t use low-contrast elements - ensure strong contrast against backgrounds
  • NEVER use accent lines under titles - hallmark of AI-generated slides

​
Quality Assurance (Required)

Assume there are problems. Your job is to find them.Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren’t looking hard enough.

​
Content QA

python -m markitdown output.pptx
Check for missing content, typos, wrong order. When using templates, check for leftover placeholder text: 
python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
If grep returns results, fix them before declaring success.

​
Visual QA

⚠️ USE SUBAGENTS - even for 2-3 slides. You’ve been staring at the code and will see what you expect, not what’s there. Subagents have fresh eyes.
Convert slides to images, then use this inspection prompt: 
Visually inspect these slides. Assume there are issues - find them.

Look for:
- Overlapping elements (text through shapes, lines through words)
- Text overflow or cut off at edges/box boundaries
- Decorative lines positioned for single-line text but title wrapped to two
- Source citations or footers colliding with content above
- Elements too close (< 0.3" gaps) or cards/sections nearly touching
- Uneven gaps (large empty area in one place, cramped in another)
- Insufficient margin from slide edges (< 0.5")
- Columns or similar elements not aligned consistently
- Low-contrast text (light gray on cream background)
- Low-contrast icons (dark icons on dark backgrounds without contrasting circle)
- Text boxes too narrow causing excessive wrapping
- Leftover placeholder content

For each slide, list issues or areas of concern, even if minor.

Read and analyze these images:
1. /path/to/slide-01.jpg (Expected: [brief description])
2. /path/to/slide-02.jpg (Expected: [brief description])

Report ALL issues found, including minor ones.

​
Verification Loop

  1. Generate slides → Convert to images → Inspect
  2. List issues found (if none found, look again more critically)
  3. Fix issues
  4. Re-verify affected slides - one fix often creates another problem
  5. Repeat until a full pass reveals no new issues
Do not declare success until you’ve completed at least one fix-and-verify cycle.

​
Converting to Images

Convert presentations to individual slide images for visual inspection: 
python scripts/office/soffice.py --headless --convert-to pdf output.pptx
pdftoppm -jpeg -r 150 output.pdf slide
This creates slide-01.jpg, slide-02.jpg, etc. To re-render specific slides after fixes: 
pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed
Where N is the slide number.

​
Dependencies

  • pip install "markitdown[pptx]" - text extraction
  • pip install Pillow - thumbnail grids
  • npm install -g pptxgenjs - creating from scratch
  • LibreOffice (soffice) - PDF conversion (auto-configured via scripts/office/soffice.py)
  • Poppler (pdftoppm) - PDF to images

​
Best Practices

Before finalizing your presentation:
  • Color palette is topic-specific and has clear dominance hierarchy
  • Visual motif is consistent across all slides
  • Every slide has at least one visual element (not text-only)
  • Font pairing is intentional and professional
  • Title text is 36pt+ and stands out from body text
  • Margins are at least 0.5” from slide edges
  • Spacing between elements is consistent (0.3” or 0.5”)
  • Text and icons have strong contrast against backgrounds
  • No accent lines under titles
  • Layout variety across slides (not repeating same pattern)
  • Content QA complete (no placeholder text)
  • Visual QA complete with subagent inspection
  • At least one fix-and-verify cycle completed

Build docs developers (and LLMs) love

Get started for freeTalk to us