PPTX creation, editing, and analysis
Overview
A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.
Prerequisites
Python dependencies are resolved automatically by uv run — scripts declare them in PEP 723 headers. The workflows below also rely on:
- Node.js packages — if
node_modules/ is missing, run npm install in this skill directory once. This installs pptxgenjs and playwright, which drives Chromium/Chrome for HTML rendering (on macOS it uses system Chrome; elsewhere run npx playwright install chromium once if no browser is present). It also installs sharp, react, react-dom, and react-icons — html2pptx.js does not use these itself; they are provided for scripts you write during the html2pptx workflow (icon and gradient rasterization, see html2pptx.md)
- LibreOffice (
brew install --cask libreoffice) and poppler (brew install poppler) — converting presentations to PDF/images for thumbnails and visual validation (soffice, pdftoppm)
Reading and analyzing content
Text extraction
If you just need to read the text contents of a presentation, you should convert the document to markdown:
# Convert document to markdown
uv run --with 'markitdown[pptx]' python -m markitdown path-to-file.pptx
Raw XML access
You need raw XML access for: comments, speaker notes, slide layouts, animations, design elements, and complex formatting. For any of these features, you'll need to unpack a presentation and read its raw XML contents.
Unpacking a file
uv run ooxml/scripts/unpack.py <office_file> <output_dir>
Note: Run this from the pptx skill directory, where the script is at ooxml/scripts/unpack.py. If it isn't found there, use find . -name "unpack.py" to locate it.
Key file structures
ppt/presentation.xml - Main presentation metadata and slide references
ppt/slides/slide{N}.xml - Individual slide contents (slide1.xml, slide2.xml, etc.)
ppt/notesSlides/notesSlide{N}.xml - Speaker notes for each slide
ppt/comments/modernComment_*.xml - Comments for specific slides
ppt/slideLayouts/ - Layout templates for slides
ppt/slideMasters/ - Master slide templates
ppt/theme/ - Theme and styling information
ppt/media/ - Images and other media files
Typography and color extraction
When given an example design to emulate: Always analyze the presentation's typography and colors first using the methods below:
- Read theme file: Check
ppt/theme/theme1.xml for colors (<a:clrScheme>) and fonts (<a:fontScheme>)
- Sample slide content: Examine
ppt/slides/slide1.xml for actual font usage (<a:rPr>) and colors
- Search for patterns: Use grep to find color (
<a:solidFill>, <a:srgbClr>) and font references across all XML files
Creating a new PowerPoint presentation without a template
When creating a new PowerPoint presentation from scratch, use the html2pptx workflow to convert HTML slides to PowerPoint with accurate positioning.
Design Principles
CRITICAL: Before creating any presentation, analyze the content and choose appropriate design elements:
- Consider the subject matter: What is this presentation about? What tone, industry, or mood does it suggest?
- Check for branding: If the user mentions a company/organization, consider their brand colors and identity
- Match palette to content: Select colors that reflect the subject
- State your approach: Explain your design choices before writing code
Requirements:
- ✅ State your content-informed design approach BEFORE writing code
- ✅ Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact
- ✅ Create clear visual hierarchy through size, weight, and color
- ✅ Ensure readability: strong contrast, appropriately sized text, clean alignment
- ✅ Be consistent: repeat patterns, spacing, and visual language across slides
Color Palette Selection
Choosing colors creatively:
- Think beyond defaults: What colors genuinely match this specific topic? Avoid autopilot choices.
- Consider multiple angles: Topic, industry, mood, energy level, target audience, brand identity (if mentioned)
- Be adventurous: Try unexpected combinations - a healthcare presentation doesn't have to be green, finance doesn't have to be navy
- Build your palette: Pick 3-5 colors that work together (dominant colors + supporting tones + accent)
- Ensure contrast: Text must be clearly readable on backgrounds
Example color palettes (use these to spark creativity - choose one, adapt it, or create your own):
- Classic Blue: Deep navy (#1C2833), slate gray (#2E4053), silver (#AAB7B8), off-white (#F4F6F6)
- Teal & Coral: Teal (#5EA8A7), deep teal (#277884), coral (#FE4447), white (#FFFFFF)
- Bold Red: Red (#C0392B), bright red (#E74C3C), orange (#F39C12), yellow (#F1C40F), green (#2ECC71)
- Warm Blush: Mauve (#A49393), blush (#EED6D3), rose (#E8B4B8), cream (#FAF7F2)
- Burgundy Luxury: Burgundy (#5D1D2E), crimson (#951233), rust (#C15937), gold (#997929)
- Deep Purple & Emerald: Purple (#B165FB), dark blue (#181B24), emerald (#40695B), white (#FFFFFF)
- Cream & Forest Green: Cream (#FFE1C7), forest green (#40695B), white (#FCFCFC)
- Pink & Purple: Pink (#F8275B), coral (#FF574A), rose (#FF737D), purple (#3D2F68)
- Lime & Plum: Lime (#C5DE82), plum (#7C3A5F), coral (#FD8C6E), blue-gray (#98ACB5)
- Black & Gold: Gold (#BF9A4A), black (#000000), cream (#F4F6F6)
- Sage & Terracotta: Sage (#87A96B), terracotta (#E07A5F), cream (#F4F1DE), charcoal (#2C2C2C)
- Charcoal & Red: Charcoal (#292929), red (#E33737), light gray (#CCCBCB)
- Vibrant Orange: Orange (#F96D00), light gray (#F2F2F2), charcoal (#222831)
- Forest Green: Black (#191A19), green (#4E9F3D), dark green (#1E5128), white (#FFFFFF)
- Retro Rainbow: Purple (#722880), pink (#D72D51), orange (#EB5C18), amber (#F08800), gold (#DEB600)
- Vintage Earthy: Mustard (#E3B448), sage (#CBD18F), forest green (#3A6B35), cream (#F4F1DE)
- Coastal Rose: Old rose (#AD7670), beaver (#B49886), eggshell (#F3ECDC), ash gray (#BFD5BE)
- Orange & Turquoise: Light orange (#FC993E), grayish turquoise (#667C6F), white (#FCFCFC)
Visual Details Options
Geometric Patterns:
- Diagonal section dividers instead of horizontal
- Asymmetric column widths (30/70, 40/60, 25/75)
- Rotated text headers at 90° or 270°
- Circular/hexagonal frames for images
- Triangular accent shapes in corners
- Overlapping shapes for depth
Border & Frame Treatments:
- Thick single-color borders (10-20pt) on one side only
- Double-line borders with contrasting colors
- Corner brackets instead of full frames
- L-shaped borders (top+left or bottom+right)
- Underline accents beneath headers (3-5pt thick)
Typography Treatments:
- Extreme size contrast (72pt headlines vs 11pt body)
- All-caps headers with wide letter spacing
- Numbered sections in oversized display type
- Monospace (Courier New) for data/stats/technical content
- Condensed fonts (Arial Narrow) for dense information
- Outlined text for emphasis
Chart & Data Styling:
- Monochrome charts with single accent color for key data
- Horizontal bar charts instead of vertical
- Dot plots instead of bar charts
- Minimal gridlines or none at all
- Data labels directly on elements (no legends)
- Oversized numbers for key metrics
Layout Innovations:
- Full-bleed images with text overlays
- Sidebar column (20-30% width) for navigation/context
- Modular grid systems (3×3, 4×4 blocks)
- Z-pattern or F-pattern content flow
- Floating text boxes over colored shapes
- Magazine-style multi-column layouts
Background Treatments:
- Solid color blocks occupying 40-60% of slide
- Gradient fills (vertical or diagonal only)
- Split backgrounds (two colors, diagonal or vertical)
- Edge-to-edge color bands
- Negative space as a design element
Layout Tips
When creating slides with charts or tables:
- Two-column layout (PREFERRED): Use a header spanning the full width, then two columns below - text/bullets in one column and the featured content in the other. This provides better balance and makes charts/tables more readable. Use flexbox with unequal column widths (e.g., 40%/60% split) to optimize space for each content type.
- Full-slide layout: Let the featured content (chart/table) take up the entire slide for maximum impact and readability
- NEVER vertically stack: Do not place charts/tables below text in a single column - this causes poor readability and layout issues
Workflow
- MANDATORY - READ ENTIRE FILE: Read
html2pptx.md completely from start to finish. NEVER set any range limits when reading this file. Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with presentation creation.
- Create an HTML file for each slide with proper dimensions (e.g., 720pt × 405pt for 16:9)
- Use
<p>, <h1>-<h6>, <ul>, <ol> for all text content
- Use
class="placeholder" for areas where charts/tables will be added (render with gray background for visibility)
- CRITICAL: Rasterize gradients and icons as PNG images FIRST using Sharp, then reference in HTML
- LAYOUT: For slides with charts/tables/images, use either full-slide layout or two-column layout for better readability
- Create and run a JavaScript file using the
html2pptx.js library to convert HTML slides to PowerPoint and save the presentation
- Use the
html2pptx() function to process each HTML file
- Add charts and tables to placeholder areas using PptxGenJS API
- Save the presentation using
pptx.writeFile()
- Visual validation: Generate thumbnails and inspect for layout issues
- Create thumbnail grid:
uv run scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4
- Read and carefully examine the thumbnail image for:
- Text cutoff: Text being cut off by header bars, shapes, or slide edges
- Text overlap: Text overlapping with other text or shapes
- Positioning issues: Content too close to slide boundaries or other elements
- Contrast issues: Insufficient contrast between text and backgrounds
- If issues found, adjust HTML margins/spacing/colors and regenerate the presentation
- Repeat until all slides are visually correct
Editing an existing PowerPoint presentation
When edit slides in an existing PowerPoint presentation, you need to work with the raw Office Open XML (OOXML) format. This involves unpacking the .pptx file, editing the XML content, and repacking it.
Workflow
- MANDATORY - READ ENTIRE FILE: Read
ooxml.md (~425 lines) completely from start to finish. NEVER set any range limits when reading this file. Read the full file content for detailed guidance on OOXML structure and editing workflows before any presentation editing.
- Unpack the presentation:
uv run ooxml/scripts/unpack.py <office_file> <output_dir>
- Edit the XML files (primarily
ppt/slides/slide{N}.xml and related files)
- CRITICAL: Validate immediately after each edit and fix any validation errors before proceeding:
uv run ooxml/scripts/validate.py <dir> --original <file>
- Pack the final presentation:
uv run ooxml/scripts/pack.py <input_directory> <office_file>
Creating a new PowerPoint presentation using a template
When you need to create a presentation that follows an existing template's design, you'll need to duplicate and re-arrange template slides before then replacing placeholder context.
Workflow
Extract template text AND create visual thumbnail grid:
- Extract text:
uv run --with 'markitdown[pptx]' python -m markitdown template.pptx > template-content.md
- Read
template-content.md: Read the entire file to understand the contents of the template presentation. NEVER set any range limits when reading this file.
- Create thumbnail grids:
uv run scripts/thumbnail.py template.pptx
- See Creating Thumbnail Grids section for more details
Analyze template and save inventory to a file:
- Visual Analysis: Review thumbnail grid(s) to understand slide layouts, design patterns, and visual structure
- Create and save a template inventory file at
template-inventory.md containing:# Template Inventory Analysis
**Total Slides: [count]**
**IMPORTANT: Slides are 0-indexed (first slide = 0, last slide = count-1)**
## [Category Name]
- Slide 0: [Layout code if available] - Description/purpose
- Slide 1: [Layout code] - Description/purpose
- Slide 2: [Layout code] - Description/purpose
[... EVERY slide must be listed individually with its index ...]
- Using the thumbnail grid: Reference the visual thumbnails to identify:
- Layout patterns (title slides, content layouts, section dividers)
- Image placeholder locations and counts
- Design consistency across slide groups
- Visual hierarchy and structure
- This inventory file is REQUIRED for selecting appropriate templates in the next step
Create presentation outline based on template inventory:
- Review available templates from step 2.
- Choose an intro or title template for the first slide. This should be one of the first templates.
- Choose safe, text-based layouts for the other slides.
- CRITICAL: Match layout structure to actual content:
- Single-column layouts: Use for unified narrative or single topic
- Two-column layouts: Use ONLY when you have exactly 2 distinct items/concepts
- Three-column layouts: Use ONLY when you have exactly 3 distinct items/concepts
- Image + text layouts: Use ONLY when you have actual images to insert
- Quote layouts: Use ONLY for actual quotes from people (with attribution), never for emphasis
- Never use layouts with more placeholders than you have content
- If you have 2 items, don't force them into a 3-column layout
- If you have 4+ items, consider breaking into multiple slides or using a list format
- Count your actual content pieces BEFORE selecting the layout
- Verify each placeholder in the chosen layout will be filled with meaningful content
- Select one option representing the best layout for each content section.
- Save
outline.md with content AND template mapping that leverages available designs
- Example template mapping:
# Template slides to use (0-based indexing)
# WARNING: Verify indices are within range! Template with 73 slides has indices 0-72
# Mapping: slide numbers from outline -> template slide indices
template_mapping = [
0, # Use slide 0 (Title/Cover)
34, # Use slide 34 (B1: Title and body)
34, # Use slide 34 again (duplicate for second B1)
50, # Use slide 50 (E1: Quote)
54, # Use slide 54 (F2: Closing + Text)
]
Duplicate, reorder, and delete slides using rearrange.py:
- Use the
scripts/rearrange.py script to create a new presentation with slides in the desired order:uv run scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52
- The script handles duplicating repeated slides, deleting unused slides, and reordering automatically
- Slide indices are 0-based (first slide is 0, second is 1, etc.)
- The same slide index can appear multiple times to duplicate that slide
Extract ALL text using the inventory.py script:
Run inventory extraction:
uv run scripts/inventory.py working.pptx text-inventory.json
Read text-inventory.json: Read the entire text-inventory.json file to understand all shapes and their properties. NEVER set any range limits when reading this file.
The inventory JSON structure:
{
"slide-0": {
"shape-0": {
"placeholder_type": "TITLE", // or null for non-placeholders
"left": 1.5, // position in inches
"top": 2.0,
"width": 7.5,
"height": 1.2,
"paragraphs": [
{
"text": "Paragraph text",
// Optional properties (only included when non-default):
"bullet": true, // explicit bullet detected
"level": 0, // only included when bullet is true
"alignment": "CENTER", // CENTER, RIGHT (not LEFT)
"space_before": 10.0, // space before paragraph in points
"space_after": 6.0, // space after paragraph in points
"line_spacing": 22.4, // line spacing in points
"font_name": "Arial", // from first run
"font_size": 14.0, // in points
"bold": true,
"italic": false,
"underline": false,
"color": "FF0000" // RGB color
}
]
}
}
}
Key features:
- Slides: Named as "slide-0", "slide-1", etc.
- Shapes: Ordered by visual position (top-to-bottom, left-to-right) as "shape-0", "shape-1", etc.
- Placeholder types: TITLE, CENTER_TITLE, SUBTITLE, BODY, OBJECT, or null
- Default font size:
default_font_size in points extracted from layout placeholders (when available)
- Slide numbers are filtered: Shapes with SLIDE_NUMBER placeholder type are automatically excluded from inventory
- Bullets: When
bullet: true, level is always included (even if 0)
- Spacing:
space_before, space_after, and line_spacing in points (only included when set)
- Colors:
color for RGB (e.g., "FF0000"), theme_color for theme colors (e.g., "DARK_1")
- Properties: Only non-default values are included in the output
Generate replacement text and save the data to a JSON file
Based on the text inventory from the previous step:
- CRITICAL: First verify which shapes exist in the inventory - only reference shapes that are actually present
- VALIDATION: The replace.py script will validate that all shapes in your replacement JSON exist in the inventory
- If you reference a non-existent shape, you'll get an error showing available shapes
- If you reference a non-existent slide, you'll get an error indicating the slide doesn't exist
- All validation errors are shown at once before the script exits
- IMPORTANT: The replace.py script uses inventory.py internally to identify ALL text shapes
- AUTOMATIC CLEARING: ALL text shapes from the inventory will be cleared unless you provide "paragraphs" for them
- Add a "paragraphs" field to shapes that need content (not "replacement_paragraphs")
- Shapes without "paragraphs" in the replacement JSON will have their text cleared automatically
- Paragraphs with bullets will be automatically left aligned. Don't set the
alignment property on when "bullet": true
- Generate appropriate replacement content for placeholder text
- Use shape size to determine appropriate content length
- CRITICAL: Include paragraph properties from the original inventory - don't just provide text
- IMPORTANT: When bullet: true, do NOT include bullet symbols (•, -, *) in text - they're added automatically
- ESSENTIAL FORMATTING RULES:
- Headers/titles should typically have
"bold": true
- List items should have
"bullet": true, "level": 0 (level is required when bullet is true)
- Preserve any alignment properties (e.g.,
"alignment": "CENTER" for centered text)
- Include font properties when different from default (e.g.,
"font_size": 14.0, "font_name": "Lora")
- Colors: Use
"color": "FF0000" for RGB or "theme_color": "DARK_1" for theme colors
- The replacement script expects properly formatted paragraphs, not just text strings
- Overlapping shapes: Prefer shapes with larger default_font_size or more appropriate placeholder_type
- Save the updated inventory with replacements to
replacement-text.json
- WARNING: Different template layouts have different shape counts - always check the actual inventory before creating replacements
Example paragraphs field showing proper formatting:
"paragraphs": [
{
"text": "New presentation title text",
"alignment": "CENTER",
"bold": true
},
{
"text": "Section Header",
"bold": true
},
{
"text": "First bullet point without bullet symbol",
"bullet": true,
"level": 0
},
{
"text": "Red colored text",
"color": "FF0000"
},
{
"text": "Theme colored text",
"theme_color": "DARK_1"
},
{
"text": "Regular paragraph text without special formatting"
}
]
Shapes not listed in the replacement JSON are automatically cleared:
{
"slide-0": {
"shape-0": {
"paragraphs": [...] // This shape gets new text
}
// shape-1 and shape-2 from inventory will be cleared automatically
}
}
Common formatting patterns for presentations:
- Title slides: Bold text, sometimes centered
- Section headers within slides: Bold text
- Bullet lists: Each item needs
"bullet": true, "level": 0
- Body text: Usually no special properties needed
- Quotes: May have special alignment or font properties
Apply replacements using the replace.py script
uv run scripts/replace.py working.pptx replacement-text.json output.pptx
The script will:
- First extract the inventory of ALL text shapes using functions from inventory.py
- Validate that all shapes in the replacement JSON exist in the inventory
- Clear text from ALL shapes identified in the inventory
- Apply new text only to shapes with "paragraphs" defined in the replacement JSON
- Preserve formatting by applying paragraph properties from the JSON
- Handle bullets, alignment, font properties, and colors automatically
- Save the updated presentation
Example validation errors:
ERROR: Invalid shapes in replacement JSON:
- Shape 'shape-99' not found on 'slide-0'. Available shapes: shape-0, shape-1, shape-4
- Slide 'slide-999' not found in inventory
ERROR: Replacement text made overflow worse in these shapes:
- slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25")
Creating Thumbnail Grids
To create visual thumbnail grids of PowerPoint slides for quick analysis and reference:
uv run scripts/thumbnail.py template.pptx [output_prefix]
Features:
- Creates:
thumbnails.jpg (or thumbnails-1.jpg, thumbnails-2.jpg, etc. for large decks)
- Default: 5 columns, max 30 slides per grid (5×6)
- Custom prefix:
uv run scripts/thumbnail.py template.pptx my-grid
- Note: The output prefix should include the path if you want output in a specific directory (e.g.,
workspace/my-grid)
- Adjust columns:
--cols 4 (range: 3-6, affects slides per grid)
- Grid limits: 3 cols = 12 slides/grid, 4 cols = 20, 5 cols = 30, 6 cols = 42
- Slides are zero-indexed (Slide 0, Slide 1, etc.)
Use cases:
- Template analysis: Quickly understand slide layouts and design patterns
- Content review: Visual overview of entire presentation
- Navigation reference: Find specific slides by their visual appearance
- Quality check: Verify all slides are properly formatted
Examples:
# Basic usage
uv run scripts/thumbnail.py presentation.pptx
# Combine options: custom name, columns
uv run scripts/thumbnail.py template.pptx analysis --cols 4
Converting Slides to Images
To visually analyze PowerPoint slides, convert them to images using a two-step process:
Convert PPTX to PDF:
soffice --headless --convert-to pdf template.pptx
Convert PDF pages to JPEG images:
pdftoppm -jpeg -r 150 template.pdf slide
This creates files like slide-1.jpg, slide-2.jpg, etc.
Options:
-r 150: Sets resolution to 150 DPI (adjust for quality/size balance)
-jpeg: Output JPEG format (use -png for PNG if preferred)
-f N: First page to convert (e.g., -f 2 starts from page 2)
-l N: Last page to convert (e.g., -l 5 stops at page 5)
slide: Prefix for output files
Example for specific range:
pdftoppm -jpeg -r 150 -f 2 -l 5 template.pdf slide # Converts only pages 2-5
Code Style Guidelines
IMPORTANT: When generating code for PPTX operations:
- Write concise code
- Avoid verbose variable names and redundant operations
- Avoid unnecessary print statements
1---
2name: pptx
3description: "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks"
4metadata:
5 source: https://skillmd.com/skills/appautomaton/pptx
6---
7
8# PPTX creation, editing, and analysis
9
10## Overview
11
12A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.
13
14## Prerequisites
15
16Python dependencies are resolved automatically by `uv run` — scripts declare them in PEP 723 headers. The workflows below also rely on:
17
18- **Node.js packages** — if `node_modules/` is missing, run `npm install` in this skill directory once. This installs `pptxgenjs` and `playwright`, which drives Chromium/Chrome for HTML rendering (on macOS it uses system Chrome; elsewhere run `npx playwright install chromium` once if no browser is present). It also installs `sharp`, `react`, `react-dom`, and `react-icons` — html2pptx.js does not use these itself; they are provided for scripts you write during the html2pptx workflow (icon and gradient rasterization, see [html2pptx.md](html2pptx.md))
19- **LibreOffice** (`brew install --cask libreoffice`) and **poppler** (`brew install poppler`) — converting presentations to PDF/images for thumbnails and visual validation (`soffice`, `pdftoppm`)
20
21## Reading and analyzing content
22
23### Text extraction
24If you just need to read the text contents of a presentation, you should convert the document to markdown:
25
26```bash
27# Convert document to markdown
28uv run --with 'markitdown[pptx]' python -m markitdown path-to-file.pptx
29```
30
31### Raw XML access
32You need raw XML access for: comments, speaker notes, slide layouts, animations, design elements, and complex formatting. For any of these features, you'll need to unpack a presentation and read its raw XML contents.
33
34#### Unpacking a file
35`uv run ooxml/scripts/unpack.py <office_file> <output_dir>`
36
37**Note**: Run this from the pptx skill directory, where the script is at `ooxml/scripts/unpack.py`. If it isn't found there, use `find . -name "unpack.py"` to locate it.
38
39#### Key file structures
40* `ppt/presentation.xml` - Main presentation metadata and slide references
41* `ppt/slides/slide{N}.xml` - Individual slide contents (slide1.xml, slide2.xml, etc.)
42* `ppt/notesSlides/notesSlide{N}.xml` - Speaker notes for each slide
43* `ppt/comments/modernComment_*.xml` - Comments for specific slides
44* `ppt/slideLayouts/` - Layout templates for slides
45* `ppt/slideMasters/` - Master slide templates
46* `ppt/theme/` - Theme and styling information
47* `ppt/media/` - Images and other media files
48
49#### Typography and color extraction
50**When given an example design to emulate**: Always analyze the presentation's typography and colors first using the methods below:
511. **Read theme file**: Check `ppt/theme/theme1.xml` for colors (`<a:clrScheme>`) and fonts (`<a:fontScheme>`)
522. **Sample slide content**: Examine `ppt/slides/slide1.xml` for actual font usage (`<a:rPr>`) and colors
533. **Search for patterns**: Use grep to find color (`<a:solidFill>`, `<a:srgbClr>`) and font references across all XML files
54
55## Creating a new PowerPoint presentation **without a template**
56
57When creating a new PowerPoint presentation from scratch, use the **html2pptx** workflow to convert HTML slides to PowerPoint with accurate positioning.
58
59### Design Principles
60
61**CRITICAL**: Before creating any presentation, analyze the content and choose appropriate design elements:
621. **Consider the subject matter**: What is this presentation about? What tone, industry, or mood does it suggest?
632. **Check for branding**: If the user mentions a company/organization, consider their brand colors and identity
643. **Match palette to content**: Select colors that reflect the subject
654. **State your approach**: Explain your design choices before writing code
66
67**Requirements**:
68- ✅ State your content-informed design approach BEFORE writing code
69- ✅ Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact
70- ✅ Create clear visual hierarchy through size, weight, and color
71- ✅ Ensure readability: strong contrast, appropriately sized text, clean alignment
72- ✅ Be consistent: repeat patterns, spacing, and visual language across slides
73
74#### Color Palette Selection
75
76**Choosing colors creatively**:
77- **Think beyond defaults**: What colors genuinely match this specific topic? Avoid autopilot choices.
78- **Consider multiple angles**: Topic, industry, mood, energy level, target audience, brand identity (if mentioned)
79- **Be adventurous**: Try unexpected combinations - a healthcare presentation doesn't have to be green, finance doesn't have to be navy
80- **Build your palette**: Pick 3-5 colors that work together (dominant colors + supporting tones + accent)
81- **Ensure contrast**: Text must be clearly readable on backgrounds
82
83**Example color palettes** (use these to spark creativity - choose one, adapt it, or create your own):
84
851. **Classic Blue**: Deep navy (#1C2833), slate gray (#2E4053), silver (#AAB7B8), off-white (#F4F6F6)
862. **Teal & Coral**: Teal (#5EA8A7), deep teal (#277884), coral (#FE4447), white (#FFFFFF)
873. **Bold Red**: Red (#C0392B), bright red (#E74C3C), orange (#F39C12), yellow (#F1C40F), green (#2ECC71)
884. **Warm Blush**: Mauve (#A49393), blush (#EED6D3), rose (#E8B4B8), cream (#FAF7F2)
895. **Burgundy Luxury**: Burgundy (#5D1D2E), crimson (#951233), rust (#C15937), gold (#997929)
906. **Deep Purple & Emerald**: Purple (#B165FB), dark blue (#181B24), emerald (#40695B), white (#FFFFFF)
917. **Cream & Forest Green**: Cream (#FFE1C7), forest green (#40695B), white (#FCFCFC)
928. **Pink & Purple**: Pink (#F8275B), coral (#FF574A), rose (#FF737D), purple (#3D2F68)
939. **Lime & Plum**: Lime (#C5DE82), plum (#7C3A5F), coral (#FD8C6E), blue-gray (#98ACB5)
9410. **Black & Gold**: Gold (#BF9A4A), black (#000000), cream (#F4F6F6)
9511. **Sage & Terracotta**: Sage (#87A96B), terracotta (#E07A5F), cream (#F4F1DE), charcoal (#2C2C2C)
9612. **Charcoal & Red**: Charcoal (#292929), red (#E33737), light gray (#CCCBCB)
9713. **Vibrant Orange**: Orange (#F96D00), light gray (#F2F2F2), charcoal (#222831)
9814. **Forest Green**: Black (#191A19), green (#4E9F3D), dark green (#1E5128), white (#FFFFFF)
9915. **Retro Rainbow**: Purple (#722880), pink (#D72D51), orange (#EB5C18), amber (#F08800), gold (#DEB600)
10016. **Vintage Earthy**: Mustard (#E3B448), sage (#CBD18F), forest green (#3A6B35), cream (#F4F1DE)
10117. **Coastal Rose**: Old rose (#AD7670), beaver (#B49886), eggshell (#F3ECDC), ash gray (#BFD5BE)
10218. **Orange & Turquoise**: Light orange (#FC993E), grayish turquoise (#667C6F), white (#FCFCFC)
103
104#### Visual Details Options
105
106**Geometric Patterns**:
107- Diagonal section dividers instead of horizontal
108- Asymmetric column widths (30/70, 40/60, 25/75)
109- Rotated text headers at 90° or 270°
110- Circular/hexagonal frames for images
111- Triangular accent shapes in corners
112- Overlapping shapes for depth
113
114**Border & Frame Treatments**:
115- Thick single-color borders (10-20pt) on one side only
116- Double-line borders with contrasting colors
117- Corner brackets instead of full frames
118- L-shaped borders (top+left or bottom+right)
119- Underline accents beneath headers (3-5pt thick)
120
121**Typography Treatments**:
122- Extreme size contrast (72pt headlines vs 11pt body)
123- All-caps headers with wide letter spacing
124- Numbered sections in oversized display type
125- Monospace (Courier New) for data/stats/technical content
126- Condensed fonts (Arial Narrow) for dense information
127- Outlined text for emphasis
128
129**Chart & Data Styling**:
130- Monochrome charts with single accent color for key data
131- Horizontal bar charts instead of vertical
132- Dot plots instead of bar charts
133- Minimal gridlines or none at all
134- Data labels directly on elements (no legends)
135- Oversized numbers for key metrics
136
137**Layout Innovations**:
138- Full-bleed images with text overlays
139- Sidebar column (20-30% width) for navigation/context
140- Modular grid systems (3×3, 4×4 blocks)
141- Z-pattern or F-pattern content flow
142- Floating text boxes over colored shapes
143- Magazine-style multi-column layouts
144
145**Background Treatments**:
146- Solid color blocks occupying 40-60% of slide
147- Gradient fills (vertical or diagonal only)
148- Split backgrounds (two colors, diagonal or vertical)
149- Edge-to-edge color bands
150- Negative space as a design element
151
152### Layout Tips
153**When creating slides with charts or tables:**
154- **Two-column layout (PREFERRED)**: Use a header spanning the full width, then two columns below - text/bullets in one column and the featured content in the other. This provides better balance and makes charts/tables more readable. Use flexbox with unequal column widths (e.g., 40%/60% split) to optimize space for each content type.
155- **Full-slide layout**: Let the featured content (chart/table) take up the entire slide for maximum impact and readability
156- **NEVER vertically stack**: Do not place charts/tables below text in a single column - this causes poor readability and layout issues
157
158### Workflow
1591. **MANDATORY - READ ENTIRE FILE**: Read [`html2pptx.md`](html2pptx.md) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with presentation creation.
1602. Create an HTML file for each slide with proper dimensions (e.g., 720pt × 405pt for 16:9)
161 - Use `<p>`, `<h1>`-`<h6>`, `<ul>`, `<ol>` for all text content
162 - Use `class="placeholder"` for areas where charts/tables will be added (render with gray background for visibility)
163 - **CRITICAL**: Rasterize gradients and icons as PNG images FIRST using Sharp, then reference in HTML
164 - **LAYOUT**: For slides with charts/tables/images, use either full-slide layout or two-column layout for better readability
1653. Create and run a JavaScript file using the [`html2pptx.js`](scripts/html2pptx.js) library to convert HTML slides to PowerPoint and save the presentation
166 - Use the `html2pptx()` function to process each HTML file
167 - Add charts and tables to placeholder areas using PptxGenJS API
168 - Save the presentation using `pptx.writeFile()`
1694. **Visual validation**: Generate thumbnails and inspect for layout issues
170 - Create thumbnail grid: `uv run scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4`
171 - Read and carefully examine the thumbnail image for:
172 - **Text cutoff**: Text being cut off by header bars, shapes, or slide edges
173 - **Text overlap**: Text overlapping with other text or shapes
174 - **Positioning issues**: Content too close to slide boundaries or other elements
175 - **Contrast issues**: Insufficient contrast between text and backgrounds
176 - If issues found, adjust HTML margins/spacing/colors and regenerate the presentation
177 - Repeat until all slides are visually correct
178
179## Editing an existing PowerPoint presentation
180
181When edit slides in an existing PowerPoint presentation, you need to work with the raw Office Open XML (OOXML) format. This involves unpacking the .pptx file, editing the XML content, and repacking it.
182
183### Workflow
1841. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~425 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed guidance on OOXML structure and editing workflows before any presentation editing.
1852. Unpack the presentation: `uv run ooxml/scripts/unpack.py <office_file> <output_dir>`
1863. Edit the XML files (primarily `ppt/slides/slide{N}.xml` and related files)
1874. **CRITICAL**: Validate immediately after each edit and fix any validation errors before proceeding: `uv run ooxml/scripts/validate.py <dir> --original <file>`
1885. Pack the final presentation: `uv run ooxml/scripts/pack.py <input_directory> <office_file>`
189
190## Creating a new PowerPoint presentation **using a template**
191
192When you need to create a presentation that follows an existing template's design, you'll need to duplicate and re-arrange template slides before then replacing placeholder context.
193
194### Workflow
1951. **Extract template text AND create visual thumbnail grid**:
196 * Extract text: `uv run --with 'markitdown[pptx]' python -m markitdown template.pptx > template-content.md`
197 * Read `template-content.md`: Read the entire file to understand the contents of the template presentation. **NEVER set any range limits when reading this file.**
198 * Create thumbnail grids: `uv run scripts/thumbnail.py template.pptx`
199 * See [Creating Thumbnail Grids](#creating-thumbnail-grids) section for more details
200
2012. **Analyze template and save inventory to a file**:
202 * **Visual Analysis**: Review thumbnail grid(s) to understand slide layouts, design patterns, and visual structure
203 * Create and save a template inventory file at `template-inventory.md` containing:
204 ```markdown
205 # Template Inventory Analysis
206 **Total Slides: [count]**
207 **IMPORTANT: Slides are 0-indexed (first slide = 0, last slide = count-1)**
208
209 ## [Category Name]
210 - Slide 0: [Layout code if available] - Description/purpose
211 - Slide 1: [Layout code] - Description/purpose
212 - Slide 2: [Layout code] - Description/purpose
213 [... EVERY slide must be listed individually with its index ...]
214 ```
215 * **Using the thumbnail grid**: Reference the visual thumbnails to identify:
216 - Layout patterns (title slides, content layouts, section dividers)
217 - Image placeholder locations and counts
218 - Design consistency across slide groups
219 - Visual hierarchy and structure
220 * This inventory file is REQUIRED for selecting appropriate templates in the next step
221
2223. **Create presentation outline based on template inventory**:
223 * Review available templates from step 2.
224 * Choose an intro or title template for the first slide. This should be one of the first templates.
225 * Choose safe, text-based layouts for the other slides.
226 * **CRITICAL: Match layout structure to actual content**:
227 - Single-column layouts: Use for unified narrative or single topic
228 - Two-column layouts: Use ONLY when you have exactly 2 distinct items/concepts
229 - Three-column layouts: Use ONLY when you have exactly 3 distinct items/concepts
230 - Image + text layouts: Use ONLY when you have actual images to insert
231 - Quote layouts: Use ONLY for actual quotes from people (with attribution), never for emphasis
232 - Never use layouts with more placeholders than you have content
233 - If you have 2 items, don't force them into a 3-column layout
234 - If you have 4+ items, consider breaking into multiple slides or using a list format
235 * Count your actual content pieces BEFORE selecting the layout
236 * Verify each placeholder in the chosen layout will be filled with meaningful content
237 * Select one option representing the **best** layout for each content section.
238 * Save `outline.md` with content AND template mapping that leverages available designs
239 * Example template mapping:
240 ```
241 # Template slides to use (0-based indexing)
242 # WARNING: Verify indices are within range! Template with 73 slides has indices 0-72
243 # Mapping: slide numbers from outline -> template slide indices
244 template_mapping = [
245 0, # Use slide 0 (Title/Cover)
246 34, # Use slide 34 (B1: Title and body)
247 34, # Use slide 34 again (duplicate for second B1)
248 50, # Use slide 50 (E1: Quote)
249 54, # Use slide 54 (F2: Closing + Text)
250 ]
251 ```
252
2534. **Duplicate, reorder, and delete slides using `rearrange.py`**:
254 * Use the `scripts/rearrange.py` script to create a new presentation with slides in the desired order:
255 ```bash
256 uv run scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52
257 ```
258 * The script handles duplicating repeated slides, deleting unused slides, and reordering automatically
259 * Slide indices are 0-based (first slide is 0, second is 1, etc.)
260 * The same slide index can appear multiple times to duplicate that slide
261
2625. **Extract ALL text using the `inventory.py` script**:
263 * **Run inventory extraction**:
264 ```bash
265 uv run scripts/inventory.py working.pptx text-inventory.json
266 ```
267 * **Read text-inventory.json**: Read the entire text-inventory.json file to understand all shapes and their properties. **NEVER set any range limits when reading this file.**
268
269 * The inventory JSON structure:
270 ```json
271 {
272 "slide-0": {
273 "shape-0": {
274 "placeholder_type": "TITLE", // or null for non-placeholders
275 "left": 1.5, // position in inches
276 "top": 2.0,
277 "width": 7.5,
278 "height": 1.2,
279 "paragraphs": [
280 {
281 "text": "Paragraph text",
282 // Optional properties (only included when non-default):
283 "bullet": true, // explicit bullet detected
284 "level": 0, // only included when bullet is true
285 "alignment": "CENTER", // CENTER, RIGHT (not LEFT)
286 "space_before": 10.0, // space before paragraph in points
287 "space_after": 6.0, // space after paragraph in points
288 "line_spacing": 22.4, // line spacing in points
289 "font_name": "Arial", // from first run
290 "font_size": 14.0, // in points
291 "bold": true,
292 "italic": false,
293 "underline": false,
294 "color": "FF0000" // RGB color
295 }
296 ]
297 }
298 }
299 }
300 ```
301
302 * Key features:
303 - **Slides**: Named as "slide-0", "slide-1", etc.
304 - **Shapes**: Ordered by visual position (top-to-bottom, left-to-right) as "shape-0", "shape-1", etc.
305 - **Placeholder types**: TITLE, CENTER_TITLE, SUBTITLE, BODY, OBJECT, or null
306 - **Default font size**: `default_font_size` in points extracted from layout placeholders (when available)
307 - **Slide numbers are filtered**: Shapes with SLIDE_NUMBER placeholder type are automatically excluded from inventory
308 - **Bullets**: When `bullet: true`, `level` is always included (even if 0)
309 - **Spacing**: `space_before`, `space_after`, and `line_spacing` in points (only included when set)
310 - **Colors**: `color` for RGB (e.g., "FF0000"), `theme_color` for theme colors (e.g., "DARK_1")
311 - **Properties**: Only non-default values are included in the output
312
3136. **Generate replacement text and save the data to a JSON file**
314 Based on the text inventory from the previous step:
315 - **CRITICAL**: First verify which shapes exist in the inventory - only reference shapes that are actually present
316 - **VALIDATION**: The replace.py script will validate that all shapes in your replacement JSON exist in the inventory
317 - If you reference a non-existent shape, you'll get an error showing available shapes
318 - If you reference a non-existent slide, you'll get an error indicating the slide doesn't exist
319 - All validation errors are shown at once before the script exits
320 - **IMPORTANT**: The replace.py script uses inventory.py internally to identify ALL text shapes
321 - **AUTOMATIC CLEARING**: ALL text shapes from the inventory will be cleared unless you provide "paragraphs" for them
322 - Add a "paragraphs" field to shapes that need content (not "replacement_paragraphs")
323 - Shapes without "paragraphs" in the replacement JSON will have their text cleared automatically
324 - Paragraphs with bullets will be automatically left aligned. Don't set the `alignment` property on when `"bullet": true`
325 - Generate appropriate replacement content for placeholder text
326 - Use shape size to determine appropriate content length
327 - **CRITICAL**: Include paragraph properties from the original inventory - don't just provide text
328 - **IMPORTANT**: When bullet: true, do NOT include bullet symbols (•, -, *) in text - they're added automatically
329 - **ESSENTIAL FORMATTING RULES**:
330 - Headers/titles should typically have `"bold": true`
331 - List items should have `"bullet": true, "level": 0` (level is required when bullet is true)
332 - Preserve any alignment properties (e.g., `"alignment": "CENTER"` for centered text)
333 - Include font properties when different from default (e.g., `"font_size": 14.0`, `"font_name": "Lora"`)
334 - Colors: Use `"color": "FF0000"` for RGB or `"theme_color": "DARK_1"` for theme colors
335 - The replacement script expects **properly formatted paragraphs**, not just text strings
336 - **Overlapping shapes**: Prefer shapes with larger default_font_size or more appropriate placeholder_type
337 - Save the updated inventory with replacements to `replacement-text.json`
338 - **WARNING**: Different template layouts have different shape counts - always check the actual inventory before creating replacements
339
340 Example paragraphs field showing proper formatting:
341 ```json
342 "paragraphs": [
343 {
344 "text": "New presentation title text",
345 "alignment": "CENTER",
346 "bold": true
347 },
348 {
349 "text": "Section Header",
350 "bold": true
351 },
352 {
353 "text": "First bullet point without bullet symbol",
354 "bullet": true,
355 "level": 0
356 },
357 {
358 "text": "Red colored text",
359 "color": "FF0000"
360 },
361 {
362 "text": "Theme colored text",
363 "theme_color": "DARK_1"
364 },
365 {
366 "text": "Regular paragraph text without special formatting"
367 }
368 ]
369 ```
370
371 **Shapes not listed in the replacement JSON are automatically cleared**:
372 ```json
373 {
374 "slide-0": {
375 "shape-0": {
376 "paragraphs": [...] // This shape gets new text
377 }
378 // shape-1 and shape-2 from inventory will be cleared automatically
379 }
380 }
381 ```
382
383 **Common formatting patterns for presentations**:
384 - Title slides: Bold text, sometimes centered
385 - Section headers within slides: Bold text
386 - Bullet lists: Each item needs `"bullet": true, "level": 0`
387 - Body text: Usually no special properties needed
388 - Quotes: May have special alignment or font properties
389
3907. **Apply replacements using the `replace.py` script**
391 ```bash
392 uv run scripts/replace.py working.pptx replacement-text.json output.pptx
393 ```
394
395 The script will:
396 - First extract the inventory of ALL text shapes using functions from inventory.py
397 - Validate that all shapes in the replacement JSON exist in the inventory
398 - Clear text from ALL shapes identified in the inventory
399 - Apply new text only to shapes with "paragraphs" defined in the replacement JSON
400 - Preserve formatting by applying paragraph properties from the JSON
401 - Handle bullets, alignment, font properties, and colors automatically
402 - Save the updated presentation
403
404 Example validation errors:
405 ```
406 ERROR: Invalid shapes in replacement JSON:
407 - Shape 'shape-99' not found on 'slide-0'. Available shapes: shape-0, shape-1, shape-4
408 - Slide 'slide-999' not found in inventory
409 ```
410
411 ```
412 ERROR: Replacement text made overflow worse in these shapes:
413 - slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25")
414 ```
415
416## Creating Thumbnail Grids
417
418To create visual thumbnail grids of PowerPoint slides for quick analysis and reference:
419
420```bash
421uv run scripts/thumbnail.py template.pptx [output_prefix]
422```
423
424**Features**:
425- Creates: `thumbnails.jpg` (or `thumbnails-1.jpg`, `thumbnails-2.jpg`, etc. for large decks)
426- Default: 5 columns, max 30 slides per grid (5×6)
427- Custom prefix: `uv run scripts/thumbnail.py template.pptx my-grid`
428 - Note: The output prefix should include the path if you want output in a specific directory (e.g., `workspace/my-grid`)
429- Adjust columns: `--cols 4` (range: 3-6, affects slides per grid)
430- Grid limits: 3 cols = 12 slides/grid, 4 cols = 20, 5 cols = 30, 6 cols = 42
431- Slides are zero-indexed (Slide 0, Slide 1, etc.)
432
433**Use cases**:
434- Template analysis: Quickly understand slide layouts and design patterns
435- Content review: Visual overview of entire presentation
436- Navigation reference: Find specific slides by their visual appearance
437- Quality check: Verify all slides are properly formatted
438
439**Examples**:
440```bash
441# Basic usage
442uv run scripts/thumbnail.py presentation.pptx
443
444# Combine options: custom name, columns
445uv run scripts/thumbnail.py template.pptx analysis --cols 4
446```
447
448## Converting Slides to Images
449
450To visually analyze PowerPoint slides, convert them to images using a two-step process:
451
4521. **Convert PPTX to PDF**:
453 ```bash
454 soffice --headless --convert-to pdf template.pptx
455 ```
456
4572. **Convert PDF pages to JPEG images**:
458 ```bash
459 pdftoppm -jpeg -r 150 template.pdf slide
460 ```
461 This creates files like `slide-1.jpg`, `slide-2.jpg`, etc.
462
463Options:
464- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance)
465- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred)
466- `-f N`: First page to convert (e.g., `-f 2` starts from page 2)
467- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5)
468- `slide`: Prefix for output files
469
470Example for specific range:
471```bash
472pdftoppm -jpeg -r 150 -f 2 -l 5 template.pdf slide # Converts only pages 2-5
473```
474
475## Code Style Guidelines
476**IMPORTANT**: When generating code for PPTX operations:
477- Write concise code
478- Avoid verbose variable names and redundant operations
479- Avoid unnecessary print statements
480