PPTX creation, editing, and analysis

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"
4license: Proprietary. LICENSE.txt has complete terms
5---
6 
7# PPTX creation, editing, and analysis
8 
9## Overview
10 
11A 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.
12 
13## Reading and analyzing content
14 
15### Text extraction
16If you just need to read the text contents of a presentation, you should convert the document to markdown:
17 
18```bash
19# Convert document to markdown
20python -m markitdown path-to-file.pptx
21```
22 
23### Raw XML access
24You 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.
25 
26#### Unpacking a file
27`python ooxml/scripts/unpack.py <office_file> <output_dir>`
28 
29**Note**: The unpack.py script is located at `skills/pptx/ooxml/scripts/unpack.py` relative to the project root. If the script doesn't exist at this path, use `find . -name "unpack.py"` to locate it.
30 
31#### Key file structures
32* `ppt/presentation.xml` - Main presentation metadata and slide references
33* `ppt/slides/slide{N}.xml` - Individual slide contents (slide1.xml, slide2.xml, etc.)
34* `ppt/notesSlides/notesSlide{N}.xml` - Speaker notes for each slide
35* `ppt/comments/modernComment_*.xml` - Comments for specific slides
36* `ppt/slideLayouts/` - Layout templates for slides
37* `ppt/slideMasters/` - Master slide templates
38* `ppt/theme/` - Theme and styling information
39* `ppt/media/` - Images and other media files
40 
41#### Typography and color extraction
42**When given an example design to emulate**: Always analyze the presentation's typography and colors first using the methods below:
431. **Read theme file**: Check `ppt/theme/theme1.xml` for colors (`<a:clrScheme>`) and fonts (`<a:fontScheme>`)
442. **Sample slide content**: Examine `ppt/slides/slide1.xml` for actual font usage (`<a:rPr>`) and colors
453. **Search for patterns**: Use grep to find color (`<a:solidFill>`, `<a:srgbClr>`) and font references across all XML files
46 
47## Creating a new PowerPoint presentation **without a template**
48 
49When creating a new PowerPoint presentation from scratch, use the **html2pptx** workflow to convert HTML slides to PowerPoint with accurate positioning.
50 
51### Design Principles
52 
53**CRITICAL**: Before creating any presentation, analyze the content and choose appropriate design elements:
541. **Consider the subject matter**: What is this presentation about? What tone, industry, or mood does it suggest?
552. **Check for branding**: If the user mentions a company/organization, consider their brand colors and identity
563. **Match palette to content**: Select colors that reflect the subject
574. **State your approach**: Explain your design choices before writing code
58 
59**Requirements**:
60- ✅ State your content-informed design approach BEFORE writing code
61- ✅ Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact
62- ✅ Create clear visual hierarchy through size, weight, and color
63- ✅ Ensure readability: strong contrast, appropriately sized text, clean alignment
64- ✅ Be consistent: repeat patterns, spacing, and visual language across slides
65 
66#### Color Palette Selection
67 
68**Choosing colors creatively**:
69- **Think beyond defaults**: What colors genuinely match this specific topic? Avoid autopilot choices.
70- **Consider multiple angles**: Topic, industry, mood, energy level, target audience, brand identity (if mentioned)
71- **Be adventurous**: Try unexpected combinations - a healthcare presentation doesn't have to be green, finance doesn't have to be navy
72- **Build your palette**: Pick 3-5 colors that work together (dominant colors + supporting tones + accent)
73- **Ensure contrast**: Text must be clearly readable on backgrounds
74 
75**Example color palettes** (use these to spark creativity - choose one, adapt it, or create your own):
76 
771. **Classic Blue**: Deep navy (#1C2833), slate gray (#2E4053), silver (#AAB7B8), off-white (#F4F6F6)
782. **Teal & Coral**: Teal (#5EA8A7), deep teal (#277884), coral (#FE4447), white (#FFFFFF)
793. **Bold Red**: Red (#C0392B), bright red (#E74C3C), orange (#F39C12), yellow (#F1C40F), green (#2ECC71)
804. **Warm Blush**: Mauve (#A49393), blush (#EED6D3), rose (#E8B4B8), cream (#FAF7F2)
815. **Burgundy Luxury**: Burgundy (#5D1D2E), crimson (#951233), rust (#C15937), gold (#997929)
826. **Deep Purple & Emerald**: Purple (#B165FB), dark blue (#181B24), emerald (#40695B), white (#FFFFFF)
837. **Cream & Forest Green**: Cream (#FFE1C7), forest green (#40695B), white (#FCFCFC)
848. **Pink & Purple**: Pink (#F8275B), coral (#FF574A), rose (#FF737D), purple (#3D2F68)
859. **Lime & Plum**: Lime (#C5DE82), plum (#7C3A5F), coral (#FD8C6E), blue-gray (#98ACB5)
8610. **Black & Gold**: Gold (#BF9A4A), black (#000000), cream (#F4F6F6)
8711. **Sage & Terracotta**: Sage (#87A96B), terracotta (#E07A5F), cream (#F4F1DE), charcoal (#2C2C2C)
8812. **Charcoal & Red**: Charcoal (#292929), red (#E33737), light gray (#CCCBCB)
8913. **Vibrant Orange**: Orange (#F96D00), light gray (#F2F2F2), charcoal (#222831)
9014. **Forest Green**: Black (#191A19), green (#4E9F3D), dark green (#1E5128), white (#FFFFFF)
9115. **Retro Rainbow**: Purple (#722880), pink (#D72D51), orange (#EB5C18), amber (#F08800), gold (#DEB600)
9216. **Vintage Earthy**: Mustard (#E3B448), sage (#CBD18F), forest green (#3A6B35), cream (#F4F1DE)
9317. **Coastal Rose**: Old rose (#AD7670), beaver (#B49886), eggshell (#F3ECDC), ash gray (#BFD5BE)
9418. **Orange & Turquoise**: Light orange (#FC993E), grayish turquoise (#667C6F), white (#FCFCFC)
95 
96#### Visual Details Options
97 
98**Geometric Patterns**:
99- Diagonal section dividers instead of horizontal
100- Asymmetric column widths (30/70, 40/60, 25/75)
101- Rotated text headers at 90° or 270°
102- Circular/hexagonal frames for images
103- Triangular accent shapes in corners
104- Overlapping shapes for depth
105 
106**Border & Frame Treatments**:
107- Thick single-color borders (10-20pt) on one side only
108- Double-line borders with contrasting colors
109- Corner brackets instead of full frames
110- L-shaped borders (top+left or bottom+right)
111- Underline accents beneath headers (3-5pt thick)
112 
113**Typography Treatments**:
114- Extreme size contrast (72pt headlines vs 11pt body)
115- All-caps headers with wide letter spacing
116- Numbered sections in oversized display type
117- Monospace (Courier New) for data/stats/technical content
118- Condensed fonts (Arial Narrow) for dense information
119- Outlined text for emphasis
120 
121**Chart & Data Styling**:
122- Monochrome charts with single accent color for key data
123- Horizontal bar charts instead of vertical
124- Dot plots instead of bar charts
125- Minimal gridlines or none at all
126- Data labels directly on elements (no legends)
127- Oversized numbers for key metrics
128 
129**Layout Innovations**:
130- Full-bleed images with text overlays
131- Sidebar column (20-30% width) for navigation/context
132- Modular grid systems (3×3, 4×4 blocks)
133- Z-pattern or F-pattern content flow
134- Floating text boxes over colored shapes
135- Magazine-style multi-column layouts
136 
137**Background Treatments**:
138- Solid color blocks occupying 40-60% of slide
139- Gradient fills (vertical or diagonal only)
140- Split backgrounds (two colors, diagonal or vertical)
141- Edge-to-edge color bands
142- Negative space as a design element
143 
144### Layout Tips
145**When creating slides with charts or tables:**
146- **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.
147- **Full-slide layout**: Let the featured content (chart/table) take up the entire slide for maximum impact and readability
148- **NEVER vertically stack**: Do not place charts/tables below text in a single column - this causes poor readability and layout issues
149 
150### Workflow
1511. **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.
1522. Create an HTML file for each slide with proper dimensions (e.g., 720pt × 405pt for 16:9)
153   - Use `<p>`, `<h1>`-`<h6>`, `<ul>`, `<ol>` for all text content
154   - Use `class="placeholder"` for areas where charts/tables will be added (render with gray background for visibility)
155   - **CRITICAL**: Rasterize gradients and icons as PNG images FIRST using Sharp, then reference in HTML
156   - **LAYOUT**: For slides with charts/tables/images, use either full-slide layout or two-column layout for better readability
1573. Create and run a JavaScript file using the [`html2pptx.js`](scripts/html2pptx.js) library to convert HTML slides to PowerPoint and save the presentation
158   - Use the `html2pptx()` function to process each HTML file
159   - Add charts and tables to placeholder areas using PptxGenJS API
160   - Save the presentation using `pptx.writeFile()`
1614. **Visual validation**: Generate thumbnails and inspect for layout issues
162   - Create thumbnail grid: `python scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4`
163   - Read and carefully examine the thumbnail image for:
164     - **Text cutoff**: Text being cut off by header bars, shapes, or slide edges
165     - **Text overlap**: Text overlapping with other text or shapes
166     - **Positioning issues**: Content too close to slide boundaries or other elements
167     - **Contrast issues**: Insufficient contrast between text and backgrounds
168   - If issues found, adjust HTML margins/spacing/colors and regenerate the presentation
169   - Repeat until all slides are visually correct
170 
171## Editing an existing PowerPoint presentation
172 
173When 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.
174 
175### Workflow
1761. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~500 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.
1772. Unpack the presentation: `python ooxml/scripts/unpack.py <office_file> <output_dir>`
1783. Edit the XML files (primarily `ppt/slides/slide{N}.xml` and related files)
1794. **CRITICAL**: Validate immediately after each edit and fix any validation errors before proceeding: `python ooxml/scripts/validate.py <dir> --original <file>`
1805. Pack the final presentation: `python ooxml/scripts/pack.py <input_directory> <office_file>`
181 
182## Creating a new PowerPoint presentation **using a template**
183 
184When 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.
185 
186### Workflow
1871. **Extract template text AND create visual thumbnail grid**:
188   * Extract text: `python -m markitdown template.pptx > template-content.md`
189   * 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.**
190   * Create thumbnail grids: `python scripts/thumbnail.py template.pptx`
191   * See [Creating Thumbnail Grids](#creating-thumbnail-grids) section for more details
192 
1932. **Analyze template and save inventory to a file**:
194   * **Visual Analysis**: Review thumbnail grid(s) to understand slide layouts, design patterns, and visual structure
195   * Create and save a template inventory file at `template-inventory.md` containing:
196     ```markdown
197     # Template Inventory Analysis
198     **Total Slides: [count]**
199     **IMPORTANT: Slides are 0-indexed (first slide = 0, last slide = count-1)**
200 
201     ## [Category Name]
202     - Slide 0: [Layout code if available] - Description/purpose
203     - Slide 1: [Layout code] - Description/purpose
204     - Slide 2: [Layout code] - Description/purpose
205     [... EVERY slide must be listed individually with its index ...]
206     ```
207   * **Using the thumbnail grid**: Reference the visual thumbnails to identify:
208     - Layout patterns (title slides, content layouts, section dividers)
209     - Image placeholder locations and counts
210     - Design consistency across slide groups
211     - Visual hierarchy and structure
212   * This inventory file is REQUIRED for selecting appropriate templates in the next step
213 
2143. **Create presentation outline based on template inventory**:
215   * Review available templates from step 2.
216   * Choose an intro or title template for the first slide. This should be one of the first templates.
217   * Choose safe, text-based layouts for the other slides.
218   * **CRITICAL: Match layout structure to actual content**:
219     - Single-column layouts: Use for unified narrative or single topic
220     - Two-column layouts: Use ONLY when you have exactly 2 distinct items/concepts
221     - Three-column layouts: Use ONLY when you have exactly 3 distinct items/concepts
222     - Image + text layouts: Use ONLY when you have actual images to insert
223     - Quote layouts: Use ONLY for actual quotes from people (with attribution), never for emphasis
224     - Never use layouts with more placeholders than you have content
225     - If you have 2 items, don't force them into a 3-column layout
226     - If you have 4+ items, consider breaking into multiple slides or using a list format
227   * Count your actual content pieces BEFORE selecting the layout
228   * Verify each placeholder in the chosen layout will be filled with meaningful content
229   * Select one option representing the **best** layout for each content section.
230   * Save `outline.md` with content AND template mapping that leverages available designs
231   * Example template mapping:
232      ```
233      # Template slides to use (0-based indexing)
234      # WARNING: Verify indices are within range! Template with 73 slides has indices 0-72
235      # Mapping: slide numbers from outline -> template slide indices
236      template_mapping = [
237          0,   # Use slide 0 (Title/Cover)
238          34,  # Use slide 34 (B1: Title and body)
239          34,  # Use slide 34 again (duplicate for second B1)
240          50,  # Use slide 50 (E1: Quote)
241          54,  # Use slide 54 (F2: Closing + Text)
242      ]
243      ```
244 
2454. **Duplicate, reorder, and delete slides using `rearrange.py`**:
246   * Use the `scripts/rearrange.py` script to create a new presentation with slides in the desired order:
247     ```bash
248     python scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52
249     ```
250   * The script handles duplicating repeated slides, deleting unused slides, and reordering automatically
251   * Slide indices are 0-based (first slide is 0, second is 1, etc.)
252   * The same slide index can appear multiple times to duplicate that slide
253 
2545. **Extract ALL text using the `inventory.py` script**:
255   * **Run inventory extraction**:
256     ```bash
257     python scripts/inventory.py working.pptx text-inventory.json
258     ```
259   * **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.**
260 
261   * The inventory JSON structure:
262      ```json
263        {
264          "slide-0": {
265            "shape-0": {
266              "placeholder_type": "TITLE",  // or null for non-placeholders
267              "left": 1.5,                  // position in inches
268              "top": 2.0,
269              "width": 7.5,
270              "height": 1.2,
271              "paragraphs": [
272                {
273                  "text": "Paragraph text",
274                  // Optional properties (only included when non-default):
275                  "bullet": true,           // explicit bullet detected
276                  "level": 0,               // only included when bullet is true
277                  "alignment": "CENTER",    // CENTER, RIGHT (not LEFT)
278                  "space_before": 10.0,     // space before paragraph in points
279                  "space_after": 6.0,       // space after paragraph in points
280                  "line_spacing": 22.4,     // line spacing in points
281                  "font_name": "Arial",     // from first run
282                  "font_size": 14.0,        // in points
283                  "bold": true,
284                  "italic": false,
285                  "underline": false,
286                  "color": "FF0000"         // RGB color
287                }
288              ]
289            }
290          }
291        }
292      ```
293 
294   * Key features:
295     - **Slides**: Named as "slide-0", "slide-1", etc.
296     - **Shapes**: Ordered by visual position (top-to-bottom, left-to-right) as "shape-0", "shape-1", etc.
297     - **Placeholder types**: TITLE, CENTER_TITLE, SUBTITLE, BODY, OBJECT, or null
298     - **Default font size**: `default_font_size` in points extracted from layout placeholders (when available)
299     - **Slide numbers are filtered**: Shapes with SLIDE_NUMBER placeholder type are automatically excluded from inventory
300     - **Bullets**: When `bullet: true`, `level` is always included (even if 0)
301     - **Spacing**: `space_before`, `space_after`, and `line_spacing` in points (only included when set)
302     - **Colors**: `color` for RGB (e.g., "FF0000"), `theme_color` for theme colors (e.g., "DARK_1")
303     - **Properties**: Only non-default values are included in the output
304 
3056. **Generate replacement text and save the data to a JSON file**
306   Based on the text inventory from the previous step:
307   - **CRITICAL**: First verify which shapes exist in the inventory - only reference shapes that are actually present
308   - **VALIDATION**: The replace.py script will validate that all shapes in your replacement JSON exist in the inventory
309     - If you reference a non-existent shape, you'll get an error showing available shapes
310     - If you reference a non-existent slide, you'll get an error indicating the slide doesn't exist
311     - All validation errors are shown at once before the script exits
312   - **IMPORTANT**: The replace.py script uses inventory.py internally to identify ALL text shapes
313   - **AUTOMATIC CLEARING**: ALL text shapes from the inventory will be cleared unless you provide "paragraphs" for them
314   - Add a "paragraphs" field to shapes that need content (not "replacement_paragraphs")
315   - Shapes without "paragraphs" in the replacement JSON will have their text cleared automatically
316   - Paragraphs with bullets will be automatically left aligned. Don't set the `alignment` property on when `"bullet": true`
317   - Generate appropriate replacement content for placeholder text
318   - Use shape size to determine appropriate content length
319   - **CRITICAL**: Include paragraph properties from the original inventory - don't just provide text
320   - **IMPORTANT**: When bullet: true, do NOT include bullet symbols (•, -, *) in text - they're added automatically
321   - **ESSENTIAL FORMATTING RULES**:
322     - Headers/titles should typically have `"bold": true`
323     - List items should have `"bullet": true, "level": 0` (level is required when bullet is true)
324     - Preserve any alignment properties (e.g., `"alignment": "CENTER"` for centered text)
325     - Include font properties when different from default (e.g., `"font_size": 14.0`, `"font_name": "Lora"`)
326     - Colors: Use `"color": "FF0000"` for RGB or `"theme_color": "DARK_1"` for theme colors
327     - The replacement script expects **properly formatted paragraphs**, not just text strings
328     - **Overlapping shapes**: Prefer shapes with larger default_font_size or more appropriate placeholder_type
329   - Save the updated inventory with replacements to `replacement-text.json`
330   - **WARNING**: Different template layouts have different shape counts - always check the actual inventory before creating replacements
331 
332   Example paragraphs field showing proper formatting:
333   ```json
334   "paragraphs": [
335     {
336       "text": "New presentation title text",
337       "alignment": "CENTER",
338       "bold": true
339     },
340     {
341       "text": "Section Header",
342       "bold": true
343     },
344     {
345       "text": "First bullet point without bullet symbol",
346       "bullet": true,
347       "level": 0
348     },
349     {
350       "text": "Red colored text",
351       "color": "FF0000"
352     },
353     {
354       "text": "Theme colored text",
355       "theme_color": "DARK_1"
356     },
357     {
358       "text": "Regular paragraph text without special formatting"
359     }
360   ]
361   ```
362 
363   **Shapes not listed in the replacement JSON are automatically cleared**:
364   ```json
365   {
366     "slide-0": {
367       "shape-0": {
368         "paragraphs": [...] // This shape gets new text
369       }
370       // shape-1 and shape-2 from inventory will be cleared automatically
371     }
372   }
373   ```
374 
375   **Common formatting patterns for presentations**:
376   - Title slides: Bold text, sometimes centered
377   - Section headers within slides: Bold text
378   - Bullet lists: Each item needs `"bullet": true, "level": 0`
379   - Body text: Usually no special properties needed
380   - Quotes: May have special alignment or font properties
381 
3827. **Apply replacements using the `replace.py` script**
383   ```bash
384   python scripts/replace.py working.pptx replacement-text.json output.pptx
385   ```
386 
387   The script will:
388   - First extract the inventory of ALL text shapes using functions from inventory.py
389   - Validate that all shapes in the replacement JSON exist in the inventory
390   - Clear text from ALL shapes identified in the inventory
391   - Apply new text only to shapes with "paragraphs" defined in the replacement JSON
392   - Preserve formatting by applying paragraph properties from the JSON
393   - Handle bullets, alignment, font properties, and colors automatically
394   - Save the updated presentation
395 
396   Example validation errors:
397   ```
398   ERROR: Invalid shapes in replacement JSON:
399     - Shape 'shape-99' not found on 'slide-0'. Available shapes: shape-0, shape-1, shape-4
400     - Slide 'slide-999' not found in inventory
401   ```
402 
403   ```
404   ERROR: Replacement text made overflow worse in these shapes:
405     - slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25")
406   ```
407 
408## Creating Thumbnail Grids
409 
410To create visual thumbnail grids of PowerPoint slides for quick analysis and reference:
411 
412```bash
413python scripts/thumbnail.py template.pptx [output_prefix]
414```
415 
416**Features**:
417- Creates: `thumbnails.jpg` (or `thumbnails-1.jpg`, `thumbnails-2.jpg`, etc. for large decks)
418- Default: 5 columns, max 30 slides per grid (5×6)
419- Custom prefix: `python scripts/thumbnail.py template.pptx my-grid`
420  - Note: The output prefix should include the path if you want output in a specific directory (e.g., `workspace/my-grid`)
421- Adjust columns: `--cols 4` (range: 3-6, affects slides per grid)
422- Grid limits: 3 cols = 12 slides/grid, 4 cols = 20, 5 cols = 30, 6 cols = 42
423- Slides are zero-indexed (Slide 0, Slide 1, etc.)
424 
425**Use cases**:
426- Template analysis: Quickly understand slide layouts and design patterns
427- Content review: Visual overview of entire presentation
428- Navigation reference: Find specific slides by their visual appearance
429- Quality check: Verify all slides are properly formatted
430 
431**Examples**:
432```bash
433# Basic usage
434python scripts/thumbnail.py presentation.pptx
435 
436# Combine options: custom name, columns
437python scripts/thumbnail.py template.pptx analysis --cols 4
438```
439 
440## Converting Slides to Images
441 
442To visually analyze PowerPoint slides, convert them to images using a two-step process:
443 
4441. **Convert PPTX to PDF**:
445   ```bash
446   soffice --headless --convert-to pdf template.pptx
447   ```
448 
4492. **Convert PDF pages to JPEG images**:
450   ```bash
451   pdftoppm -jpeg -r 150 template.pdf slide
452   ```
453   This creates files like `slide-1.jpg`, `slide-2.jpg`, etc.
454 
455Options:
456- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance)
457- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred)
458- `-f N`: First page to convert (e.g., `-f 2` starts from page 2)
459- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5)
460- `slide`: Prefix for output files
461 
462Example for specific range:
463```bash
464pdftoppm -jpeg -r 150 -f 2 -l 5 template.pdf slide  # Converts only pages 2-5
465```
466 
467## Code Style Guidelines
468**IMPORTANT**: When generating code for PPTX operations:
469- Write concise code
470- Avoid verbose variable names and redundant operations
471- Avoid unnecessary print statements
472 
473## Dependencies
474 
475Required dependencies (should already be installed):
476 
477- **markitdown**: `pip install "markitdown[pptx]"` (for text extraction from presentations)
478- **pptxgenjs**: `npm install -g pptxgenjs` (for creating presentations via html2pptx)
479- **playwright**: `npm install -g playwright` (for HTML rendering in html2pptx)
480- **react-icons**: `npm install -g react-icons react react-dom` (for icons)
481- **sharp**: `npm install -g sharp` (for SVG rasterization and image processing)
482- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion)
483- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images)
484- **defusedxml**: `pip install defusedxml` (for secure XML parsing)