### Setup and Export DOCX

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/docx-js.md

Imports necessary components from the docx library and shows how to create a document buffer for Node.js or a blob for browser downloads. Assumes the docx library is installed globally.

```javascript
const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun, Media, 
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink, 
        InternalHyperlink, TableOfContents, HeadingLevel, BorderStyle, WidthType, TabStopType, 
        TabStopPosition, UnderlineType, ShadingType, VerticalAlign, SymbolRun, PageNumber,
        FootnoteReferenceRun, Footnote, PageBreak } = require('docx');

// Create & Save
const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); // Node.js
Packer.toBlob(doc).then(blob => { /* download logic */ }); // Browser
```

--------------------------------

### Complete html2pptx and PptxGenJS Example

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

A full example showing the initialization of pptxgen, conversion of multiple HTML slides using html2pptx, adding a chart to a placeholder, and saving the presentation.

```javascript
const pptxgen = require('pptxgenjs');
const html2pptx = require('./html2pptx');

async function createPresentation() {
    const pptx = new pptxgen();
    pptx.layout = 'LAYOUT_16x9';
    pptx.author = 'Your Name';
    pptx.title = 'My Presentation';

    // Slide 1: Title
    const { slide: slide1 } = await html2pptx('slides/title.html', pptx);

    // Slide 2: Content with chart
    const { slide: slide2, placeholders } = await html2pptx('slides/data.html', pptx);

    const chartData = [{
        name: 'Sales',
        labels: ['Q1', 'Q2', 'Q3', 'Q4'],
        values: [4500, 5500, 6200, 7100]
    }];

    slide2.addChart(pptx.charts.BAR, chartData, {
        ...placeholders[0],
        showTitle: true,
        title: 'Quarterly Sales',
        showCatAxisTitle: true,
        catAxisTitle: 'Quarter',
        showValAxisTitle: true,
        valAxisTitle: 'Sales ($000s)'
    });

    // Save
    await pptx.writeFile({ fileName: 'presentation.pptx' });
    console.log('Presentation created successfully!');
}

createPresentation().catch(console.error);
```

--------------------------------

### Install Python and Node.js Dependencies

Source: https://github.com/tfriedel/claude-office-skills/blob/main/README.md

Install necessary Python and Node.js packages for the Office document skills. Ensure system tools like LibreOffice, Poppler, and Pandoc are also available.

```bash
# Python dependencies
virtualenv/bin/pip install -r requirements.txt

# Node.js dependencies (for html2pptx)
npm install

# System tools (usually pre-installed)
# - LibreOffice (soffice)
# - Poppler (pdftoppm)
# - Pandoc
```

--------------------------------

### OOXML Text Formatting Examples

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/ooxml.md

Demonstrates how to apply bold, italic, underline, and highlight formatting to text within a run.

```xml
<!-- Bold -->
<w:r><w:rPr><w:b/><w:bCs/></w:rPr><w:t>Bold</w:t></w:r>
<!-- Italic -->
<w:r><w:rPr><w:i/><w:iCs/></w:rPr><w:t>Italic</w:t></w:r>
<!-- Underline -->
<w:r><w:rPr><w:u w:val="single"/></w:rPr><w:t>Underlined</w:t></w:r>
<!-- Highlight -->
<w:r><w:rPr><w:highlight w:val="yellow"/></w:rPr><w:t>Highlighted</w:t></w:r>
```

--------------------------------

### Example: Create Presentation from Template

Source: https://github.com/tfriedel/claude-office-skills/blob/main/README.md

Demonstrates a two-step process for creating a presentation from a template using command-line scripts. First, extract template text, then generate thumbnails for review.

```bash
# 1. Extract template text
virtualenv/bin/python -m markitdown template.pptx

# 2. Generate thumbnails
virtualenv/bin/python public/pptx/scripts/thumbnail.py template.pptx outputs/sales-deck/thumbnails
```

--------------------------------

### Application Properties in OOXML

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/ooxml.md

Example of `app.xml` content showing slide count and basic statistics for the presentation.

```xml
<Slides>2</Slides>
<Paragraphs>10</Paragraphs>
<Words>50</Words>
```

--------------------------------

### Install Node.js Dependencies

Source: https://github.com/tfriedel/claude-office-skills/blob/main/CLAUDE.md

Install Node.js dependencies, including the Playwright Chromium browser, for JavaScript-based workflows like html2pptx.

```bash
npm install
```

--------------------------------

### Text Formatting: Complete Example XML

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/ooxml.md

A comprehensive example of text formatting, including language, size, bold attribute, and a light gray color fill. Includes the 'dirty="0"' attribute for clean state.

```xml
<a:r>
  <a:rPr lang="en-US" sz="1400" b="1" dirty="0">
    <a:solidFill>
      <a:srgbClr val="FAFAFA"/>
    </a:solidFill>
  </a:rPr>
  <a:t>Formatted text</a:t>
</a:r>
```

--------------------------------

### Basic PDF Creation with reportlab

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/SKILL.md

Create a simple PDF document with text and a line using the reportlab library. This is a foundational example for PDF generation.

```python
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

# Save
c.save()
```

--------------------------------

### Convert HTML to PPTX

Source: https://github.com/tfriedel/claude-office-skills/blob/main/CLAUDE.md

Converts HTML files into a PowerPoint presentation using the html2pptx.js library. Requires Node.js to be installed.

```bash
node script.js  # Uses html2pptx.js library
```

--------------------------------

### Configure Document with Headers, Footers, and Page Setup

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/docx-js.md

Set up a new document with custom page margins, landscape orientation, and page numbering. Includes default headers and footers with current and total page numbers.

```javascript
const doc = new Document({
  sections: [{
    properties: {
      page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 }, // 1440 = 1 inch
        size: { orientation: PageOrientation.LANDSCAPE },
        pageNumbers: { start: 1, formatType: "decimal" } // "upperRoman", "lowerRoman", "upperLetter", "lowerLetter"
      }
    },
    headers: {
      default: new Header({ children: [new Paragraph({
        alignment: AlignmentType.RIGHT,
        children: [new TextRun("Header Text")]
      })] })
    },
    footers: {
      default: new Footer({ children: [new Paragraph({
        alignment: AlignmentType.CENTER,
        children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] }), new TextRun(" of "), new TextRun({ children: [PageNumber.TOTAL_PAGES] })]
      })] })
    },
    children: [/* content */]
  }]
});
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/tfriedel/claude-office-skills/blob/main/CLAUDE.md

Install or update Python dependencies required for the repository's scripts. Always use the venv/bin/pip command.

```bash
venv/bin/pip install -r requirements.txt
```

--------------------------------

### HTML Slide Template for html2pptx

Source: https://context7.com/tfriedel/claude-office-skills/llms.txt

This is an example HTML structure for creating slides compatible with the `html2pptx` utility. Ensure the body dimensions match the `pptx.layout` setting and use `div.placeholder` for chart/table injection areas. Note the comment regarding `<br>` usage.

```html
<!DOCTYPE html>
<html>
<head>
<style>
body { width: 720pt; height: 405pt; margin: 0; display: flex;
       background: #1C2833; font-family: Arial, sans-serif; }
.sidebar { width: 30%; background: #2E4053; padding: 30pt; }
.main { flex: 1; padding: 30pt; }
h1 { color: #F4F6F6; font-size: 28pt; }
</style>
</head>
<body>
  <div class="sidebar">
    <h1>Q3<br>2024</h1>          <!-- WRONG: use separate <p> tags, not <br> -->
  </div>
  <div class="main">
    <h1>Sales Results</h1>
    <ul>
      <li><b>Revenue:</b> $7.4M</li>
      <li><b>Growth:</b> +18% YoY</li>
    </ul>
    <!-- Placeholder for chart injection -->
    <div id="revenue-chart" class="placeholder" style="width: 380pt; height: 220pt;"></div>
  </div>
</body>
</html>
```

--------------------------------

### Template Inventory Structure

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

This is an example structure for a template inventory Markdown file. It should list all slides with their index, layout code, and a description.

```markdown
# 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 ...]
```

--------------------------------

### Compare DOCX Tracked Changes

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/SKILL.md

Demonstrates how tracked changes are represented in XML. The 'GOOD' example shows a more granular approach to marking changes compared to the 'BAD' example which replaces an entire sentence.

```xml
<w:del><w:r><w:delText>The term is 30 days.</w:delText></w:r></w:del><w:ins><w:r><w:t>The term is 60 days.</w:t></w:r></w:ins>
```

```xml
<w:r w:rsidR="00AB12CD"><w:t>The term is </w:t></w:r><w:del><w:r><w:delText>30</w:delText></w:r></w:del><w:ins><w:r><w:t>60</w:t></w:r></w:ins><w:r w:rsidR="00AB12CD"><w:t> days.</w:t></w:r>
```

--------------------------------

### Relationship Definitions in OOXML

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/ooxml.md

Shows example relationship definitions in `presentation.xml.rels` and `slide1.xml.rels` for linking slides, masters, and media files.

```xml
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>
<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slideMaster" Target="slideMasters/slideMaster1.xml"/>
```

```xml
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slideLayout" Target="../slideLayouts/slideLayout1.xml"/>
<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="../media/image1.png"/>
```

--------------------------------

### Shape Replacement Structure Example

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

Demonstrates the JSON structure for specifying text replacements for shapes within a presentation. Shapes not included in this structure will have their text automatically cleared.

```json
{
  "slide-0": {
    "shape-0": {
      "paragraphs": [
        // Paragraph objects go here
      ]
    }
    // Other shapes on slide-0 will be cleared
  }
}
```

--------------------------------

### Paragraph Formatting Example

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

Illustrates the structure for defining paragraphs with various formatting options like text, alignment, bolding, bullets, color, and theme color. Use this structure when providing content for shapes.

```json
{
  "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"
    }
  ]
}
```

--------------------------------

### Convert PPTX to Markdown

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

Use this command to extract text content from a .pptx file into a markdown format for easier reading and analysis. Ensure markitdown is installed.

```bash
python -m markitdown path-to-file.pptx
```

--------------------------------

### Create DOCX Document with JavaScript

Source: https://context7.com/tfriedel/claude-office-skills/llms.txt

Uses the 'docx' npm package to generate .docx files from JavaScript. Supports rich formatting, tables, lists, headers, footers, and page numbering. Ensure the 'docx' package is installed.

```javascript
const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell,
        Header, Footer, AlignmentType, HeadingLevel, LevelFormat, BorderStyle,
        WidthType, ShadingType, VerticalAlign, PageNumber, ImageRun } = require('docx');
const fs = require('fs');

const tableBorder = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const cellBorders = { top: tableBorder, bottom: tableBorder, left: tableBorder, right: tableBorder };

const doc = new Document({
    styles: {
        default: { document: { run: { font: "Arial", size: 24 } } },
        paragraphStyles: [
            { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal",
              run: { size: 32, bold: true, color: "000000" },
              paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }
        ]
    },
    numbering: {
        config: [{
            reference: "bullet-list",
            levels: [{
                level: 0, format: LevelFormat.BULLET, text: "•",
                alignment: AlignmentType.LEFT,
                style: { paragraph: { indent: { left: 720, hanging: 360 } } }
            }]
        }]
    },
    sections: [{
        properties: {
            page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } }
        },
        headers: {
            default: new Header({ children: [
                new Paragraph({ alignment: AlignmentType.RIGHT,
                    children: [new TextRun("Company Confidential")] })
            ]})
        },
        footers: {
            default: new Footer({ children: [
                new Paragraph({ alignment: AlignmentType.CENTER, children: [
                    new TextRun("Page "),
                    new TextRun({ children: [PageNumber.CURRENT] }),
                    new TextRun(" of "),
                    new TextRun({ children: [PageNumber.TOTAL_PAGES] })
                ]})
            ]})
        },
        children: [
            new Paragraph({ heading: HeadingLevel.HEADING_1,
                children: [new TextRun("Executive Summary")] }),
            new Paragraph({ children: [new TextRun("Revenue increased 22% in FY2024.")] }),
            new Paragraph({ numbering: { reference: "bullet-list", level: 0 },
                children: [new TextRun("North America: +18%")] }),
            new Paragraph({ numbering: { reference: "bullet-list", level: 0 },
                children: [new TextRun("EMEA: +31%")] }),
            new Table({
                columnWidths: [4680, 4680],
                margins: { top: 100, bottom: 100, left: 180, right: 180 },
                rows: [
                    new TableRow({ tableHeader: true, children: [
                        new TableCell({ borders: cellBorders, width: { size: 4680, type: WidthType.DXA },
                            shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
                            children: [new Paragraph({ alignment: AlignmentType.CENTER,
                                children: [new TextRun({ text: "Region", bold: true })] })]
                        }),
                        new TableCell({ borders: cellBorders, width: { size: 4680, type: WidthType.DXA },
                            shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
                            children: [new Paragraph({ alignment: AlignmentType.CENTER,
                                children: [new TextRun({ text: "Growth", bold: true })] })]
                        })
                    ]}),
                    new TableRow({ children: [
                        new TableCell({ borders: cellBorders, width: { size: 4680, type: WidthType.DXA },
                            children: [new Paragraph({ children: [new TextRun("North America")] })]
                        }),
                        new TableCell({ borders: cellBorders, width: { size: 4680, type: WidthType.DXA },
                            children: [new Paragraph({ children: [new TextRun("+18%")] })]
                        })
                    ]})
                ]
            })
        ]
    }]
});

Packer.toBuffer(doc).then(buf => fs.writeFileSync("outputs/report/report.docx", buf));
```

--------------------------------

### Initialize and Use html2pptx

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

This snippet demonstrates the basic usage of the html2pptx library. It initializes a pptxgenjs presentation, sets the layout, converts an HTML file to a slide, and optionally adds a chart to a placeholder. Finally, it writes the presentation to a file.

```javascript
const pptxgen = require('pptxgenjs');
const html2pptx = require('./html2pptx');

const pptx = new pptxgen();
pptx.layout = 'LAYOUT_16x9';  // Must match HTML body dimensions

const { slide, placeholders } = await html2pptx('slide1.html', pptx);

// Add chart to placeholder area
if (placeholders.length > 0) {
    slide.addChart(pptx.charts.LINE, chartData, placeholders[0]);
}

await pptx.writeFile('output.pptx');
```

--------------------------------

### Python Document Class Initialization

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/ooxml.md

Demonstrates various ways to initialize the Document class, including specifying author, initials, track revisions, and custom RSID.

```python
# Adjust import path or run with: PYTHONPATH=/path/to/skill python script.py
# e.g: from skills.docx.scripts.document import Document, DocxXMLEditor
from ... import Document, DocxXMLEditor

# Basic initialization (automatically creates temp copy and sets up infrastructure)
doc = Document('unpacked')

# Customize author and initials
doc = Document('unpacked', author="John Doe", initials="JD")

# Enable track revisions mode
doc = Document('unpacked', track_revisions=True)

# Specify custom RSID (auto-generated if not provided)
doc = Document('unpacked', rsid="07DC5ECB")
```

--------------------------------

### Create New Excel File with Formulas and Formatting

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/xlsx/SKILL.md

Demonstrates creating a new Excel workbook using openpyxl, adding data, formulas, and applying basic formatting like bold text, background color, and alignment. Column width can also be adjusted.

```python
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment

wb = Workbook()
sheet = wb.active

# Add data
sheet['A1'] = 'Hello'
sheet['B1'] = 'World'
sheet.append(['Row', 'of', 'data'])

# Add formula
sheet['B2'] = '=SUM(A1:A10)'

# Formatting
sheet['A1'].font = Font(bold=True, color='FF0000')
sheet['A1'].fill = PatternFill('solid', start_color='FFFF00')
sheet['A1'].alignment = Alignment(horizontal='center')

# Column width
sheet.column_dimensions['A'].width = 20

wb.save('output.xlsx')
```

--------------------------------

### Text Inventory JSON Structure

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

This is an example structure of the JSON output from the text inventory script. It details shapes, their properties, and paragraph content on each slide.

```json
{
  "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

```

--------------------------------

### Create a Table with Borders and Headers

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/docx-js.md

Constructs a table with specified column widths, margins, borders, and header styling. Ensure column widths are set at both the table and cell levels. Use ShadingType.CLEAR to avoid unexpected background colors.

```javascript
const tableBorder = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const cellBorders = { top: tableBorder, bottom: tableBorder, left: tableBorder, right: tableBorder };

new Table({
  columnWidths: [4680, 4680], // ⚠️ CRITICAL: Set column widths at table level - values in DXA (twentieths of a point)
  margins: { top: 100, bottom: 100, left: 180, right: 180 }, // Set once for all cells
  rows: [
    new TableRow({
      tableHeader: true,
      children: [
        new TableCell({
          borders: cellBorders,
          width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
          // ⚠️ CRITICAL: Always use ShadingType.CLEAR to prevent black backgrounds in Word.
          shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, 
          verticalAlign: VerticalAlign.CENTER,
          children: [new Paragraph({ 
            alignment: AlignmentType.CENTER,
            children: [new TextRun({ text: "Header", bold: true, size: 22 })]
          })]
        }),
        new TableCell({
          borders: cellBorders,
          width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
          shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
          children: [new Paragraph({ 
            alignment: AlignmentType.CENTER,
            children: [new TextRun({ text: "Bullet Points", bold: true, size: 22 })]
          })]
        })
      ]
    }),
    new TableRow({
      children: [
        new TableCell({
          borders: cellBorders,
          width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
          children: [new Paragraph({ children: [new TextRun("Regular data")] })]
        }),
        new TableCell({
          borders: cellBorders,
          width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
          children: [
            new Paragraph({ 
              numbering: { reference: "bullet-list", level: 0 },
              children: [new TextRun("First bullet point")] 
            }),
            new Paragraph({ 
              numbering: { reference: "bullet-list", level: 0 },
              children: [new TextRun("Second bullet point")] 
            })
          ]
        })
      ]
    })
  ]
})
```

--------------------------------

### Create Complex PDFs from Scratch with pdf-lib

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/REFERENCE.md

Generate a new PDF document from scratch using pdf-lib. Embed standard fonts, add text with styling, draw shapes like rectangles, and create table-like structures.

```javascript
import { PDFDocument, rgb, StandardFonts } from 'pdf-lib';
import fs from 'fs';

async function createPDF() {
    const pdfDoc = await PDFDocument.create();

    // Add fonts
    const helveticaFont = await pdfDoc.embedFont(StandardFonts.Helvetica);
    const helveticaBold = await pdfDoc.embedFont(StandardFonts.HelveticaBold);

    // Add page
    const page = pdfDoc.addPage([595, 842]); // A4 size
    const { width, height } = page.getSize();

    // Add text with styling
    page.drawText('Invoice #12345', {
        x: 50,
        y: height - 50,
        size: 18,
        font: helveticaBold,
        color: rgb(0.2, 0.2, 0.8)
    });

    // Add rectangle (header background)
    page.drawRectangle({
        x: 40,
        y: height - 100,
        width: width - 80,
        height: 30,
        color: rgb(0.9, 0.9, 0.9)
    });

    // Add table-like content
    const items = [
        ['Item', 'Qty', 'Price', 'Total'],
        ['Widget', '2', '$50', '$100'],
        ['Gadget', '1', '$75', '$75']
    ];

    let yPos = height - 150;
    items.forEach(row => {
        let xPos = 50;
        row.forEach(cell => {
            page.drawText(cell, {
                x: xPos,
                y: yPos,
                size: 12,
                font: helveticaFont
            });
            xPos += 120;
        });
        yPos -= 25;
    });

    const pdfBytes = await pdfDoc.save();
    fs.writeFileSync('created.pdf', pdfBytes);
}
```

--------------------------------

### Advanced Table Extraction to Excel with pdfplumber and pandas

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/SKILL.md

Extract all tables from a PDF, convert them into pandas DataFrames, and combine them into a single Excel file. Requires pandas to be installed.

```python
import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # Check if table is not empty
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combine all tables
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)
```

--------------------------------

### html2pptx Basic Usage

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

Demonstrates the basic workflow for converting an HTML file into a PowerPoint slide using the html2pptx library and pptxgenjs.

```APIDOC
## Basic Usage of html2pptx

### Description
This example shows how to initialize a PptxGenJS presentation, convert an HTML file into a slide using `html2pptx`, and potentially add other elements like charts to the generated slide.

### Code Example
```javascript
const pptxgen = require('pptxgenjs');
const html2pptx = require('./html2pptx');

async function convertHtmlToPpt() {
  const pptx = new pptxgen();
  pptx.layout = 'LAYOUT_16x9';  // Must match HTML body dimensions

  // Convert HTML file to a slide
  const { slide, placeholders } = await html2pptx('slide1.html', pptx);

  // Example: Add a chart to the first placeholder if available
  if (placeholders.length > 0) {
    // Assuming chartData is defined elsewhere
    // const chartData = [...]; 
    // slide.addChart(pptx.charts.LINE, chartData, placeholders[0]);
  }

  await pptx.writeFile('output.pptx');
  console.log('Presentation saved as output.pptx');
}

convertHtmlToPpt().catch(console.error);
```
```

--------------------------------

### Basic HTML Structure for Conversion

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

This is a sample HTML document structure. Ensure that the HTML body dimensions match the presentation layout set in pptxgenjs for accurate conversion. Avoid CSS gradients as they are not supported.

```html
<!DOCTYPE html>
<html>
<head>
<style>
html { background: #ffffff; }
body {
  width: 720pt; height: 405pt; margin: 0; padding: 0;
  background: #f5f5f5; font-family: Arial, sans-serif;
  display: flex;
}
.content { margin: 30pt; padding: 40pt; background: #ffffff; border-radius: 8pt; }
h1 { color: #2d3748; font-size: 32pt; }
.box {
  background: #70ad47; padding: 20pt; border: 3px solid #5a8f37;
  border-radius: 12pt; box-shadow: 3px 3px 10px rgba(0, 0, 0, 0.25);
}
</style>
</head>
<body>
<div class="content">
  <h1>Recipe Title</h1>
  <ul>
    <li><b>Item:</b> Description</li>
  </ul>
  <p>Text with <b>bold</b>, <i>italic</i>, <u>underline</u>.</p>
  <div id="chart" class="placeholder" style="width: 350pt; height: 200pt;"></div>

  <!-- Text MUST be in <p> tags -->
  <div class="box">
    <p>5</p>
  </div>
</div>
</body>
</html>
```

--------------------------------

### PDF Form Field Values JSON

Source: https://context7.com/tfriedel/claude-office-skills/llms.txt

Example JSON structure for defining values to be filled into PDF form fields. Each object maps a field ID to its desired value.

```json
// outputs/form/field_values.json
[
  { "field_id": "last_name",   "description": "Applicant last name",  "page": 1, "value": "Smith"  },
  { "field_id": "first_name",  "description": "Applicant first name", "page": 1, "value": "Jane"   },
  { "field_id": "Checkbox12",  "description": "US citizen checkbox",  "page": 1, "value": "/On"    },
  { "field_id": "state_select","description": "State of residence",   "page": 2, "value": "CA"     }
]
```

--------------------------------

### Create PPTX Thumbnail Grid

Source: https://github.com/tfriedel/claude-office-skills/blob/main/CLAUDE.md

Generates a grid of thumbnails from a PPTX file for visual analysis. The number of columns can be specified.

```bash
venv/bin/python public/pptx/scripts/thumbnail.py template.pptx outputs/<document-name>/thumbnails [--cols 4]
```

--------------------------------

### OCR Scanned PDFs with pytesseract

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/SKILL.md

Use this to extract text from scanned PDF documents. Requires `pytesseract` and `pdf2image` to be installed. The PDF is first converted to images, and then OCR is applied to each image.

```python
import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path('scanned.pdf')

# OCR each page
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)
```

--------------------------------

### Create Thumbnail Grids

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

Generate a visual thumbnail grid for a PowerPoint template to aid in analyzing slide layouts and design patterns.

```bash
python scripts/thumbnail.py template.pptx
```

--------------------------------

### Basic Text Formatting

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/docx-js.md

Demonstrates how to create paragraphs with various text formatting options. It is crucial to use separate Paragraph elements for line breaks, not '\n' within TextRun.

```javascript
// IMPORTANT: Never use \n for line breaks - always use separate Paragraph elements
// ❌ WRONG: new TextRun("Line 1\nLine 2")
// ✅ CORRECT: new Paragraph({ children: [new TextRun("Line 1")] }), new Paragraph({ children: [new TextRun("Line 2")] })

// Basic text with all formatting options
new Paragraph({
  alignment: AlignmentType.CENTER,
  spacing: { before: 200, after: 200 },
  indent: { left: 720, right: 720 },
  children: [
    new TextRun({ text: "Bold", bold: true }),
    new TextRun({ text: "Italic", italics: true }),
    new TextRun({ text: "Underlined", underline: { type: UnderlineType.DOUBLE, color: "FF0000" } }),
    new TextRun({ text: "Colored", color: "FF0000", size: 28, font: "Arial" }), // Arial default
    new TextRun({ text: "Highlighted", highlight: "yellow" }),
    new TextRun({ text: "Strikethrough", strike: true }),
    new TextRun({ text: "x2", superScript: true }),
    new TextRun({ text: "H2O", subScript: true }),
    new TextRun({ text: "SMALL CAPS", smallCaps: true }),
    new SymbolRun({ char: "2022", font: "Symbol" }), // Bullet •
    new SymbolRun({ char: "00A9", font: "Arial" })   // Copyright © - Arial for symbols
  ]
})
```

--------------------------------

### Example Validation Error: Overflow Worsened

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

This error message highlights shapes where the replacement text caused an overflow issue to worsen. Check the text content and formatting for affected shapes.

```bash
ERROR: Replacement text made overflow worse in these shapes:
  - slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25")
```

--------------------------------

### Example Validation Error: Invalid Shapes

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

This error message indicates that shapes specified in the replacement JSON were not found in the presentation's inventory. Verify shape names and slide numbers.

```bash
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
```

--------------------------------

### Replace Node with Tracked Changes

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/ooxml.md

Use replace_node() to modify text within tracked changes. This example shows changing a single word, a number, or completely replacing text while preserving formatting.

```python
# Minimal edit - change one word: "The report is monthly" → "The report is quarterly"
# Original: <w:r w:rsidR="00AB12CD"><w:rPr><w:rFonts w:ascii="Calibri"/></w:rPr><w:t>The report is monthly</w:t></w:r>
node = doc["word/document.xml"].get_node(tag="w:r", contains="The report is monthly")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:r w:rsidR="00AB12CD">{rpr}<w:t>The report is </w:t></w:r><w:del><w:r>{rpr}<w:delText>monthly</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>quarterly</w:t></w:r></w:ins>'
doc["word/document.xml"].replace_node(node, replacement)
```

```python
# Minimal edit - change number: "within 30 days" → "within 45 days"
# Original: <w:r w:rsidR="00XYZ789"><w:rPr><w:rFonts w:ascii="Calibri"/></w:rPr><w:t>within 30 days</w:t></w:r>
node = doc["word/document.xml"].get_node(tag="w:r", contains="within 30 days")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:r w:rsidR="00XYZ789">{rpr}<w:t>within </w:t></w:r><w:del><w:r>{rpr}<w:delText>30</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>45</w:t></w:r></w:ins><w:r w:rsidR="00XYZ789">{rpr}<w:t> days</w:t></w:r>'
doc["word/document.xml"].replace_node(node, replacement)
```

```python
# Complete replacement - preserve formatting even when replacing all text
node = doc["word/document.xml"].get_node(tag="w:r", contains="apple")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:del><w:r>{rpr}<w:delText>apple</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>banana orange</w:t></w:r></w:ins>'
doc["word/document.xml"].replace_node(node, replacement)
```

--------------------------------

### OOXML Headings and Styles

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/ooxml.md

Shows how to apply styles like 'Title' and 'Heading2' to paragraphs, along with text alignment.

```xml
<w:p>
  <w:pPr>
    <w:pStyle w:val="Title"/>
    <w:jc w:val="center"/>
  </w:pPr>
  <w:r><w:t>Document Title</w:t></w:r>
</w:p>

<w:p>
  <w:pPr><w:pStyle w:val="Heading2"/></w:pPr>
  <w:r><w:t>Section Heading</w:t></w:r>
</w:p>
```

--------------------------------

### Add Basic Table

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

Create a simple table with specified dimensions and basic formatting for borders and fill color.

```javascript
slide.addTable([
    ["Header 1", "Header 2", "Header 3"],
    ["Row 1, Col 1", "Row 1, Col 2", "Row 1, Col 3"],
    ["Row 2, Col 1", "Row 2, Col 2", "Row 2, Col 3"]
], {
    x: 0.5,
    y: 1,
    w: 9,
    h: 3,
    border: { pt: 1, color: "999999" },
    fill: { color: "F1F1F1" }
});
```

--------------------------------

### Adding Shapes to a Slide

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/html2pptx.md

Provides examples of adding different types of shapes (rectangle, circle, rounded rectangle) to a PptxGenJS slide, including options for fill color, line style, and corner radius.

```javascript
// Rectangle
slide.addShape(pptx.shapes.RECTANGLE, {
    x: 1, y: 1, w: 3, h: 2,
    fill: { color: "4472C4" },
    line: { color: "000000", width: 2 }
});

// Circle
slide.addShape(pptx.shapes.OVAL, {
    x: 5, y: 1, w: 2, h: 2,
    fill: { color: "ED7D31" }
});

// Rounded rectangle
slide.addShape(pptx.shapes.ROUNDED_RECTANGLE, {
    x: 1, y: 4, w: 3, h: 1.5,
    fill: { color: "70AD47" },
    rectRadius: 0.2
});
```

--------------------------------

### Convert PPTX to PDF then to Images using LibreOffice and Poppler

Source: https://context7.com/tfriedel/claude-office-skills/llms.txt

This two-step process converts PPTX slides to images. First, use headless LibreOffice (`soffice`) to convert PPTX to PDF. Second, use `pdftoppm` from Poppler to convert the PDF pages into JPEG images at a specified resolution (e.g., 150 DPI).

```bash
# Step 1: PPTX → PDF (headless LibreOffice)
soffice --headless --convert-to pdf --outdir outputs/my-deck/ outputs/my-deck/final.pptx
# Output: outputs/my-deck/final.pdf

# Step 2: PDF → JPEG images (150 DPI)
pdftoppm -jpeg -r 150 outputs/my-deck/final.pdf outputs/my-deck/slide
# Output: outputs/my-deck/slide-1.jpg, slide-2.jpg, ...

# Specific page range only (e.g., slides 3–7)
pdftoppm -jpeg -r 150 -f 3 -l 7 outputs/my-deck/final.pdf outputs/my-deck/slide
```

--------------------------------

### Get OOXML Nodes by Criteria

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/docx/ooxml.md

Retrieves specific nodes from an OOXML document based on tag name and various filtering criteria. Use line number ranges for disambiguation when text appears multiple times.

```python
# By text content
node = doc["word/document.xml"].get_node(tag="w:p", contains="specific text")

# By line range
para = doc["word/document.xml"].get_node(tag="w:p", line_number=range(100, 150))

# By attributes
node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"})

# By exact line number (must be line number where tag opens)
para = doc["word/document.xml"].get_node(tag="w:p", line_number=42)

# Combine filters
node = doc["word/document.xml"].get_node(tag="w:r", line_number=range(40, 60), contains="text")

# Disambiguate when text appears multiple times - add line_number range
node = doc["word/document.xml"].get_node(tag="w:r", contains="Section", line_number=range(2400, 2500))
```

--------------------------------

### Generate Thumbnail Grids from PPTX

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/SKILL.md

Use this script to create visual thumbnail grids of PowerPoint slides. Customize output prefix and the number of columns for grid layout. Adjust columns to control the number of slides per grid.

```bash
python scripts/thumbnail.py template.pptx [output_prefix]
```

```bash
python scripts/thumbnail.py template.pptx my-grid
```

```bash
python scripts/thumbnail.py template.pptx workspace/my-grid
```

```bash
python scripts/thumbnail.py template.pptx analysis --cols 4
```

```bash
python scripts/thumbnail.py presentation.pptx
```

--------------------------------

### Interpreting recalc.py Output JSON

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/xlsx/SKILL.md

Example JSON output from the recalc.py script, showing the status of formula recalculation, total errors, total formulas processed, and a summary of specific error types and their locations if errors were found.

```json
{
  "status": "success",           // or "errors_found"
  "total_errors": 0,              // Total error count
  "total_formulas": 42,           // Number of formulas in file
  "error_summary": {              // Only present if errors found
    "#REF!": {
      "count": 2,
      "locations": ["Sheet1!B5", "Sheet1!C10"]
    }
  }
}
```

--------------------------------

### Extract Figures/Images from PDF using pypdfium2 and PIL

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/REFERENCE.md

Provides a Python-based approach to rendering PDF pages and performing basic image processing for figure detection. This snippet outlines the setup for rendering and a simplified detection mask.

```python
import pypdfium2 as pdfium
from PIL import Image
import numpy as np

def extract_figures(pdf_path, output_dir):
    pdf = pdfium.PdfDocument(pdf_path)
    
    for page_num, page in enumerate(pdf):
        # Render high-resolution page
        bitmap = page.render(scale=3.0)
        img = bitmap.to_pil()
        
        # Convert to numpy for processing
        img_array = np.array(img)
        
        # Simple figure detection (non-white regions)
        mask = np.any(img_array != [255, 255, 255], axis=2)
        
        # Find contours and extract bounding boxes
        # (This is simplified - real implementation would need more sophisticated detection)
        
        # Save detected figures
        # ... implementation depends on specific needs
```

--------------------------------

### Reordering Slides in `presentation.xml`

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pptx/ooxml.md

Demonstrates how to reorder slides by modifying the `<p:sldIdLst>` in `ppt/presentation.xml`. The order of elements dictates the slide order.

```xml
<!-- Original order -->
<p:sldIdLst>
  <p:sldId id="256" r:id="rId2"/>
  <p:sldId id="257" r:id="rId3"/>
  <p:sldId id="258" r:id="rId4"/>
</p:sldIdLst>

<!-- After moving slide 3 to position 2 -->
<p:sldIdLst>
  <p:sldId id="256" r:id="rId2"/>
  <p:sldId id="258" r:id="rId4"/>
  <p:sldId id="257" r:id="rId3"/>
</p:sldIdLst>
```

--------------------------------

### Show Detailed PDF Structure (qpdf)

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/REFERENCE.md

Outputs the internal structure of a PDF file to a text file, useful for debugging and understanding PDF content. Includes all page information.

```bash
# Show detailed PDF structure for debugging
qpdf --show-all-pages input.pdf > structure.txt
```

--------------------------------

### Advanced PDF Cropping using pypdf

Source: https://github.com/tfriedel/claude-office-skills/blob/main/public/pdf/REFERENCE.md

Initializes a PDF reader and writer for performing operations like cropping on PDF documents. This snippet sets up the necessary objects for subsequent cropping logic.

```python
from pypdf import PdfWriter, PdfReader

reader = PdfReader("input.pdf")
writer = PdfWriter()
```