### Quick Start Installation

Source: https://github.com/aidotnet/opencowork/blob/main/README.md

Instructions to clone the repository, install dependencies, and run the development server.

```bash
git clone https://github.com/AIDotNet/OpenCowork.git
cd OpenCowork
npm install
npm run dev
```

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

### Usage Example: Recommended Method (python-docx)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/CHANGELOG.md

Bash commands to install dependencies and run the simple and full example scripts for adding comments using python-docx.

```bash
# Install dependencies
pip install python-docx

# Use the simple script
python scripts/add_comment_simple.py input.docx output.docx

# Use the full example
python scripts/examples/add_comments_pythondocx.py document.docx reviewed.docx
```

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

### Headers/Footers & Page Setup

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/docx-js.md

Example of configuring document sections with custom page margins, orientation, page numbers, default headers, and footers.

```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 */
      ]
    }
  ]
})
```

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

### Complete TOC Implementation Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

A comprehensive Python example demonstrating how to implement an auto-generated Table of Contents using ReportLab's `TableOfContents` and a custom `TocDocTemplate`.

```python
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, PageBreak, Spacer
from reportlab.platypus.tableofcontents import TableOfContents
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch

class TocDocTemplate(SimpleDocTemplate):
    def __init__(self, *args, **kwargs):
        SimpleDocTemplate.__init__(self, *args, **kwargs)

    def afterFlowable(self, flowable):
        """Capture TOC entries after each flowable is rendered"""
        if hasattr(flowable, 'bookmark_name'):
            level = getattr(flowable, 'bookmark_level', 0)
            text = getattr(flowable, 'bookmark_text', '')
            self.notify('TOCEntry', (level, text, self.page))

# Create document
doc = TocDocTemplate("document.pdf", pagesize=letter)
story = []
styles = getSampleStyleSheet()

# Create Table of Contents
toc = TableOfContents()
toc.levelStyles = [
    ParagraphStyle(name='TOCHeading1', fontSize=14, leftIndent=20,
                   fontName='Times New Roman'),
    ParagraphStyle(name='TOCHeading2', fontSize=12, leftIndent=40,
                   fontName='Times New Roman'),
]
story.append(Paragraph("<b>Table of Contents</b>", styles['Title']))
story.append(Spacer(1, 0.2*inch))
story.append(toc)
story.append(PageBreak())

# Helper function: Create heading with TOC bookmark
def add_heading(text, style, level=0):
    p = Paragraph(text, style)
    p.bookmark_name = text
    p.bookmark_level = level
    p.bookmark_text = text
    return p

# Chapter 1: Introduction
story.append(add_heading("Chapter 1: Introduction", styles['Heading1'], 0))
story.append(Paragraph("This is the introduction chapter with some example content.",
                       styles['Normal']))
story.append(Spacer(1, 0.2*inch))

story.append(add_heading("1.1 Background", styles['Heading2'], 1))
story.append(Paragraph("Background information goes here.", styles['Normal']))


# Chapter 2: Conclusion
story.append(add_heading("Chapter 2: Conclusion", styles['Heading1'], 0))
story.append(Paragraph("This concludes our document.", styles['Normal']))
story.append(Spacer(1, 0.2*inch))

story.append(add_heading("2.1 Summary", styles['Heading2'], 1))
story.append(Paragraph("Summary of the document.", styles['Normal']))

# Build the document (must use multiBuild for TOC to work)
doc.multiBuild(story)

print("PDF with Table of Contents created successfully!")
```

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

### Complete Table Example with Styles

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Provides a comprehensive example of creating a table using ReportLab, including defining various ParagraphStyles for headers and cells with different alignments, and importing necessary components.

```python
from reportlab.platypus import Table, TableStyle, Paragraph, Image
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib import colors
from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_RIGHT, TA_JUSTIFY

# Define styles for table cells
header_style = ParagraphStyle(
    name='TableHeader',
    fontName='Times New Roman',
    fontSize=11,
    textColor=colors.white,
    alignment=TA_CENTER
)

cell_style = ParagraphStyle(
    name='TableCell',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_CENTER
)

cell_style_jus = ParagraphStyle(
    name='TableCellLeft',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY
)

cell_style_right = ParagraphStyle(
    name='TableCellRight',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_RIGHT
)

```

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

### Cover Page Style Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Python code example demonstrating cover page styling with specific font sizes, spacing, and alignment.

```python
story.append(Paragraph(
    'RoutinAI Copilot (<font name="SimHei">RoutinAI 协作助手</font>) is built by routin.ai'
    'My name is RoutinAI Analyst (<font name="SimHei">洞察顾问</font>)', 
    enbody_style
))

cnbody_style = ParagraphStyle(
    name="CNBodyStyle",
    fontName="SimHei",  # Base font for Chinese
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    '本报告使用 <font name="Times New Roman">GPT-4</font> '
    '和 <font name="Times New Roman">GLM</font> 进行测试。',
    cnbody_style
))
```

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

### Font Rules Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example of registering fonts and applying them to paragraphs with mixed languages.

```python
from reportlab.lib.styles import ParagraphStyle
from reportlab.platypus import Paragraph
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

pdfmetrics.registerFont(TTFont('SimHei', '/usr/share/fonts/truetype/chinese/SimHei.ttf'))
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))

# Base font is English; wrap Chinese parts:
enbody_style = ParagraphStyle(
    name="ENBodyStyle",
    fontName="Times New Roman",  # Base font for English
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    'RoutinAI Copilot (<font name="SimHei">RoutinAI 协作助手</font>) is built by routin.ai'
    'My name is RoutinAI Analyst (<font name="SimHei">洞察顾问</font>)', 
    '<font name="SimHei">企业智能文档</font> services are powered by routin.ai.',
    enbody_style
))
```

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

### Simple tweet example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/post-to-x/SKILL.md

An example of posting a simple tweet.

```bash
# Simple tweet
python scripts/post_to_x.py "Hello X! 👋"
```

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

### Creating a Table with Styled Data

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example demonstrating how to create a table with styled text, including bolding, superscripts, and subscripts, using the reportlab library.

```python
data = [
    # Header row - bold text with Paragraph
    [
        Paragraph('<b>Parameter</b>', header_style),
        Paragraph('<b>Unit</b>', header_style),
        Paragraph('<b>Value</b>', header_style),
        Paragraph('<b>Note</b>', header_style)
    ],
    # Data rows - all text in Paragraph
    [
        Paragraph('Temperature', cell_style_jus),
        Paragraph('°C', cell_style),
        Paragraph('25.5', cell_style_jus),
        Paragraph('Ambient', cell_style)
    ],
    [
        Paragraph('Pressure', cell_style_jus),
        Paragraph('Pa', cell_style),
        Paragraph('1.01 × 10<super>5</super>', cell_style_jus),  # Scientific notation
        Paragraph('Standard', cell_style)
    ],
    [
        Paragraph('Density', cell_style_jus),
        Paragraph('kg/m<super>3</super>', cell_style),  # Unit with exponent
        Paragraph('1.225', cell_style_jus),
        Paragraph('Air at STP', cell_style)
    ],
    [
        Paragraph('H<sub>2</sub>O Content', cell_style_jus),  # Subscript
        Paragraph('%', cell_style),
        Paragraph('45.2', cell_style_jus),
        Paragraph('Relative humidity', cell_style)
    ]
]

# Create table
table = Table(data, colWidths=[120, 80, 100, 120])
table.setStyle(TableStyle([
    # Header styling
    ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#1F4E79')),
    ('TEXTCOLOR', (0, 0), (-1, 0), colors.white),
    # Alternating row colors
    ('BACKGROUND', (0, 1), (-1, 1), colors.white),
    ('BACKGROUND', (0, 2), (-1, 2), colors.HexColor('#F5F5F5')),
    ('BACKGROUND', (0, 3), (-1, 3), colors.white),
    ('BACKGROUND', (0, 4), (-1, 4), colors.HexColor('#F5F5F5')),
    # Grid and alignment
    ('GRID', (0, 0), (-1, -1), 0.5, colors.grey),
    ('VALIGN', (0, 0), (-1, -1), 'MIDDLE'),
    ('LEFTPADDING', (0, 0), (-1, -1), 8),
    ('RIGHTPADDING', (0, 0), (-1, -1), 8),
    ('TOPPADDING', (0, 0), (-1, -1), 6),
    ('BOTTOMPADDING', (0, 0), (-1, -1), 6),
]))
```

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

### Complete Python Example for Character Handling

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Demonstrates how to register fonts, define paragraph styles, and use Paragraph objects with tags for bold text, scientific notation with superscripts, and chemical formulas with subscripts.

```python
# --- Register fonts and font family ---
pdfmetrics.registerFont(TTFont('Times New Roman', '/usr/share/fonts/truetype/english/Times-New-Roman.ttf'))

# CRITICAL: Must call registerFontFamily() to enable <b> and <i> tags
registerFontFamily('Times New Roman', normal='Times New Roman', bold='Times New Roman')

# --- Define styles ---
body_style = ParagraphStyle(
    name='BodyStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY,
)
bold_style = ParagraphStyle(
    name='BoldStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.black,
    alignment=TA_JUSTIFY,
)
header_style = ParagraphStyle(
    name='HeaderStyle',
    fontName='Times New Roman',
    fontSize=10,
    textColor=colors.white,
    alignment=TA_JUSTIFY,
)

# --- Body text examples ---
# Bold title
title = Paragraph('<b>Scientific Formulas and Chemical Expressions</b>', bold_style)

# Math formula with superscript and mathematical symbol ×
math_text = Paragraph(
    'The Einstein mass-energy equivalence is expressed as E = mc<super>2</super>. '
    'In applied physics, the gravitational force is F = 6.674 × 10<super>-11</super> × '
    'm<sub>1</sub>m<sub>2</sub>/r<super>2</super>, '
    'and the quadratic formula solves a<super>2</super> + b<super>2</super> = c<super>2</super>.',
    body_style,
)

# Chemical expressions with subscript
chem_text = Paragraph(
    'The combustion of methane: CH<sub>4</sub> + 2O<sub>2</sub> ' 
    '= CO<sub>2</sub> + 2H<sub>2</sub>O. ' 
    'Sulfuric acid (H<sub>2</sub>SO<sub>4</sub>) reacts with sodium hydroxide to produce ' 
    'Na<sub>2</sub>SO<sub>4</sub> and water.',
    body_style,
)
```

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

### Dependencies - LibreOffice installation

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/SKILL.md

Install LibreOffice using apt-get.

```bash
sudo apt-get install libreoffice
```

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

### Multi-line tweet example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/post-to-x/SKILL.md

An example of posting a multi-line tweet with hashtags.

```bash
# Multi-line tweet
python scripts/post_to_x.py "🚀 New product launch!\n\n✨ Feature 1: xxx\n✨ Feature 2: yyy\n\n#ProductLaunch #NewFeature"
```

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

### Basic PDF Creation Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

A simple Python script using reportlab to create a PDF file, add text, draw a line, and save the document.

```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()
```

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

### Dependencies - pandoc installation

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/SKILL.md

Install pandoc using apt-get.

```bash
sudo apt-get install pandoc
```

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

### ReportLab Paragraph Examples

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Demonstrates how to use ReportLab's Paragraph object with tags for superscripts, subscripts, bold text, and mathematical operators, along with setting up paragraph styles.

```python
from reportlab.platypus import Paragraph
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib.enums import TA_LEFT, TA_CENTER

body_style = enbody_style = ParagraphStyle(
    name="ENBodyStyle",
    fontName="Times New Roman",
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
header_style = ParagraphStyle(
    name='CoverTitle',
    fontName='Times New Roman',
    fontSize=42,
    leading=50,
    alignment=TA_CENTER,
    spaceAfter=36
)

# Superscript: area unit
Paragraph('Total area: 500 m<super>2</super>', body_style)

# Subscript: chemical formula
Paragraph('The reaction produces CO<sub>2</sub> and H<sub>2</sub>O', body_style)

# Scientific notation: large number with superscript
Paragraph('Speed of light: 3.0 × 10<super>8</super> m/s', body_style)

# Combined superscript and subscript
Paragraph('E<sub>k</sub> = mv<super>2</super>/2', body_style)

# Bold heading
Paragraph('<b>Chapter 1: Introduction</b>', header_style)

# Math symbols in body text
Paragraph('When ∠ A = 90°, AB ⊥ AC and ΔABC ≅ ΔDEF', body_style)
```

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

### Dependencies - docx installation

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/SKILL.md

Install the 'docx' package using bun.

```bash
bun add docx
```

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

### Fetch a Web Page (Static) - Example 1

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/web-scraper/SKILL.md

Example of fetching an article from a given URL.

```bash
# Fetch an article
python fetch_page.py "https://example.com/article"
```

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

### Fetch a Web Page (Static) - Example 3

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/web-scraper/SKILL.md

Example of fetching raw full-page Markdown with a character limit.

```bash
# Fetch raw full-page markdown, limit to 5000 chars
python fetch_page.py "https://example.com" --raw --max-length 5000
```

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

### Example: Cold outreach

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/email-drafter/SKILL.md

Example of generating a cold outreach email and saving it to a file.

```bash
# Cold outreach
python scripts/email_draft.py --type cold-outreach --to "Sarah" --from "Alex" --subject "Partnership opportunity" --body "mutual benefit;our platform capabilities;propose a call" --tone professional --save outreach.txt
```

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

### Dependencies - Poppler installation

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/SKILL.md

Install Poppler utilities (including pdftoppm) using apt-get.

```bash
sudo apt-get install poppler-utils
```

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

### Palette and Application Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/xlsx/SKILL.md

Shows the color palette constraints and an example of applying styles to data headers and titles using openpyxl.

```python
# Palette
from openpyxl.styles import Alignment, Border, Font, Side, PatternFill,

# Base & Accents
background_white = "FFFFFF"           # background
background_row_alt = "E9E9E9"         # Alternating row fill
grey_header = "333333"   # Section headers
border_grey = "E3DEDE"        # Standard borders
blue_primary = "0B5CAD"       # Primary Accent

# Application Example: Data Headers (NOT Titles)
header_fill = PatternFill(start_color=grey_header, end_color=grey_header, fill_type="solid")
header_font = Font(name='Times New Roman', color="FFFFFF", bold=True)

for cell in sheet['B3:E3'][0]:
    cell.fill = header_fill
    cell.font = header_font

# Example: Title style (NO shading, left-aligned)
title_font = Font(name='Times New Roman', size=18, bold=True, color="000000")
title_alignment = Alignment(horizontal='left', vertical='center')
sheet['B2'].font = title_font
sheet['B2'].alignment = title_alignment
# NO fill for titles

```

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

### Install Dependencies (Lightweight)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/web-scraper/SKILL.md

Installs dependencies for lightweight scraping of static pages, search, and link extraction.

```bash
pip install requests beautifulsoup4 readability-lxml html2text ddgs
```

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

### Search the Web - Example 1

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/web-scraper/SKILL.md

Example of a general web search query.

```bash
# General search
python search_web.py "Python web scraping best practices 2025"
```

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

### Example MCP Server Configuration

Source: https://github.com/aidotnet/opencowork/blob/main/docs/docs/capabilities/mcp-servers.mdx

An example JSON configuration for an MCP server, specifically for integrating with GitHub.

```json
{
  "id": "github",
  "name": "GitHub MCP",
  "enabled": true,
  "transport": "stdio",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-github"],
  "env": {
    "GITHUB_PERSONAL_ACCESS_TOKEN": "..."
  }
}
```

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

### Fetch a Web Page (Static) - Example 2

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/web-scraper/SKILL.md

Example of extracting only table elements from a URL.

```bash
# Extract only tables
python fetch_page.py "https://example.com/data" --selector "table"
```

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

### Setup and Initialization

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/docx-js.md

Imports necessary components from the 'docx' library and demonstrates basic document creation and saving for both Node.js and browser environments.

```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
```

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

### Install Dependencies

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/excel-processor/SKILL.md

Installs the necessary openpyxl library for Excel processing. This is a one-time setup.

```bash
pip install openpyxl
```

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

### Prerequisites

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/post-to-x/SKILL.md

Installs Playwright and downloads the Chromium browser.

```bash
pip install playwright
playwright install chromium
```

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

### Docs Site Build Commands

Source: https://github.com/aidotnet/opencowork/blob/main/docs/docs/reference/building.mdx

Commands for installing dependencies, running the development server, and building the documentation site for production.

```bash
cd docs
npm install
npm run dev     # Local development
npm run build   # Production build (output: standalone)
```

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

### PROHIBIT - Manual TOC Entry Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

An example of how NOT to create TOC entries, demonstrating manual creation of entries with hardcoded page numbers and leader dots.

```python
toc_entries = [("1. Title", "5"), ("2. Section", "10")]
for entry, page in toc_entries:
    story.append(Paragraph(f"{entry} {'.'*50} {page}", style))
```

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

### Basic List Syntax with Numbering Configuration

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/docx-js.md

Provides an example of setting up numbering configurations for bullet lists and numbered lists, and then creating paragraphs that utilize these configurations. It highlights the importance of using `LevelFormat.BULLET` and different references for independent lists.

```javascript
// Bullets - ALWAYS use the numbering config, NOT unicode symbols
// CRITICAL: Use LevelFormat.BULLET constant, NOT the string "bullet"
const doc = new Document({
  numbering: {
    config: [
      {
        reference: 'bullet-list',
        levels: [
          {
            level: 0,
            format: LevelFormat.BULLET,
            text: '•',
            alignment: AlignmentType.LEFT,
            style: { paragraph: { indent: { left: 720, hanging: 360 } } }
          }
        ]
      },
      {
        reference: 'first-numbered-list',
        levels: [
          {
            level: 0,
            format: LevelFormat.DECIMAL,
            text: '%1.',
            alignment: AlignmentType.LEFT,
            style: { paragraph: { indent: { left: 720, hanging: 360 } } }
          }
        ]
      },
      {
        reference: 'second-numbered-list', // Different reference = restarts at 1
        levels: [
          {
            level: 0,
            format: LevelFormat.DECIMAL,
            text: '%1.',
            alignment: AlignmentType.LEFT,
            style: { paragraph: { indent: { left: 720, hanging: 360 } } }
          }
        ]
      }
    ]
  },
  sections: [
    {
      children: [
        // Bullet list items
        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')]
        }),
        // Numbered list items
        new Paragraph({
          numbering: { reference: 'first-numbered-list', level: 0 },
          children: [new TextRun('First numbered item')]
        }),
        new Paragraph({
          numbering: { reference: 'first-numbered-list', level: 0 },
          children: [new TextRun('Second numbered item')]
        }),
        // ⚠️ CRITICAL: Different reference = INDEPENDENT list that restarts at 1
        // Same reference = CONTINUES previous numbering
        new Paragraph({
          numbering: { reference: 'second-numbered-list', level: 0 },
          children: [new TextRun('Starts at 1 again (because different reference)')]
        })
      ]
    }
  ]
})

// ⚠️ CRITICAL: NEVER use unicode bullets - they create fake lists that don't work properly
// new TextRun("• Item")           // WRONG
// new SymbolRun({ char: "2022" }) // WRONG
// ✅ ALWAYS use numbering config with LevelFormat.BULLET for real Word lists

```

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

### Table Styling Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/docx-js.md

Demonstrates creating a centered table with specific cell styling, including vertical alignment, shading, and borders.

```javascript
new Table({
  alignment: AlignmentType.CENTER,
  rows: [
    new TableRow({
      children: [
        new TableCell({
          children: [
            new Paragraph({
              text: 'centered text',
              alignment: AlignmentType.CENTER
            })
          ],
          verticalAlign: VerticalAlign.CENTER,
          shading: { fill: colors.tableBg },
          borders: cellBorders
        })
      ]
    })
  ]
})
```

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

### Show help

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Display help information for the add_routinai_metadata.py script.

```bash
# Show help
python scripts/add_routinai_metadata.py --help
```

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

### Set/Update Metadata (RoutinAI Branding)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Command-line examples for adding RoutinAI branding metadata to PDFs.

```bash
# Add metadata to a single PDF (in-place)
python scripts/add_routinai_metadata.py document.pdf

# Add metadata with custom title
python scripts/add_routinai_metadata.py report.pdf -t "Q4 Financial Analysis"

# Batch process multiple PDFs
python scripts/add_routinai_metadata.py *.pdf
```

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

### Read a PDF and Extract Text

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example of reading a PDF and extracting all its text content using pypdf.

```python
from pypdf import PdfReader, PdfWriter

# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")

# Extract text
text = ""
for page in reader.pages:
    text += page.extract_text()
```

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

### Wrap Chinese segments with <font> tag

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example of appending paragraphs with Chinese segments wrapped in a <font> tag for specific font rendering.

```python
story.append(Paragraph(
    'RoutinAI Copilot (<font name="SimHei">RoutinAI 协作助手</font>) is built by routin.ai'
    'My name is RoutinAI Analyst (<font name="SimHei">洞察顾问</font>)',
    '<font name="SimHei">企业智能文档</font> services are powered by routin.ai.'
    enbody_style
))
```

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

### Registering a Viewer

Source: https://github.com/aidotnet/opencowork/blob/main/docs/docs/capabilities/file-preview.mdx

Example of how to register a new viewer for specific file extensions.

```typescript
viewerRegistry.register({
  type: 'markdown',
  extensions: ['.md', '.mdx'],
  component: MarkdownViewer
})
```

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

### Table Cell Content Formatting (Prohibited Example)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Illustrates a prohibited way of adding plain strings to table cells, which will not render formatting tags.

```python
# NEVER DO THIS - formatting will NOT work
data = [
    ['<b>Header</b>', 'Value'],           # Bold won't render
    ['Temperature', '25°C'],               # No style control
    ['Pressure', '1.01 × 10<super>5</super>'],  # Superscript won't work
]
```

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

### Usage Example: Advanced Method (OOXML)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/CHANGELOG.md

Bash commands demonstrating the workflow for the OOXML method, involving unpacking, adding comments, and repacking the document.

```bash
# Unpack, process, and pack
python ooxml/scripts/unpack.py document.docx unpacked
python scripts/add_comment.py unpacked 10 "批注内容"
python ooxml/scripts/pack.py unpacked output.docx
```

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

### Chinese and English Text Formatting

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example of setting a base font for Chinese and wrapping English segments with a font tag within a Paragraph object.

```python
cnbody_style = ParagraphStyle(
    name="CNBodyStyle",
    fontName="SimHei",  # Base font for Chinese
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    '本报告使用 <font name="Times New Roman">GPT-4</font> ' 
    '和 <font name="Times New Roman">GLM</font> 进行测试。',
    cnbody_style
))
```

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

### 更新文档

Source: https://github.com/aidotnet/opencowork/blob/main/docs/docs/reference/contributing.mdx

Commands to run the documentation development server.

```bash
cd docs
npm run dev
```

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

### Base font is Chinese; wrap English parts

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example of setting a base Chinese font and wrapping English segments with a specific font tag.

```python
cnbody_style = ParagraphStyle(
    name="CNBodyStyle",
    fontName="SimHei",  # Base font for Chinese
    fontSize=10.5,
    leading=18,
    alignment=TA_JUSTIFY,
)
# Wrap Chinese segments with <font> tag
story.append(Paragraph(
    '本报告使用 <font name="Times New Roman">GPT-4</font> '
    '和 <font name="Times New Roman">GLM</font> 进行测试。',
    cnbody_style
))
```

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

### Create PDF

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Basic PDF creation step before adding metadata.

```python
doc.build(story)
print("PDF built")
```

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

### Build Commands

Source: https://github.com/aidotnet/opencowork/blob/main/docs/docs/reference/building.mdx

Commands for type checking, building the production version, and packaging for different platforms.

```bash
# Type checking + build (recommended)
npm run build

# Build platform-specific installers
npm run build:win    # Windows (.exe)
npm run build:mac    # macOS (.dmg)
npm run build:linux  # Linux (.AppImage / .deb)
```

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

### Preventing Unwanted Line Breaks - Non-breaking Space

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example showing how to use a non-breaking space (U+00A0) to prevent English names from breaking at awkward positions.

```python
# PROHIBITED: "K.G. Palepu" may break after "K.G."
text = Paragraph("Professors (K.G. Palepu) proposed...",style)

# RIGHT: Use non-breaking space (U+00A0) to prevent breaking
text = Paragraph("Professors (K.G.\u00A0Palepu) proposed...",style)
```

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

### Table Cell Content Formatting (Required Example)

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Demonstrates the mandatory way to wrap all text content in table cells with Paragraph() objects to ensure proper formatting.

```python
# ALWAYS DO THIS
data = [
    [Paragraph('<b>Header</b>', header_style), Paragraph('Value', header_style)],
    [Paragraph('Temperature', cell_style), Paragraph('25°C', cell_style)],
    [Paragraph('Pressure', cell_style), Paragraph('1.01 × 10<super>5</super>', cell_style)],
]
```

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

### Preventing Unwanted Line Breaks - Word Wrap for Punctuation

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example demonstrating the use of 'wordWrap="CJK"' in ParagraphStyle to handle punctuation at the beginning of a line correctly.

```python
# RIGHT: Add wordWrap='CJK' for proper typography
styles.add(ParagraphStyle(
    name='BodyStyle',
    fontName='SimHei',
    fontSize=10.5,
    leading=18,
    alignment=TA_LEFT,
    wordWrap='CJK'  # Prevents orphaned punctuation
))
```

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

### Custom Styles Example

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/docx/docx-js.md

Example of defining custom styles for a Word document, including font size, bolding, font family, and paragraph spacing.

```javascript
styles.create({ 
    paragraphStyles: [
      {
        id: 'Heading1',
        name: 'Heading 1',
        basedOn: 'Normal',
        next: 'Normal',
        quickFormat: true,
        run: { size: 32, bold: true, font: 'SimSun' }, // SimSun 16pt for H1
        paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 }
      },
      {
        id: 'Heading2',
        name: 'Heading 2',
        basedOn: 'Normal',
        next: 'Normal',
        quickFormat: true,
        run: { size: 28, bold: true, font: 'SimHei' }, // SimHei 14pt for H2
        paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 }
      }
    ]
  })
```

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

### Development Commands

Source: https://github.com/aidotnet/opencowork/blob/main/docs/AGENTS.md

Common commands for development, building, and testing the project.

```bash
npm install
npm run dev
npm run types:check
npm run build
npm run start
docker compose up --build
```

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

### Creating New PDFs with Metadata

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example using reportlab to create a new PDF document and set essential metadata fields like Title, Author, Creator, Subject, and Description.

```python
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate
import os

# Extract filename without extension for metadata title
pdf_filename = "financial_report_2024.pdf"
title_for_metadata = os.path.splitext(pdf_filename)[0]  # "financial_report_2024"

doc = SimpleDocTemplate(
    pdf_filename,
    pagesize=letter,
    title=title_for_metadata,    # MUST: Match filename
    author='RoutinAI',           # MUST: Set to "RoutinAI"
    creator='RoutinAI',          # MUST: Set to "RoutinAI"
    subject='Annual financial analysis and performance metrics'  # SHOULD: Describe purpose
)
```

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

### Modifying Existing PDFs with Metadata

Source: https://github.com/aidotnet/opencowork/blob/main/resources/skills/pdf/SKILL.md

Example using pypdf to read an existing PDF, add pages to a writer object, and set required metadata fields (Title, Author, Creator, Subject).

```python
from pypdf import PdfReader, PdfWriter
import os

pdf_filename = "output.pdf"
title_for_metadata = os.path.splitext(os.path.basename(pdf_filename))[0]

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

for page in reader.pages:
    writer.add_page(page)

# Set metadata: Title, Author, Creator are REQUIRED
writer.add_metadata({
    '/Title': title_for_metadata,  # MUST: Match filename
    '/Author': 'RoutinAI',         # MUST: Set to "RoutinAI"
    '/Subject': 'Document purpose description',  # SHOULD: Describe purpose
    '/Creator': 'RoutinAI'         # MUST: Set to "RoutinAI"
})

with open(pdf_filename, "wb") as output:
    writer.write(output)
```