scientific-writer 2.1.1__py3-none-any.whl → 2.2.2__py3-none-any.whl

scientific_writer/.claude/skills/clinical-reports/scripts/validate_trial_report.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""
+Validate clinical trial reports against ICH-E3 structure.
+
+Checks Clinical Study Reports (CSR) for ICH-E3 compliance.
+
+Usage:
+    python validate_trial_report.py <csr_file.md>
+"""
+
+import argparse
+import json
+import re
+from pathlib import Path
+
+
+ICH_E3_SECTIONS = {
+    "title_page": "Title Page",
+    "synopsis": "Synopsis (2)",
+    "toc": "Table of Contents (3)",
+    "abbreviations": "List of Abbreviations (4)",
+    "ethics": "Ethics (Section 2)",
+    "investigators": "Investigators and Study Administrative Structure (Section 3)",
+    "introduction": "Introduction (Section 4)",
+    "objectives": "Study Objectives and Plan (Section 5)",
+    "study_patients": "Study Patients (Section 6)",
+    "efficacy": "Efficacy Evaluation (Section 7)",
+    "safety": "Safety Evaluation (Section 8)",
+    "discussion": "Discussion and Overall Conclusions (Section 9)",
+    "tables_figures": "Tables, Figures, and Graphs (Section 10)",
+    "references": "References (Section 11)",
+    "appendices": "Appendices (Section 12-14)",
+}
+
+
+def validate_ich_e3(filename: str) -> dict:
+    """Validate CSR structure against ICH-E3."""
+    with open(filename, 'r', encoding='utf-8') as f:
+        content = f.read()
+    
+    results = {}
+    for section_id, section_name in ICH_E3_SECTIONS.items():
+        # Simple pattern matching for section headers
+        pattern = rf"(?i)##?\s*{re.escape(section_name.split('(')[0].strip())}"
+        found = bool(re.search(pattern, content))
+        results[section_id] = {"name": section_name, "found": found}
+    
+    compliance_rate = sum(1 for r in results.values() if r["found"]) / len(results) * 100
+    
+    return {
+        "filename": filename,
+        "compliance_rate": round(compliance_rate, 1),
+        "sections": results,
+        "status": "PASS" if compliance_rate >= 90 else "NEEDS_REVISION"
+    }
+
+
+def main():
+    """Main entry point."""
+    parser = argparse.ArgumentParser(description="Validate CSR against ICH-E3")
+    parser.add_argument("input_file", help="Path to CSR file")
+    parser.add_argument("--json", action="store_true", help="Output JSON")
+    
+    args = parser.parse_args()
+    
+    try:
+        report = validate_ich_e3(args.input_file)
+        
+        if args.json:
+            print(json.dumps(report, indent=2))
+        else:
+            print(f"\nICH-E3 Compliance: {report['compliance_rate']}%")
+            print(f"Status: {report['status']}\n")
+            print("Section Checklist:")
+            for section, details in report["sections"].items():
+                symbol = "✓" if details["found"] else "✗"
+                print(f"{symbol} {details['name']}")
+        
+        return 0 if report["status"] == "PASS" else 1
+        
+    except Exception as e:
+        print(f"Error: {e}")
+        return 1
+
+
+if __name__ == "__main__":
+    import sys
+    sys.exit(main())
+

scientific_writer/.claude/skills/document-skills/docx/LICENSE.txt

@@ -0,0 +1,30 @@
+© 2025 Anthropic, PBC. All rights reserved.
+
+LICENSE: Use of these materials (including all code, prompts, assets, files,
+and other components of this Skill) is governed by your agreement with
+Anthropic regarding use of Anthropic's services. If no separate agreement
+exists, use is governed by Anthropic's Consumer Terms of Service or
+Commercial Terms of Service, as applicable:
+https://www.anthropic.com/legal/consumer-terms
+https://www.anthropic.com/legal/commercial-terms
+Your applicable agreement is referred to as the "Agreement." "Services" are
+as defined in the Agreement.
+
+ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
+contrary, users may not:
+
+- Extract these materials from the Services or retain copies of these
+  materials outside the Services
+- Reproduce or copy these materials, except for temporary copies created
+  automatically during authorized use of the Services
+- Create derivative works based on these materials
+- Distribute, sublicense, or transfer these materials to any third party
+- Make, offer to sell, sell, or import any inventions embodied in these
+  materials
+- Reverse engineer, decompile, or disassemble these materials
+
+The receipt, viewing, or possession of these materials does not convey or
+imply any license or right beyond those expressly granted above.
+
+Anthropic retains all right, title, and interest in these materials,
+including all copyrights, patents, and other intellectual property rights.

scientific_writer/.claude/skills/document-skills/docx/SKILL.md

@@ -0,0 +1,197 @@
+---
+name: docx
+description: "Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing."
+license: Proprietary. LICENSE.txt has complete terms
+---
+
+# DOCX creation, editing, and analysis
+
+## Overview
+
+A .docx file is a ZIP archive containing XML files and resources. Create, edit, or analyze Word documents using text extraction, raw XML access, or redlining workflows. Apply this skill for professional document processing, tracked changes, and content manipulation.
+
+## Workflow Decision Tree
+
+### Reading/Analyzing Content
+Use "Text extraction" or "Raw XML access" sections below
+
+### Creating New Document
+Use "Creating a new Word document" workflow
+
+### Editing Existing Document
+- **Your own document + simple changes**
+  Use "Basic OOXML editing" workflow
+
+- **Someone else's document**
+  Use **"Redlining workflow"** (recommended default)
+
+- **Legal, academic, business, or government docs**
+  Use **"Redlining workflow"** (required)
+
+## Reading and analyzing content
+
+### Text extraction
+To read the text contents of a document, convert the document to markdown using pandoc. Pandoc provides excellent support for preserving document structure and can show tracked changes:
+
+```bash
+# Convert document to markdown with tracked changes
+pandoc --track-changes=all path-to-file.docx -o output.md
+# Options: --track-changes=accept/reject/all
+```
+
+### Raw XML access
+Raw XML access is required for: comments, complex formatting, document structure, embedded media, and metadata. For any of these features, unpack a document and read its raw XML contents.
+
+#### Unpacking a file
+`python ooxml/scripts/unpack.py <office_file> <output_directory>`
+
+#### Key file structures
+* `word/document.xml` - Main document contents
+* `word/comments.xml` - Comments referenced in document.xml
+* `word/media/` - Embedded images and media files
+* Tracked changes use `<w:ins>` (insertions) and `<w:del>` (deletions) tags
+
+## Creating a new Word document
+
+When creating a new Word document from scratch, use **docx-js**, which allows you to create Word documents using JavaScript/TypeScript.
+
+### Workflow
+1. **MANDATORY - READ ENTIRE FILE**: Read [`docx-js.md`](docx-js.md) (~500 lines) 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 document creation.
+2. Create a JavaScript/TypeScript file using Document, Paragraph, TextRun components (You can assume all dependencies are installed, but if not, refer to the dependencies section below)
+3. Export as .docx using Packer.toBuffer()
+
+## Editing an existing Word document
+
+When editing an existing Word document, use the **Document library** (a Python library for OOXML manipulation). The library automatically handles infrastructure setup and provides methods for document manipulation. For complex scenarios, you can access the underlying DOM directly through the library.
+
+### Workflow
+1. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for the Document library API and XML patterns for directly editing document files.
+2. Unpack the document: `python ooxml/scripts/unpack.py <office_file> <output_directory>`
+3. Create and run a Python script using the Document library (see "Document Library" section in ooxml.md)
+4. Pack the final document: `python ooxml/scripts/pack.py <input_directory> <office_file>`
+
+The Document library provides both high-level methods for common operations and direct DOM access for complex scenarios.
+
+## Redlining workflow for document review
+
+This workflow allows planning comprehensive tracked changes using markdown before implementing them in OOXML. **CRITICAL**: For complete tracked changes, implement ALL changes systematically.
+
+**Batching Strategy**: Group related changes into batches of 3-10 changes. This makes debugging manageable while maintaining efficiency. Test each batch before moving to the next.
+
+**Principle: Minimal, Precise Edits**
+When implementing tracked changes, only mark text that actually changes. Repeating unchanged text makes edits harder to review and appears unprofessional. Break replacements into: [unchanged text] + [deletion] + [insertion] + [unchanged text]. Preserve the original run's RSID for unchanged text by extracting the `<w:r>` element from the original and reusing it.
+
+Example - Changing "30 days" to "60 days" in a sentence:
+```python
+# BAD - Replaces entire sentence
+'<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>'
+
+# GOOD - Only marks what changed, preserves original <w:r> for unchanged text
+'<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>'
+```
+
+### Tracked changes workflow
+
+1. **Get markdown representation**: Convert document to markdown with tracked changes preserved:
+   ```bash
+   pandoc --track-changes=all path-to-file.docx -o current.md
+   ```
+
+2. **Identify and group changes**: Review the document and identify ALL changes needed, organizing them into logical batches:
+
+   **Location methods** (for finding changes in XML):
+   - Section/heading numbers (e.g., "Section 3.2", "Article IV")
+   - Paragraph identifiers if numbered
+   - Grep patterns with unique surrounding text
+   - Document structure (e.g., "first paragraph", "signature block")
+   - **DO NOT use markdown line numbers** - they don't map to XML structure
+
+   **Batch organization** (group 3-10 related changes per batch):
+   - By section: "Batch 1: Section 2 amendments", "Batch 2: Section 5 updates"
+   - By type: "Batch 1: Date corrections", "Batch 2: Party name changes"
+   - By complexity: Start with simple text replacements, then tackle complex structural changes
+   - Sequential: "Batch 1: Pages 1-3", "Batch 2: Pages 4-6"
+
+3. **Read documentation and unpack**:
+   - **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Pay special attention to the "Document Library" and "Tracked Change Patterns" sections.
+   - **Unpack the document**: `python ooxml/scripts/unpack.py <file.docx> <dir>`
+   - **Note the suggested RSID**: The unpack script will suggest an RSID to use for your tracked changes. Copy this RSID for use in step 4b.
+
+4. **Implement changes in batches**: Group changes logically (by section, by type, or by proximity) and implement them together in a single script. This approach:
+   - Makes debugging easier (smaller batch = easier to isolate errors)
+   - Allows incremental progress
+   - Maintains efficiency (batch size of 3-10 changes works well)
+
+   **Suggested batch groupings:**
+   - By document section (e.g., "Section 3 changes", "Definitions", "Termination clause")
+   - By change type (e.g., "Date changes", "Party name updates", "Legal term replacements")
+   - By proximity (e.g., "Changes on pages 1-3", "Changes in first half of document")
+
+   For each batch of related changes:
+
+   **a. Map text to XML**: Grep for text in `word/document.xml` to verify how text is split across `<w:r>` elements.
+
+   **b. Create and run script**: Use `get_node` to find nodes, implement changes, then `doc.save()`. See **"Document Library"** section in ooxml.md for patterns.
+
+   **Note**: Always grep `word/document.xml` immediately before writing a script to get current line numbers and verify text content. Line numbers change after each script run.
+
+5. **Pack the document**: After all batches are complete, convert the unpacked directory back to .docx:
+   ```bash
+   python ooxml/scripts/pack.py unpacked reviewed-document.docx
+   ```
+
+6. **Final verification**: Do a comprehensive check of the complete document:
+   - Convert final document to markdown:
+     ```bash
+     pandoc --track-changes=all reviewed-document.docx -o verification.md
+     ```
+   - Verify ALL changes were applied correctly:
+     ```bash
+     grep "original phrase" verification.md  # Should NOT find it
+     grep "replacement phrase" verification.md  # Should find it
+     ```
+   - Check that no unintended changes were introduced
+
+
+## Converting Documents to Images
+
+To visually analyze Word documents, convert them to images using a two-step process:
+
+1. **Convert DOCX to PDF**:
+   ```bash
+   soffice --headless --convert-to pdf document.docx
+   ```
+
+2. **Convert PDF pages to JPEG images**:
+   ```bash
+   pdftoppm -jpeg -r 150 document.pdf page
+   ```
+   This creates files like `page-1.jpg`, `page-2.jpg`, etc.
+
+Options:
+- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance)
+- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred)
+- `-f N`: First page to convert (e.g., `-f 2` starts from page 2)
+- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5)
+- `page`: Prefix for output files
+
+Example for specific range:
+```bash
+pdftoppm -jpeg -r 150 -f 2 -l 5 document.pdf page  # Converts only pages 2-5
+```
+
+## Code Style Guidelines
+**IMPORTANT**: When generating code for DOCX operations:
+- Write concise code
+- Avoid verbose variable names and redundant operations
+- Avoid unnecessary print statements
+
+## Dependencies
+
+Required dependencies (install if not available):
+
+- **pandoc**: `sudo apt-get install pandoc` (for text extraction)
+- **docx**: `npm install -g docx` (for creating new documents)
+- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion)
+- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images)
+- **defusedxml**: `pip install defusedxml` (for secure XML parsing)

scientific_writer/.claude/skills/document-skills/docx/docx-js.md

@@ -0,0 +1,350 @@
+# DOCX Library Tutorial
+
+Generate .docx files with JavaScript/TypeScript.
+
+**Important: Read this entire document before starting.** Critical formatting rules and common pitfalls are covered throughout - skipping sections may result in corrupted files or rendering issues.
+
+## Setup
+Assumes docx is already installed globally
+If not installed: `npm install -g docx`
+
+```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
+```
+
+## Text & Formatting
+```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
+  ]
+})
+```
+
+## Styles & Professional Formatting
+
+```javascript
+const doc = new Document({
+  styles: {
+    default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default
+    paragraphStyles: [
+      // Document title style - override built-in Title style
+      { id: "Title", name: "Title", basedOn: "Normal",
+        run: { size: 56, bold: true, color: "000000", font: "Arial" },
+        paragraph: { spacing: { before: 240, after: 120 }, alignment: AlignmentType.CENTER } },
+      // IMPORTANT: Override built-in heading styles by using their exact IDs
+      { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true,
+        run: { size: 32, bold: true, color: "000000", font: "Arial" }, // 16pt
+        paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // Required for TOC
+      { id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true,
+        run: { size: 28, bold: true, color: "000000", font: "Arial" }, // 14pt
+        paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } },
+      // Custom styles use your own IDs
+      { id: "myStyle", name: "My Style", basedOn: "Normal",
+        run: { size: 28, bold: true, color: "000000" },
+        paragraph: { spacing: { after: 120 }, alignment: AlignmentType.CENTER } }
+    ],
+    characterStyles: [{ id: "myCharStyle", name: "My Char Style",
+      run: { color: "FF0000", bold: true, underline: { type: UnderlineType.SINGLE } } }]
+  },
+  sections: [{
+    properties: { page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } },
+    children: [
+      new Paragraph({ heading: HeadingLevel.TITLE, children: [new TextRun("Document Title")] }), // Uses overridden Title style
+      new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Heading 1")] }), // Uses overridden Heading1 style
+      new Paragraph({ style: "myStyle", children: [new TextRun("Custom paragraph style")] }),
+      new Paragraph({ children: [
+        new TextRun("Normal with "),
+        new TextRun({ text: "custom char style", style: "myCharStyle" })
+      ]})
+    ]
+  }]
+});
+```
+
+**Professional Font Combinations:**
+- **Arial (Headers) + Arial (Body)** - Most universally supported, clean and professional
+- **Times New Roman (Headers) + Arial (Body)** - Classic serif headers with modern sans-serif body
+- **Georgia (Headers) + Verdana (Body)** - Optimized for screen reading, elegant contrast
+
+**Key Styling Principles:**
+- **Override built-in styles**: Use exact IDs like "Heading1", "Heading2", "Heading3" to override Word's built-in heading styles
+- **HeadingLevel constants**: `HeadingLevel.HEADING_1` uses "Heading1" style, `HeadingLevel.HEADING_2` uses "Heading2" style, etc.
+- **Include outlineLevel**: Set `outlineLevel: 0` for H1, `outlineLevel: 1` for H2, etc. to ensure TOC works correctly
+- **Use custom styles** instead of inline formatting for consistency
+- **Set a default font** using `styles.default.document.run.font` - Arial is universally supported
+- **Establish visual hierarchy** with different font sizes (titles > headers > body)
+- **Add proper spacing** with `before` and `after` paragraph spacing
+- **Use colors sparingly**: Default to black (000000) and shades of gray for titles and headings (heading 1, heading 2, etc.)
+- **Set consistent margins** (1440 = 1 inch is standard)
+
+
+## Lists (ALWAYS USE PROPER LISTS - NEVER USE UNICODE BULLETS)
+```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 NUMBERING RULE: Each reference creates an INDEPENDENT numbered list
+// - Same reference = continues numbering (1, 2, 3... then 4, 5, 6...)
+// - Different reference = restarts at 1 (1, 2, 3... then 1, 2, 3...)
+// Use unique reference names for each separate numbered section!
+
+// ⚠️ 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
+```
+
+## Tables
+```javascript
+// Complete table with margins, borders, headers, and bullet points
+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")] 
+            })
+          ]
+        })
+      ]
+    })
+  ]
+})
+```
+
+**IMPORTANT: Table Width & Borders**
+- Use BOTH `columnWidths: [width1, width2, ...]` array AND `width: { size: X, type: WidthType.DXA }` on each cell
+- Values in DXA (twentieths of a point): 1440 = 1 inch, Letter usable width = 9360 DXA (with 1" margins)
+- Apply borders to individual `TableCell` elements, NOT the `Table` itself
+
+**Precomputed Column Widths (Letter size with 1" margins = 9360 DXA total):**
+- **2 columns:** `columnWidths: [4680, 4680]` (equal width)
+- **3 columns:** `columnWidths: [3120, 3120, 3120]` (equal width)
+
+## Links & Navigation
+```javascript
+// TOC (requires headings) - CRITICAL: Use HeadingLevel only, NOT custom styles
+// ❌ WRONG: new Paragraph({ heading: HeadingLevel.HEADING_1, style: "customHeader", children: [new TextRun("Title")] })
+// ✅ CORRECT: new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] })
+new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" }),
+
+// External link
+new Paragraph({
+  children: [new ExternalHyperlink({
+    children: [new TextRun({ text: "Google", style: "Hyperlink" })],
+    link: "https://www.google.com"
+  })]
+}),
+
+// Internal link & bookmark
+new Paragraph({
+  children: [new InternalHyperlink({
+    children: [new TextRun({ text: "Go to Section", style: "Hyperlink" })],
+    anchor: "section1"
+  })]
+}),
+new Paragraph({
+  children: [new TextRun("Section Content")],
+  bookmark: { id: "section1", name: "section1" }
+}),
+```
+
+## Images & Media
+```javascript
+// Basic image with sizing & positioning
+// CRITICAL: Always specify 'type' parameter - it's REQUIRED for ImageRun
+new Paragraph({
+  alignment: AlignmentType.CENTER,
+  children: [new ImageRun({
+    type: "png", // NEW REQUIREMENT: Must specify image type (png, jpg, jpeg, gif, bmp, svg)
+    data: fs.readFileSync("image.png"),
+    transformation: { width: 200, height: 150, rotation: 0 }, // rotation in degrees
+    altText: { title: "Logo", description: "Company logo", name: "Name" } // IMPORTANT: All three fields are required
+  })]
+})
+```
+
+## Page Breaks
+```javascript
+// Manual page break
+new Paragraph({ children: [new PageBreak()] }),
+
+// Page break before paragraph
+new Paragraph({
+  pageBreakBefore: true,
+  children: [new TextRun("This starts on a new page")]
+})
+
+// ⚠️ CRITICAL: NEVER use PageBreak standalone - it will create invalid XML that Word cannot open
+// ❌ WRONG: new PageBreak() 
+// ✅ CORRECT: new Paragraph({ children: [new PageBreak()] })
+```
+
+## Headers/Footers & Page Setup
+```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 */]
+  }]
+});
+```
+
+## Tabs
+```javascript
+new Paragraph({
+  tabStops: [
+    { type: TabStopType.LEFT, position: TabStopPosition.MAX / 4 },
+    { type: TabStopType.CENTER, position: TabStopPosition.MAX / 2 },
+    { type: TabStopType.RIGHT, position: TabStopPosition.MAX * 3 / 4 }
+  ],
+  children: [new TextRun("Left\tCenter\tRight")]
+})
+```
+
+## Constants & Quick Reference
+- **Underlines:** `SINGLE`, `DOUBLE`, `WAVY`, `DASH`
+- **Borders:** `SINGLE`, `DOUBLE`, `DASHED`, `DOTTED`  
+- **Numbering:** `DECIMAL` (1,2,3), `UPPER_ROMAN` (I,II,III), `LOWER_LETTER` (a,b,c)
+- **Tabs:** `LEFT`, `CENTER`, `RIGHT`, `DECIMAL`
+- **Symbols:** `"2022"` (•), `"00A9"` (©), `"00AE"` (®), `"2122"` (™), `"00B0"` (°), `"F070"` (✓), `"F0FC"` (✗)
+
+## Critical Issues & Common Mistakes
+- **CRITICAL: PageBreak must ALWAYS be inside a Paragraph** - standalone PageBreak creates invalid XML that Word cannot open
+- **ALWAYS use ShadingType.CLEAR for table cell shading** - Never use ShadingType.SOLID (causes black background).
+- Measurements in DXA (1440 = 1 inch) | Each table cell needs ≥1 Paragraph | TOC requires HeadingLevel styles only
+- **ALWAYS use custom styles** with Arial font for professional appearance and proper visual hierarchy
+- **ALWAYS set a default font** using `styles.default.document.run.font` - Arial recommended
+- **ALWAYS use columnWidths array for tables** + individual cell widths for compatibility
+- **NEVER use unicode symbols for bullets** - always use proper numbering configuration with `LevelFormat.BULLET` constant (NOT the string "bullet")
+- **NEVER use \n for line breaks anywhere** - always use separate Paragraph elements for each line
+- **ALWAYS use TextRun objects within Paragraph children** - never use text property directly on Paragraph
+- **CRITICAL for images**: ImageRun REQUIRES `type` parameter - always specify "png", "jpg", "jpeg", "gif", "bmp", or "svg"
+- **CRITICAL for bullets**: Must use `LevelFormat.BULLET` constant, not string "bullet", and include `text: "•"` for the bullet character
+- **CRITICAL for numbering**: Each numbering reference creates an INDEPENDENT list. Same reference = continues numbering (1,2,3 then 4,5,6). Different reference = restarts at 1 (1,2,3 then 1,2,3). Use unique reference names for each separate numbered section!
+- **CRITICAL for TOC**: When using TableOfContents, headings must use HeadingLevel ONLY - do NOT add custom styles to heading paragraphs or TOC will break
+- **Tables**: Set `columnWidths` array + individual cell widths, apply borders to cells not table
+- **Set table margins at TABLE level** for consistent cell padding (avoids repetition per cell)