DOCX

DOCX creation, editing, and analysis

Overview

A .docx file is a ZIP archive containing XML files.

Generating Reports (Recommended for research reports)

For structured reports with cover page, TOC, tables, images, and references, use the pre-built template. The DOCX generator accepts the same JSON schema as the PDF generator, so one report_data.json can produce both formats.

Step 1: Copy the generator script

cp /builtin-skills/docx/scripts/generate_report.js ./generate_report.js

Step 2: Build report_data.json

Two phases: write section text files, then assemble into JSON.

Phase 1 — Write each section as a plain text file using write_file:

For each major section, read_file the relevant research data, then write_file the section content directly:

read_file("research_data/literature.md")           # refresh data in context
write_file("sections/sec_01_intro.txt", "...")      # write section content
write_file("sections/sec_02_mutations.txt", "...")   # next section
...

Each section file should be 1,000-2,000+ words with specific data, citations, and analysis.

NEVER write a Python script that contains section text as string literals. The section content goes directly into .txt files via write_file, not into Python code. Do NOT write scripts named "generate_sections", "create_content", "build_report" etc. that embed text in Python strings. If a sandbox script fails twice, switch to direct write_file calls.

Writing style — academic research report (CRITICAL):

• Write continuous flowing prose. Each paragraph: 8–10 sentences following the pattern: topic sentence → supporting evidence with specific data → analysis/comparison → transition to next point.
• Use in-text citations [1], [2] when referencing data. These render as blue superscript in the DOCX. Do NOT add a "References" list at the end of each chapter — all references go in ONE final references section.
• Synthesize across sources: "Study A [1] reported X, while Study B [2] found Y, suggesting that Z."
• Use academic connectives: "Furthermore", "In contrast", "These findings indicate", "Notably", "Taken together".
• NEVER use numbered-point structure (e.g. "1. Topic Title\n\nParagraph. 2. Topic Title\n\nParagraph."). Instead, use ## subheadings for structure and prose paragraphs for content. The template's renderText correctly renders ##/### as formatted subheadings.
• Bullet lists: max 5% of section, only for short enumerations (e.g. 4-5 drug names).

Language (CRITICAL):

• All report content (title, subtitle, section headings, body text, chart labels, table headers, cover metadata) MUST be written in the user's configured language as specified in the system prompt's ## Language section.
• If the user's language is Chinese (zh), write the entire report in Chinese; if English (en), write in English. Do NOT mix languages unless quoting a proper noun or technical term that has no standard translation.

Verification (before generating DOCX): Run a one-liner to count chars per section:

python3 -c "import os,glob; [print(f'{f}: {len(open(f).read())} chars') for f in sorted(glob.glob('sections/*.txt'))]; total=sum(len(open(f).read()) for f in glob.glob('sections/*.txt')); print(f'TOTAL: {total} chars, ~{total//500} pages')"

If total is under target, do ONE revision: read_file data again, then write_file to rewrite the thinnest 1-2 sections. Then proceed — no looping.

Phase 2 — Assemble into JSON using a standard assembler script:

import json, glob, os

SECTIONS_DIR = "sections"
TITLE = "Report Title"
SUBTITLE = "Subtitle"

# Section config: (file_pattern, heading_number, heading_text)
SECTION_MAP = [
    ("sec_01_*.txt", "1.", "Introduction"),
    ("sec_02_*.txt", "2.", "Background"),
    ("sec_03_*.txt", "3.", "Analysis"),
    ("sec_04_*.txt", "4.", "Discussion"),
    ("sec_05_*.txt", "5.", "Conclusion"),
]

data = {
    "title": TITLE, "subtitle": SUBTITLE,
    "short_title": TITLE[:40], "report_type": "Research Report",
    "toc": True, "sections": [],
    "cover_meta": [["Report Type", "Research Report"]],
}

for pattern, num, heading in SECTION_MAP:
    matches = sorted(glob.glob(os.path.join(SECTIONS_DIR, pattern)))
    if not matches:
        continue
    body = open(matches[0], encoding="utf-8").read().strip()
    data["sections"].append({"type": "heading", "level": 1, "number": num, "text": heading})
    data["sections"].append({"type": "text", "body": body})

# Add references section at end
data["sections"].append({"type": "heading", "level": 1, "text": "References"})
data["sections"].append({"type": "references", "items": []})

with open("report_data.json", "w", encoding="utf-8") as f:
    json.dump(data, f, ensure_ascii=False, indent=2)
print(f"Generated report_data.json ({len(data['sections'])} sections)")

Adding charts: Generate chart images separately using matplotlib, then include via the image section type.

CRITICAL — CJK font config (MUST include when chart has Chinese/Japanese/Korean text):

import matplotlib
matplotlib.use("Agg")
matplotlib.rcParams["font.sans-serif"] = [
    "WenQuanYi Micro Hei", "SimHei", "Noto Sans CJK SC",
    "Arial Unicode MS", "sans-serif",
]
matplotlib.rcParams["axes.unicode_minus"] = False
import matplotlib.pyplot as plt

# ... generate chart ...
plt.savefig("figures/chart.png", dpi=180, bbox_inches="tight")
plt.close()

Without this config, Chinese text in charts will appear as garbled boxes (□□□).

Then in the assembler:

data["sections"].append({"type": "text", "body": analysis_text})
data["sections"].append({"type": "image", "path": "figures/chart.png", "caption": "Figure 1: ..."})

Step 3: Generate the DOCX

python3 build_report_data.py   # outputs report_data.json
node generate_report.js report_data.json output_report.docx

Supported section types

Template features

• Cover page: Title, subtitle, metadata table, disclaimer, accent styling
• Table of Contents: Auto-generated from headings (levels 1-3)
• Headers/Footers: Short title + report type in header, page numbers in footer
• In-text citations: [1], [2,3] rendered as blue superscript
• Tables: Alternating row colors, header styling
• Callout boxes: Accent-bar styled highlight boxes
• References: Hanging-indent numbered list
• Two-section layout: Cover page as separate section (no header/footer)

Writing guidelines for high-quality reports

1. Flowing prose, NOT bullet points: Each text body must be continuous paragraphs of 8–10 sentences each, following: topic sentence → evidence with data → analysis → transition. NEVER write content as a list of bullet points or numbered items. Bullet lists max 5% of any section, only for short enumerations (e.g. 4-5 drug names).
2. Use numbered headings: Set number field ("1.", "2.1", "3.2.1") for professional structure
3. Add table captions: Use caption field like "Table 3: Key Financial Metrics (FY2026)"
4. Include references: Always end with a references section for credibility
5. In-text citations: Use [1], [2], [1,2,3] markers in text body — the template auto-renders them as blue superscript. Synthesize across sources: "Study A [1] reported X, while Study B [2] found Y, suggesting that Z."
6. Cover metadata: Use cover_meta to show report type, date, sector, etc. Do NOT include page count or total pages in cover_meta — the page count is unknown at assembly time and including it produces inaccurate information.
7. Include visuals: Generate chart images with matplotlib and include via image sections (aim for 2-4 per report)
8. Academic connectives: Use "Furthermore", "In contrast", "These findings indicate", "Notably", "Taken together" for cohesive flow between ideas

Quick Reference

Converting .doc to .docx

Legacy .doc files must be converted before editing:

python3 /builtin-skills/docx/scripts/office/soffice.py --headless --convert-to docx document.doc

Reading Content

# Text extraction with tracked changes
pandoc --track-changes=all document.docx -o output.md

# Raw XML access
python3 /builtin-skills/docx/scripts/office/unpack.py document.docx unpacked/

Converting to Images

python3 /builtin-skills/docx/scripts/office/soffice.py --headless --convert-to pdf document.docx
pdftoppm -jpeg -r 150 document.pdf page

Accepting Tracked Changes

To produce a clean document with all tracked changes accepted (requires LibreOffice):

python3 /builtin-skills/docx/scripts/accept_changes.py input.docx output.docx

Creating New Documents

Generate .docx files with JavaScript, then validate. Install: npm install -g docx

Setup

const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun,
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
        InternalHyperlink, Bookmark, FootnoteReferenceRun, PositionalTab,
        PositionalTabAlignment, PositionalTabRelativeTo, PositionalTabLeader,
        TabStopType, TabStopPosition, Column, SectionType,
        TableOfContents, HeadingLevel, BorderStyle, WidthType, ShadingType,
        VerticalAlign, PageNumber, PageBreak } = require('docx');

const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer));

Validation

After creating the file, validate it. If validation fails, unpack, fix the XML, and repack.

python3 /builtin-skills/docx/scripts/office/validate.py doc.docx

Page Size

// CRITICAL: docx-js defaults to A4, not US Letter
// Always set page size explicitly for consistent results
sections: [{
  properties: {
    page: {
      size: {
        width: 12240,   // 8.5 inches in DXA
        height: 15840   // 11 inches in DXA
      },
      margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } // 1 inch margins
    }
  },
  children: [/* content */]
}]

Common page sizes (DXA units, 1440 DXA = 1 inch):

Landscape orientation: docx-js swaps width/height internally, so pass portrait dimensions and let it handle the swap:

size: {
  width: 12240,   // Pass SHORT edge as width
  height: 15840,  // Pass LONG edge as height
  orientation: PageOrientation.LANDSCAPE  // docx-js swaps them in the XML
},
// Content width = 15840 - left margin - right margin (uses the long edge)

Styles (Override Built-in Headings)

Use Arial as the default font (universally supported). Keep titles black for readability.

const doc = new Document({
  styles: {
    default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default
    paragraphStyles: [
      // IMPORTANT: Use exact IDs to override built-in styles
      { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true,
        run: { size: 32, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // outlineLevel required for TOC
      { id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true,
        run: { size: 28, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } },
    ]
  },
  sections: [{
    children: [
      new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] }),
    ]
  }]
});

Lists (NEVER use unicode bullets)

// ❌ WRONG - never manually insert bullet characters
new Paragraph({ children: [new TextRun("• Item")] })  // BAD
new Paragraph({ children: [new TextRun("\u2022 Item")] })  // BAD

// ✅ CORRECT - use numbering config with LevelFormat.BULLET
const doc = new Document({
  numbering: {
    config: [
      { reference: "bullets",
        levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
      { reference: "numbers",
        levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT,
          style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
    ]
  },
  sections: [{
    children: [
      new Paragraph({ numbering: { reference: "bullets", level: 0 },
        children: [new TextRun("Bullet item")] }),
      new Paragraph({ numbering: { reference: "numbers", level: 0 },
        children: [new TextRun("Numbered item")] }),
    ]
  }]
});

// ⚠️ Each reference creates INDEPENDENT numbering
// Same reference = continues (1,2,3 then 4,5,6)
// Different reference = restarts (1,2,3 then 1,2,3)

Tables

CRITICAL: Tables need dual widths - set both columnWidths on the table AND width on each cell. Without both, tables render incorrectly on some platforms.

// CRITICAL: Always set table width for consistent rendering
// CRITICAL: Use ShadingType.CLEAR (not SOLID) to prevent black backgrounds
const border = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const borders = { top: border, bottom: border, left: border, right: border };

new Table({
  width: { size: 9360, type: WidthType.DXA }, // Always use DXA (percentages break in Google Docs)
  columnWidths: [4680, 4680], // Must sum to table width (DXA: 1440 = 1 inch)
  rows: [
    new TableRow({
      children: [
        new TableCell({
          borders,
          width: { size: 4680, type: WidthType.DXA }, // Also set on each cell
          shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, // CLEAR not SOLID
          margins: { top: 80, bottom: 80, left: 120, right: 120 }, // Cell padding (internal, not added to width)
          children: [new Paragraph({ children: [new TextRun("Cell")] })]
        })
      ]
    })
  ]
})

Table width calculation:

Always use WidthType.DXA — WidthType.PERCENTAGE breaks in Google Docs.

// Table width = sum of columnWidths = content width
// US Letter with 1" margins: 12240 - 2880 = 9360 DXA
width: { size: 9360, type: WidthType.DXA },
columnWidths: [7000, 2360]  // Must sum to table width

Width rules:

• Always use WidthType.DXA — never WidthType.PERCENTAGE (incompatible with Google Docs)
• Table width must equal the sum of columnWidths
• Cell width must match corresponding columnWidth
• Cell margins are internal padding - they reduce content area, not add to cell width
• For full-width tables: use content width (page width minus left and right margins)

Images

// CRITICAL: type parameter is REQUIRED
new Paragraph({
  children: [new ImageRun({
    type: "png", // Required: png, jpg, jpeg, gif, bmp, svg
    data: fs.readFileSync("image.png"),
    transformation: { width: 200, height: 150 },
    altText: { title: "Title", description: "Desc", name: "Name" } // All three required
  })]
})

Page Breaks

// CRITICAL: PageBreak must be inside a Paragraph
new Paragraph({ children: [new PageBreak()] })

// Or use pageBreakBefore
new Paragraph({ pageBreakBefore: true, children: [new TextRun("New page")] })

Hyperlinks

// External link
new Paragraph({
  children: [new ExternalHyperlink({
    children: [new TextRun({ text: "Click here", style: "Hyperlink" })],
    link: "https://example.com",
  })]
})

// Internal link (bookmark + reference)
// 1. Create bookmark at destination
new Paragraph({ heading: HeadingLevel.HEADING_1, children: [
  new Bookmark({ id: "chapter1", children: [new TextRun("Chapter 1")] }),
]})
// 2. Link to it
new Paragraph({ children: [new InternalHyperlink({
  children: [new TextRun({ text: "See Chapter 1", style: "Hyperlink" })],
  anchor: "chapter1",
})]})

Footnotes

const doc = new Document({
  footnotes: {
    1: { children: [new Paragraph("Source: Annual Report 2024")] },
    2: { children: [new Paragraph("See appendix for methodology")] },
  },
  sections: [{
    children: [new Paragraph({
      children: [
        new TextRun("Revenue grew 15%"),
        new FootnoteReferenceRun(1),
        new TextRun(" using adjusted metrics"),
        new FootnoteReferenceRun(2),
      ],
    })]
  }]
});

Tab Stops

// Right-align text on same line (e.g., date opposite a title)
new Paragraph({
  children: [
    new TextRun("Company Name"),
    new TextRun("\tJanuary 2025"),
  ],
  tabStops: [{ type: TabStopType.RIGHT, position: TabStopPosition.MAX }],
})

// Dot leader (e.g., TOC-style)
new Paragraph({
  children: [
    new TextRun("Introduction"),
    new TextRun({ children: [
      new PositionalTab({
        alignment: PositionalTabAlignment.RIGHT,
        relativeTo: PositionalTabRelativeTo.MARGIN,
        leader: PositionalTabLeader.DOT,
      }),
      "3",
    ]}),
  ],
})

Multi-Column Layouts

// Equal-width columns
sections: [{
  properties: {
    column: {
      count: 2,          // number of columns
      space: 720,        // gap between columns in DXA (720 = 0.5 inch)
      equalWidth: true,
      separate: true,    // vertical line between columns
    },
  },
  children: [/* content flows naturally across columns */]
}]

// Custom-width columns (equalWidth must be false)
sections: [{
  properties: {
    column: {
      equalWidth: false,
      children: [
        new Column({ width: 5400, space: 720 }),
        new Column({ width: 3240 }),
      ],
    },
  },
  children: [/* content */]
}]

Force a column break with a new section using type: SectionType.NEXT_COLUMN.

Table of Contents

// CRITICAL: Headings must use HeadingLevel ONLY - no custom styles
new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" })

Headers/Footers

sections: [{
  properties: {
    page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } // 1440 = 1 inch
  },
  headers: {
    default: new Header({ children: [new Paragraph({ children: [new TextRun("Header")] })] })
  },
  footers: {
    default: new Footer({ children: [new Paragraph({
      children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] })]
    })] })
  },
  children: [/* content */]
}]

Critical Rules for docx-js

• Set page size explicitly - docx-js defaults to A4; use US Letter (12240 x 15840 DXA) for US documents
• Landscape: pass portrait dimensions - docx-js swaps width/height internally; pass short edge as width, long edge as height, and set orientation: PageOrientation.LANDSCAPE
• Never use \n - use separate Paragraph elements
• Never use unicode bullets - use LevelFormat.BULLET with numbering config
• PageBreak must be in Paragraph - standalone creates invalid XML
• ImageRun requires type - always specify png/jpg/etc
• Always set table width with DXA - never use WidthType.PERCENTAGE (breaks in Google Docs)
• Tables need dual widths - columnWidths array AND cell width, both must match
• Table width = sum of columnWidths - for DXA, ensure they add up exactly
• Always add cell margins - use margins: { top: 80, bottom: 80, left: 120, right: 120 } for readable padding
• Use ShadingType.CLEAR - never SOLID for table shading
• Never use tables as dividers/rules - cells have minimum height and render as empty boxes (including in headers/footers); use border: { bottom: { style: BorderStyle.SINGLE, size: 6, color: "2E75B6", space: 1 } } on a Paragraph instead. For two-column footers, use tab stops (see Tab Stops section), not tables
• TOC requires HeadingLevel only - no custom styles on heading paragraphs
• Override built-in styles - use exact IDs: "Heading1", "Heading2", etc.
• Include outlineLevel - required for TOC (0 for H1, 1 for H2, etc.)

Editing Existing Documents

Follow all 3 steps in order.

Step 1: Unpack

python3 /builtin-skills/docx/scripts/office/unpack.py document.docx unpacked/

Extracts XML, pretty-prints, merges adjacent runs, and converts smart quotes to XML entities (“ etc.) so they survive editing. Use --merge-runs false to skip run merging.

Step 2: Edit XML

Edit files in unpacked/word/. See XML Reference below for patterns.

Use "Claude" as the author for tracked changes and comments, unless the user explicitly requests use of a different name.

Use the Edit tool directly for string replacement. Do not write Python scripts. Scripts introduce unnecessary complexity. The Edit tool shows exactly what is being replaced.

CRITICAL: Use smart quotes for new content. When adding text with apostrophes or quotes, use XML entities to produce smart quotes:

<!-- Use these entities for professional typography -->
<w:t>Here&#x2019;s a quote: &#x201C;Hello&#x201D;</w:t>

Adding comments: Use comment.py to handle boilerplate across multiple XML files (text must be pre-escaped XML):

python3 /builtin-skills/docx/scripts/comment.py unpacked/ 0 "Comment text with & and ’"
python3 /builtin-skills/docx/scripts/comment.py unpacked/ 1 "Reply text" --parent 0  # reply to comment 0
python3 /builtin-skills/docx/scripts/comment.py unpacked/ 0 "Text" --author "Custom Author"  # custom author name

Then add markers to document.xml (see Comments in XML Reference).

Step 3: Pack

python3 /builtin-skills/docx/scripts/office/pack.py unpacked/ output.docx --original document.docx

Validates with auto-repair, condenses XML, and creates DOCX. Use --validate false to skip.

Auto-repair will fix:

• durableId >= 0x7FFFFFFF (regenerates valid ID)
• Missing xml:space="preserve" on <w:t> with whitespace

Auto-repair won't fix:

• Malformed XML, invalid element nesting, missing relationships, schema violations

Common Pitfalls

• Replace entire <w:r> elements: When adding tracked changes, replace the whole <w:r>...</w:r> block with <w:del>...<w:ins>... as siblings. Don't inject tracked change tags inside a run.
• Preserve <w:rPr> formatting: Copy the original run's <w:rPr> block into your tracked change runs to maintain bold, font size, etc.

XML Reference

Schema Compliance

• Element order in <w:pPr>: <w:pStyle>, <w:numPr>, <w:spacing>, <w:ind>, <w:jc>, <w:rPr> last
• Whitespace: Add xml:space="preserve" to <w:t> with leading/trailing spaces
• RSIDs: Must be 8-digit hex (e.g., 00AB1234)

Tracked Changes

Insertion:

<w:ins w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:t>inserted text</w:t></w:r>
</w:ins>

Deletion:

<w:del w:id="2" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:delText>deleted text</w:delText></w:r>
</w:del>

Inside <w:del>: Use <w:delText> instead of <w:t>, and <w:delInstrText> instead of <w:instrText>.

Minimal edits - only mark what changes:

<!-- Change "30 days" to "60 days" -->
<w:r><w:t>The term is </w:t></w:r>
<w:del w:id="1" w:author="Claude" w:date="...">
  <w:r><w:delText>30</w:delText></w:r>
</w:del>
<w:ins w:id="2" w:author="Claude" w:date="...">
  <w:r><w:t>60</w:t></w:r>
</w:ins>
<w:r><w:t> days.</w:t></w:r>

Deleting entire paragraphs/list items - when removing ALL content from a paragraph, also mark the paragraph mark as deleted so it merges with the next paragraph. Add <w:del/> inside <w:pPr><w:rPr>:

<w:p>
  <w:pPr>
    <w:numPr>...</w:numPr>  <!-- list numbering if present -->
    <w:rPr>
      <w:del w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z"/>
    </w:rPr>
  </w:pPr>
  <w:del w:id="2" w:author="Claude" w:date="2025-01-01T00:00:00Z">
    <w:r><w:delText>Entire paragraph content being deleted...</w:delText></w:r>
  </w:del>
</w:p>

Without the <w:del/> in <w:pPr><w:rPr>, accepting changes leaves an empty paragraph/list item.

Rejecting another author's insertion - nest deletion inside their insertion:

<w:ins w:author="Jane" w:id="5">
  <w:del w:author="Claude" w:id="10">
    <w:r><w:delText>their inserted text</w:delText></w:r>
  </w:del>
</w:ins>

Restoring another author's deletion - add insertion after (don't modify their deletion):

<w:del w:author="Jane" w:id="5">
  <w:r><w:delText>deleted text</w:delText></w:r>
</w:del>
<w:ins w:author="Claude" w:id="10">
  <w:r><w:t>deleted text</w:t></w:r>
</w:ins>

Comments

After running comment.py (see Step 2), add markers to document.xml. For replies, use --parent flag and nest markers inside the parent's.

CRITICAL: <w:commentRangeStart> and <w:commentRangeEnd> are siblings of <w:r>, never inside <w:r>.

<!-- Comment markers are direct children of w:p, never inside w:r -->
<w:commentRangeStart w:id="0"/>
<w:del w:id="1" w:author="Claude" w:date="2025-01-01T00:00:00Z">
  <w:r><w:delText>deleted</w:delText></w:r>
</w:del>
<w:r><w:t> more text</w:t></w:r>
<w:commentRangeEnd w:id="0"/>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="0"/></w:r>

<!-- Comment 0 with reply 1 nested inside -->
<w:commentRangeStart w:id="0"/>
  <w:commentRangeStart w:id="1"/>
  <w:r><w:t>text</w:t></w:r>
  <w:commentRangeEnd w:id="1"/>
<w:commentRangeEnd w:id="0"/>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="0"/></w:r>
<w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="1"/></w:r>

Images

1. Add image file to word/media/
2. Add relationship to word/_rels/document.xml.rels:

<Relationship Id="rId5" Type=".../image" Target="media/image1.png"/>

3. Add content type to [Content_Types].xml:

<Default Extension="png" ContentType="image/png"/>

4. Reference in document.xml:

<w:drawing>
  <wp:inline>
    <wp:extent cx="914400" cy="914400"/>  <!-- EMUs: 914400 = 1 inch -->
    <a:graphic>
      <a:graphicData uri=".../picture">
        <pic:pic>
          <pic:blipFill><a:blip r:embed="rId5"/></pic:blipFill>
        </pic:pic>
      </a:graphicData>
    </a:graphic>
  </wp:inline>
</w:drawing>

Dependencies

• pandoc: Text extraction
• docx: npm install -g docx (new documents)
• LibreOffice: PDF conversion (auto-configured for sandboxed environments via /builtin-skills/docx/scripts/office/soffice.py)
• Poppler: pdftoppm for images