Docx

Important: All scripts/ paths are relative to this skill directory. Use run_skill_script tool to execute scripts, or run with: cd {this_skill_dir} && python scripts/...

DOCX creation, editing, and analysis

Quick Start — Pick the Right Tool

Create a new document (recommended path)

Call the in-process Java tool — no Node.js install, no fork, no disk round-trip:

Copy code
renderDocx(
  markdown="# Title\n\nBody paragraph...",
  filename="monthly-report",
  pageSize="A4"
)

Returns a clickable link of the form [monthly-report.docx](/api/v1/files/generated/<uuid>) valid for 10 minutes. The user clicks it to download — no follow-up Agent step needed.

renderDocx supports headings (# ## ###), bold (**text**), bullet lists (- item), numbered lists (1. item), pipe-style tables, and plain paragraphs. For images, headers/footers, or precise OOXML control, fall back to the docx-js workflow below.

Prerequisites

• python-docx (pip install python-docx): direct structure reading and light editing (paragraphs, styles, tables)
• docx (npm install -g docx): new document creation
• LibreOffice (soffice): .doc -> .docx conversion, tracked-changes acceptance, and PDF export
• pandoc: text extraction
• pdftoppm (poppler-utils): document-to-image workflows
• If pdftoppm is unavailable, a Python fallback path may use pdf2image.
• On Windows, dependencies must be installed and available in PATH; if missing, report the dependency issue and stop (do not keep retrying).

Overview

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

Quick Reference

Converting .doc to .docx

Legacy .doc files must be converted before editing:

bashCopy code
python scripts/office/soffice.py --headless --convert-to docx document.doc

Reading Content

Option A: python-docx (recommended for structured access)

Install: pip install python-docx. Gives direct access to paragraphs, styles, tables, and metadata without unpacking ZIP.

pythonCopy code
from docx import Document

doc = Document("document.docx")

# Paragraphs with styles
for para in doc.paragraphs:
    print(f"[{para.style.name}] {para.text}")

# Tables
for i, table in enumerate(doc.tables):
    print(f"Table {i+1}:")
    for row in table.rows:
        print([cell.text for cell in row.cells])

# Inline styles within a paragraph
for para in doc.paragraphs:
    for run in para.runs:
        print(f"  run: bold={run.bold} italic={run.italic} text={run.text!r}")

Use python-docx when you need to read or lightly modify content. Fall back to the unpack/XML workflow for complex structural changes.

Option B: pandoc (plain text extraction)

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

# Raw XML access
python scripts/office/unpack.py document.docx unpacked/

Converting to Images

bashCopy code
python 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):

bashCopy code
python scripts/accept_changes.py input.docx output.docx

Creating New Documents

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

Setup

javascriptCopy code
const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun,
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
        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.

bashCopy code
python scripts/office/validate.py doc.docx

Page Size

javascriptCopy code
// 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:

javascriptCopy code
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.

javascriptCopy code
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)

javascriptCopy code
// CORRECT - use numbering config with LevelFormat.BULLET
const doc = new Document({
  numbering: {
    config: [
      { reference: "bullets",
        levels: [{ level: 0, format: LevelFormat.BULLET, text: "\u2022", 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.

javascriptCopy code
// 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
  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 },
          children: [new Paragraph({ children: [new TextRun("Cell")] })]
        })
      ]
    })
  ]
})

Width rules:

• Always use WidthType.DXA - never WidthType.PERCENTAGE
• Table width must equal the sum of columnWidths
• Cell width must match corresponding columnWidth

Images

javascriptCopy code
// 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

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

Table of Contents

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

Headers/Footers

javascriptCopy code
sections: [{
  properties: {
    page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } }
  },
  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
• Landscape: pass portrait dimensions - docx-js swaps width/height internally
• Never use \n - use separate Paragraph elements
• Never use unicode bullets - use LevelFormat.BULLET with numbering config
• PageBreak must be in Paragraph
• ImageRun requires type
• Always set table width with DXA - never use WidthType.PERCENTAGE
• Tables need dual widths - columnWidths array AND cell width
• Use ShadingType.CLEAR - never SOLID for table shading
• TOC requires HeadingLevel only
• 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

bashCopy code
python scripts/office/unpack.py document.docx unpacked/

Extracts XML, pretty-prints, merges adjacent runs, and converts smart quotes to XML entities. Use --merge-runs false to skip run merging.

Step 2: Edit XML

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

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

CRITICAL: Use smart quotes for new content:

xmlCopy code
<w:t>Here&#x2019;s a quote: &#x201C;Hello&#x201D;</w:t>

Adding comments: Use comment.py to handle boilerplate:

bashCopy code
python scripts/comment.py unpacked/ 0 "Comment text with & and ’"
python scripts/comment.py unpacked/ 1 "Reply text" --parent 0  # reply to comment 0
python scripts/comment.py unpacked/ 0 "Text" --author "Custom Author"

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

Step 3: Pack

bashCopy code
python 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

Common Pitfalls

• Replace entire <w:r> elements: When adding tracked changes, replace the whole <w:r>...</w:r> block.
• Preserve <w:rPr> formatting: Copy the original run's <w:rPr> block into your tracked change runs.

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:

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

Deletion:

xmlCopy code
<w:del w:id="2" w:author="MateClaw" 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:

xmlCopy code
<!-- Change "30 days" to "60 days" -->
<w:r><w:t>The term is </w:t></w:r>
<w:del w:id="1" w:author="MateClaw" w:date="...">
  <w:r><w:delText>30</w:delText></w:r>
</w:del>
<w:ins w:id="2" w:author="MateClaw" 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 - mark the paragraph mark as deleted:

xmlCopy code
<w:p>
  <w:pPr>
    <w:rPr>
      <w:del w:id="1" w:author="MateClaw" w:date="2025-01-01T00:00:00Z"/>
    </w:rPr>
  </w:pPr>
  <w:del w:id="2" w:author="MateClaw" w:date="2025-01-01T00:00:00Z">
    <w:r><w:delText>Entire paragraph content being deleted...</w:delText></w:r>
  </w:del>
</w:p>

Rejecting another author's insertion:

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

Restoring another author's deletion:

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

Comments

After running comment.py, add markers to document.xml:

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

xmlCopy code
<w:commentRangeStart w:id="0"/>
<w:r><w:t>commented 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>

Images

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

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

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

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

4. Reference in document.xml:

xmlCopy code
<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>