Create and manipulate Word DOCX files programmatically. Use when the user needs to generate documents, modify DOCX templates, extract document content, or automate Word document workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: Word, DOCX, document, report, template, contract, letter, corporate, branding.
npx skills add https://github.com/jwynia/agent-skills --skill docx-generator
Use this skill when:
{{TITLE}} or ${author}Do NOT use this skill when:
{{PLACEHOLDERS}} with actual contentExtract text inventory to understand what can be replaced:
deno run --allow-read scripts/analyze-template.ts corporate-template.docx > inventory.json
Output (inventory.json):
{
"filename": "corporate-template.docx",
"paragraphCount": 25,
"tableCount": 2,
"imageCount": 1,
"paragraphs": [
{
"index": 0,
"style": "Title",
"fullText": "{{DOCUMENT_TITLE}}",
"runs": [
{ "text": "{{DOCUMENT_TITLE}}", "bold": true, "fontSize": 28 }
]
}
],
"placeholders": [
{ "tag": "{{DOCUMENT_TITLE}}", "location": "paragraph", "paragraphIndex": 0 },
{ "tag": "{{AUTHOR}}", "location": "footer-default", "paragraphIndex": 0 },
{ "tag": "${date}", "location": "table", "tableIndex": 0, "cellLocation": "R1C2" }
]
}
Create replacements.json:
{
"textReplacements": [
{ "tag": "{{DOCUMENT_TITLE}}", "value": "Q4 2024 Financial Report" },
{ "tag": "{{AUTHOR}}", "value": "Finance Department" },
{ "tag": "${date}", "value": "December 15, 2024" },
{ "tag": "{{COMPANY}}", "value": "Acme Corporation" }
],
"includeHeaders": true,
"includeFooters": true
}
deno run --allow-read --allow-write scripts/generate-from-template.ts \
corporate-template.docx replacements.json output.docx
Create spec.json:
{
"title": "Quarterly Report",
"creator": "Finance Team",
"styles": {
"defaultFont": "Calibri",
"defaultFontSize": 11
},
"sections": [
{
"header": {
"paragraphs": [
{ "text": "Acme Corporation", "alignment": "right" }
]
},
"footer": {
"paragraphs": [
{ "text": "Confidential", "alignment": "center" }
]
},
"content": [
{
"text": "Q4 2024 Financial Report",
"heading": 1,
"alignment": "center"
},
{
"runs": [
{ "text": "Executive Summary: ", "bold": true },
{ "text": "This report provides an overview of our financial performance for Q4 2024." }
]
},
{ "pageBreak": true },
{
"text": "Revenue Breakdown",
"heading": 2
},
{
"rows": [
{
"cells": [
{ "content": [{ "text": "Category" }], "shading": "DDDDDD" },
{ "content": [{ "text": "Amount" }], "shading": "DDDDDD" },
{ "content": [{ "text": "Change" }], "shading": "DDDDDD" }
],
"isHeader": true
},
{
"cells": [
{ "content": [{ "text": "Product Sales" }] },
{ "content": [{ "text": "$1,250,000" }] },
{ "content": [{ "text": "+15%" }] }
]
},
{
"cells": [
{ "content": [{ "text": "Services" }] },
{ "content": [{ "text": "$750,000" }] },
{ "content": [{ "text": "+8%" }] }
]
}
],
"width": 100,
"borders": true
}
]
}
]
}
deno run --allow-read --allow-write scripts/generate-scratch.ts spec.json output.docx
Scenario: Generate contracts from a branded template.
Steps:
# 1. Analyze template for replaceable content
deno run --allow-read scripts/analyze-template.ts contract-template.docx --pretty
# 2. Create replacements.json with client data
# 3. Generate contract
deno run --allow-read --allow-write scripts/generate-from-template.ts \
contract-template.docx replacements.json acme-contract.docx
Scenario: Generate a data report with tables and formatting.
spec.json:
{
"title": "Sales Report",
"sections": [{
"content": [
{ "text": "Monthly Sales Report", "heading": 1 },
{ "text": "January 2025", "heading": 2 },
{
"runs": [
{ "text": "Total Sales: ", "bold": true },
{ "text": "$125,000", "color": "2E7D32" }
]
}
]
}]
}
Scenario: Create a formal letter with letterhead.
spec.json:
{
"sections": [{
"header": {
"paragraphs": [
{ "text": "ACME CORPORATION", "alignment": "center", "runs": [{"text": "ACME CORPORATION", "bold": true, "fontSize": 16}] },
{ "text": "123 Business Ave, City, ST 12345", "alignment": "center" }
]
},
"content": [
{ "text": "December 15, 2024", "alignment": "right" },
{ "text": "" },
{ "text": "Dear Valued Customer," },
{ "text": "" },
{ "text": "Thank you for your continued business..." },
{ "text": "" },
{ "text": "Sincerely," },
{ "text": "John Smith" },
{ "runs": [{ "text": "CEO", "italic": true }] }
],
"footer": {
"paragraphs": [
{ "text": "www.acme.com | [email protected]", "alignment": "center" }
]
}
}]
}
| Script | Purpose | Permissions |
|--------|---------|-------------|
| analyze-template.ts | Extract text, tables, placeholders from DOCX | --allow-read |
| generate-from-template.ts | Replace placeholders in templates | --allow-read --allow-write |
| generate-scratch.ts | Create DOCX from JSON specification | --allow-read --allow-write |
| Property | Type | Description |
|----------|------|-------------|
| text | string | Simple text content |
| runs | array | Formatted text runs (for mixed formatting) |
| heading | 1-6 | Heading level |
| alignment | string | left, center, right, justify |
| bullet | boolean | Bulleted list item |
| numbering | boolean | Numbered list item |
| spacing | object | before, after, line spacing |
| indent | object | left, right, firstLine indentation |
| pageBreakBefore | boolean | Insert page break before paragraph |
| Property | Type | Description |
|----------|------|-------------|
| text | string | Text content |
| bold | boolean | Bold formatting |
| italic | boolean | Italic formatting |
| underline | boolean | Underline formatting |
| strike | boolean | Strikethrough |
| fontSize | number | Font size in points |
| font | string | Font family name |
| color | string | Text color (hex, no #) |
| highlight | string | Highlight color |
| superScript | boolean | Superscript |
| subScript | boolean | Subscript |
| Property | Type | Description |
|----------|------|-------------|
| rows | array | Array of row specifications |
| width | number | Table width as percentage |
| borders | boolean | Show table borders |
| Property | Type | Description |
|----------|------|-------------|
| text | string | Link text |
| url | string | Target URL |
| bold | boolean | Bold formatting |
| italic | boolean | Italic formatting |
Symptoms: Output DOCX still contains {{PLACEHOLDER}} tags.
Solution:
analyze-template.ts to verify exact tag textincludeHeaders and includeFooters are true if placeholders are thereSymptoms: Replaced text doesn't match original formatting.
Solution:
Symptoms: Image elements are blank in output.
Solution:
Symptoms: Table cells have wrong content or formatting.
Solution:
content must be an array of paragraph specificationsshading for background color, verticalAlign for alignmentComprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Take jwynia/docx-generator from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.