Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

minimax-docx · minimax-ai — Claude Code DOCX skill: create, edit, format

A skill for generating, filling and formatting Word documents with OpenXML SDK. Use it when the agent must deliver a .docx, not plain text.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add MiniMax-AI/skills --skill minimax-docx -a claude-code
Open on GitHub

What minimax-docx does

minimax-docx handles everything .docx: creating files from scratch, editing existing ones, applying template formatting. Three pipelines route the work — A for new documents, B for filling and editing, C for template application.

Simple jobs go through CLI commands like create or edit replace-text. Structural work — custom styles, multi-section layouts, headers and footers, TOC, images — needs direct C# on OpenXML SDK, because the CLI does not cover it. The skill insists on reading Samples/*.cs before writing any C#: those files contain version-verified patterns.

First run requires scripts/setup.sh, and each session starts with scripts/env_check.sh. If it reports NOT READY, stop. Pipeline C adds a hard gate: the output must pass XSD validation against assets/xsd/business-rules.xsd before delivery. That means quick one-shot document generation is not the path here.

What it helps with

  • Build a new .docx with TOC, headers and custom styles
  • Fill placeholders in a contract or report template
  • Reformat a document to match another template's style
  • Convert .doc to .docx before processing
  • Analyze document structure before editing

Example prompts for the agent

  • Create a report from this data and save it as DOCX
  • Fill this contract template: client name, date, amount
  • Apply the formatting from this file to my document

How to install minimax-docx

1Skills CLI (Vercel)

npx skills add MiniMax-AI/skills --skill minimax-docx -a claude-code

2Manually: put the files in place

~/.claude/skills/minimax-docx/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/minimax-docx/

From the same set17

The whole set →
pptx-generator MiniMax-AI A skill to read, edit, and build PowerPoint decks from scratch using PptxGenJS and XML workflows. Useful when generating presentations from code or extracting slide text. Claude Code CX Codex Cursor +1 6,000installs minimax-xlsx MiniMax-AI Skill to create, read, edit, and validate Excel files (.xlsx, .xlsm, .csv, .tsv) directly in code. Use it when you need to build a financial model, add calculated columns, or fix broken formulas while preserving formatting and macros. Claude Code CX Codex Cursor +1 3,800installs minimax-pdf MiniMax-AI Generates professional PDFs with visual identity: reports, resumes, portfolios. Design is derived from document type, with consistent color and typography throughout. Claude Code CX Codex Cursor +1 3,800installs fullstack-dev MiniMax-AI Guides full-stack backend architecture and frontend integration. It enforces a structured checklist from requirement gathering to verification smoke tests. Claude Code CX Codex Cursor +1 3,400installs frontend-dev MiniMax-AI Orchestrates frontend development, motion design, AI-generated media, and conversion copy. Built for landing pages, marketing sites, and dashboards. Claude Code CX Codex Cursor +1 3,200installs vision-analysis MiniMax-AI Describes images, extracts text, and reviews UI mockups using the MiniMax vision MCP tool. Handy when an agent needs to understand a screenshot or design file. Claude Code CX Codex Cursor +1 2,700installs android-native-dev MiniMax-AI Guides AI agents through native Android development: project scaffolding, Gradle setup, Jetpack Compose dependencies, and product flavors. Claude Code CX Codex Cursor +1 2,700installs shader-dev MiniMax-AI GLSL reference skill covering 36 real-time shader techniques for ShaderToy and WebGL2. Helpful for ray marching, SDF scenes, fluids, and visual effects. Claude Code CX Codex Cursor +1 2,500installs

Other versions of minimax-docx

Similar

month-end-prep official anthropics Reconciles QuickBooks, Xero, Zoho Books, NetSuite, or MYOB against PayPal, Shopify, Square, and Stripe settlements, surfaces discrepancies and duplicates, writes a P&L summary, and exports the close packet as xlsx and PDF. Claude Code CX Codex Cursor +1 1,700installs job-post-builder official anthropics Generates hiring packets with job descriptions, structured interview guides, and offer letter templates from a brief role intake. Claude Code CX Codex Cursor +1 1,700installs rhwp-edit NomaDamas Edits HWP documents directly from the coding assistant: inserts text, runs search-and-replace, builds tables, and updates cell values. Claude Code CX Codex Cursor +1 6,600installs resume-builder reactive-resume Builds resumes as Reactive Resume JSON through conversation with your agent. Asks for missing details instead of inventing them. Claude Code CX Codex Cursor +1 560installs pptx official anthropics This skill helps create, read, and edit .pptx files and .potx templates. Use it when building a deck or extracting slide text. Claude Code Claude.ai 241,433installs pdf official anthropics This skill lets an agent read, create, and edit PDF files, including forms and scanned documents. Use it when PDF work is part of the task. Claude Code Claude.ai 216,041installs docx official anthropics This skill creates, reads, and edits Word documents and templates. Use it for reports, letters, and files that need headings, tables, or page numbers. Claude Code Claude.ai 206,304installs xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. Claude Code Claude.ai 187,223installs

Questions about minimax-docx

How do I install minimax-docx in Claude Code?

Run npx skills add MiniMax-AI/skills --skill minimax-docx -a claude-code. The skill lands in ~/.claude/skills/minimax-docx/SKILL.md.

What does minimax-docx do?

Creates, edits and formats Word documents via OpenXML SDK (.NET). Three scenarios: creating new files, filling existing ones, and applying templates with XSD validation.

What do I need before the first run?

Run scripts/setup.sh first (or scripts/setup.ps1 on Windows; --minimal skips optional dependencies). At the start of each session run scripts/env_check.sh — if it says NOT READY, do not proceed.

Source text

SKILL.md · MIT
---
name: minimax-docx
license: MIT
metadata:
  version: "1.0.0"
  category: document-processing
  author: MiniMaxAI
  sources:
    - "ECMA-376 Office Open XML File Formats"
    - "GB/T 9704-2012 Layout Standard for Official Documents"
    - "IEEE / ACM / APA / MLA / Chicago / Turabian Style Guides"
    - "Springer LNCS / Nature / HBR Document Templates"
description: >
  Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET).
  Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing
  documents, (C) apply template formatting with XSD validation gate-check.
  MUST use this skill whenever the user wants to produce, modify, or format a Word document —
  including when they say "write a report", "draft a proposal", "make a contract",
  "fill in this form", "reformat to match this template", or any task whose final output
  is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task
  implies a printable/formal document, use this skill.
triggers:
  - Word
  - docx
  - document
  - 文档
  - Word文档
  - 报告
  - 合同
  - 公文
  - 排版
  - 套模板
---

# minimax-docx

Create, edit, and format DOCX documents via CLI tools or direct C# scripts built on OpenXML SDK (.NET).

## Setup

**First time:** `bash scripts/setup.sh` (or `powershell scripts/setup.ps1` on Windows, `--minimal` to skip optional deps).

**First operation in session:** `scripts/env_check.sh` — do not proceed if `NOT READY`. (Skip on subsequent operations within the same session.)

## Quick Start: Direct C# Path

When the task requires structural document manipulation (custom styles, complex tables, multi-section layouts, headers/footers, TOC, images), write C# directly instead of wrestling with CLI limitations. Use this scaffold:

```csharp
// File: scripts/dotnet/task.csx  (or a new .cs in a Console project)
// dotnet run --project scripts/dotnet/MiniMaxAIDocx.Cli -- run-script task.csx
#r "nuget: DocumentFormat.OpenXml, 3.2.0"

using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

using var doc = WordprocessingDocument.Create("output.docx", WordprocessingDocumentType.Document);
var mainPart = doc.AddMainDocumentPart();
mainPart.Document = new Document(new Body());

// --- Your logic here ---
// Read the relevant Samples/*.cs file FIRST for tested patterns.
// See Samples/ table in References section below.
```

**Before writing any C#, read the relevant `Samples/*.cs` file** — they contain compilable, SDK-version-verified patterns. The Samples table in the References section below maps topics to files.

## CLI shorthand

All CLI commands below use `$CLI` as shorthand for:
```bash
dotnet run --project scripts/dotnet/MiniMaxAIDocx.Cli --
```

## Pipeline routing

Route by checking: does the user have an input .docx file?

```
User task
├─ No input file → Pipeline A: CREATE
│   signals: "write", "create", "draft", "generate", "new", "make a report/proposal/memo"
│   → Read references/scenario_a_create.md
│
└─ Has input .docx
    ├─ Replace/fill/modify content → Pipeline B: FILL-EDIT
    │   signals: "fill in", "replace", "update", "change text", "add section", "edit"
    │   → Read references/scenario_b_edit_content.md
    │
    └─ Reformat/apply style/template → Pipeline C: FORMAT-APPLY
        signals: "reformat", "apply template", "restyle", "match this format", "套模板", "排版"
        ├─ Template is pure style (no content) → C-1: OVERLAY (apply styles to source)
        └─ Template has structure (cover/TOC/example sections) → C-2: BASE-REPLACE
            (use template as base, replace example content with user content)
        → Read references/scenario_c_apply_template.md
```

If the request spans multiple pipelines, run them sequentially (e.g., Create then Format-Apply).

## Pre-processing

Convert `.doc` → `.docx` if needed: `scripts/doc_to_docx.sh input.doc output_dir/`

Preview before editing (avoids reading raw XML): `scripts/docx_preview.sh document.docx`

Analyze structure for editing scenarios: `$CLI analyze --input document.docx`

## Scenario A: Create

Read `references/scenario_a_create.md`, `references/typography_guide.md`, and `references/design_principles.md` first. Pick an aesthetic recipe from `Samples/AestheticRecipeSamples.cs` that matches the document type — do not invent formatting values. For CJK, also read `references/cjk_typography.md`.

**Choose your path:**
- **Simple** (plain text, minimal formatting): use CLI — `$CLI create --type report --output out.docx --config content.json`
- **Structural** (custom styles, multi-section, TOC, images, complex tables): write C# directly. Read the relevant `Samples/*.cs` first.

CLI options: `--type` (report|letter|memo|academic), `--title`, `--author`, `--page-size` (letter|a4|legal|a3), `--margins` (standard|narrow|wide), `--header`, `--footer`, `--page-numbers`, `--toc`, `--content-json`.

Then run the **validation pipeline** (below).

## Scenario B: Edit / Fill

Read `references/scenario_b_edit_content.md` first. Preview → analyze → edit → validate.

**Choose your path:**
- **Simple** (text replacement, placeholder fill): use CLI subcommands.
- **Structural** (add/reorganize sections, modify styles, manipulate tables, insert images): write C# directly. Read `references/openxml_element_order.md` and the relevant `Samples/*.cs`.

Available CLI edit subcommands:
- `replace-text --find "X" --replace "Y"`
- `fill-placeholders --data '{"key":"value"}'`
- `fill-table --data table.json`
- `insert-section`, `remove-section`, `update-header-footer`

```bash
$CLI edit replace-text --input in.docx --output out.docx --find "OLD" --replace "NEW"
$CLI edit fill-placeholders --input in.docx --output out.docx --data '{"name":"John"}'
```

Then run the **validation pipeline**. Also run diff to verify minimal changes:
```bash
$CLI diff --before in.docx --after out.docx
```

## Scenario C: Apply Template

Read `references/scenario_c_apply_template.md` first. Preview and analyze both source and template.

```bash
$CLI apply-template --input source.docx --template template.docx --output out.docx
```

For complex template operations (multi-template merge, per-section headers/footers, style merging), write C# directly — see Critical Rules below for required patterns.

Run the **validation pipeline**, then the **hard gate-check**:
```bash
$CLI validate --input out.docx --gate-check assets/xsd/business-rules.xsd
```
Gate-check is a **hard requirement**. Do NOT deliver until it passes. If it fails: diagnose, fix, re-run.

Also diff to verify content preservation: `$CLI diff --before source.docx --after out.docx`

## Validation pipeline

Run after every write operation. For Scenario C the full pipeline is **mandatory**; for A/B it is **recommended** (skip only if the operation was trivially simple).

```bash
$CLI merge-runs --input doc.docx                                    # 1. consolidate runs
$CLI validate --input doc.docx --xsd assets/xsd/wml-subset.xsd     # 2. XSD structure
$CLI validate --input doc.docx --business                           # 3. business rules
```

If XSD fails, auto-repair and retry:
```bash
$CLI fix-order --input doc.docx
$CLI validate --input doc.docx --xsd assets/xsd/wml-subset.xsd
```

If XSD still fails, fall back to business rules + preview:
```bash
$CLI validate --input doc.docx --business
scripts/docx_preview.sh doc.docx
# Verify: font contamination=0, table count correct, drawing count correct, sectPr count correct
```

Final preview: `scripts/docx_preview.sh doc.docx`

## Critical rules

These prevent file corruption — OpenXML is strict about element ordering.

**Element order** (properties always first):

| Parent | Order |
|--------|-------|
| `w:p`  | `pPr` → runs |
| `w:r`  | `rPr` → `t`/`br`/`tab` |
| `w:tbl`| `tblPr` → `tblGrid` → `tr` |
| `w:tr` | `trPr` → `tc` |
| `w:tc` | `tcPr` → `p` (min 1 `<w:p/>`) |
| `w:body` | block content → `sectPr` (LAST child) |

**Direct format contamination:** When copying content from a source document, inline `rPr` (fonts, color) and `pPr` (borders, shading, spacing) override template styles. Always strip direct formatting — keep only `pStyle` reference and `t` text. Clean tables too (including `pPr/rPr` inside cells).

**Track changes:** `<w:del>` uses `<w:delText>`, never `<w:t>`. `<w:ins>` uses `<w:t>`, never `<w:delText>`.

**Font size:** `w:sz` = points × 2 (12pt → `sz="24"`). Margins/spacing in DXA (1 inch = 1440, 1cm ≈ 567).

**Heading styles MUST have OutlineLevel:** When defining heading styles (Heading1, ThesisH1, etc.), always include `new OutlineLevel { Val = N }` in `StyleParagraphProperties` (H1→0, H2→1, H3→2). Without this, Word sees them as plain styled text — TOC and navigation pane won't work.

**Multi-template merge:** When given multiple template files (font, heading, breaks), read `references/scenario_c_apply_template.md` section "Multi-Template Merge" FIRST. Key rules:
- Merge styles from all templates into one styles.xml. Structure (sections/breaks) comes from the breaks template.
- Each content paragraph must appear exactly ONCE — never duplicate when inserting section breaks.
- NEVER insert empty/blank paragraphs as padding or section separators. Output paragraph count must equal input. Use section break properties (`w:sectPr` inside `w:pPr`) and style spacing (`w:spacing` before/after) for visual separation.
- Insert oddPage section breaks before EVERY chapter heading, not just the first. Even if a chapter has dual-column content, it MUST start with oddPage; use a second continuous break after the heading for column switching.
- Dual-column chapters need THREE section breaks: (1) oddPage in preceding para's pPr, (2) continuous+cols=2 in the chapter HEADING's pPr, (3) continuous+cols=1 in the last body para's pPr to revert.
- Copy `titlePg` settings from the breaks template for EACH section. Abstract and TOC sections typically need `titlePg=true`.

**Multi-section headers/footers:** Templates with 10+ sections (e.g., Chinese thesis) have DIFFERENT headers/footers per section (Roman vs Arabic page numbers, different header text per zone). Rules:
- Use C-2 Base-Replace: copy the TEMPLATE as output base, then replace body content. This preserves all sections, headers, footers, and titlePg settings automatically.
- NEVER recreate headers/footers from scratch — copy template header/footer XML byte-for-byte.
- NEVER add formatting (borders, alignment, font size) not present in the template header XML.
- Non-cover sections MUST have header/footer XML files (at least empty header + page number footer).
- See `references/scenario_c_apply_template.md` section "Multi-Section Header/Footer Transfer".

## References

Load as needed — don't load all at once. Pick the most relevant files for the task.

**The C# samples and design references below are the project's knowledge base ("encyclopedia").** When writing OpenXML code, ALWAYS read the relevant sample file first — it contains compilable, SDK-version-verified patterns that prevent common errors. When making aesthetic decisions, read the design principles and recipe files — they encode tested, harmonious parameter sets from authoritative sources (IEEE, ACM, APA, Nature, etc.), not guesses.

### Scenario guides (read first for each pipeline)

| File | When |
|------|------|
| `references/scenario_a_create.md` | Pipeline A: creating from scratch |
| `references/scenario_b_edit_content.md` | Pipeline B: editing existing content |
| `references/scenario_c_apply_template.md` | Pipeline C: applying template formatting |

### C# code samples (compilable, heavily commented — read when writing code)

| File | Topic |
|------|-------|
| `Samples/DocumentCreationSamples.cs` | Document lifecycle: create, open, save, streams, doc defaults, settings, properties, page setup, multi-section |
| `Samples/StyleSystemSamples.cs` | Styles: Normal/Heading chain, character/table/list styles, DocDefaults, latentStyles, CJK 公文, APA 7th, import, resolve inheritance |
| `Samples/CharacterFormattingSamples.cs` | RunProperties: fonts, size, bold/italic, all underlines, color, highlight, strike, sub/super, caps, spacing, shading, border, emphasis marks |
| `Samples/ParagraphFormattingSamples.cs` | ParagraphProperties: justification, indentation, line/paragraph spacing, keep/widow, outline level, borders, tabs, numbering, bidi, frame |
| `Samples/TableSamples.cs` | Tables: borders, grid, cell props, margins, row height, header repeat, merge (H+V), nested, floating, three-line 三线表, zebra striping |
| `Samples/HeaderFooterSamples.cs` | Headers/footers: page numbers, "Page X of Y", first/even/odd, logo image, table layout, 公文 "-X-", per-section |
| `Samples/ImageSamples.cs` | Images: inline, floating, text wrapping, border, alt text, in header/table, replace, SVG fallback, dimension calc |
| `Samples/ListAndNumberingSamples.cs` | Numbering: bullets, multi-level decimal, custom symbols, outline→headings, legal, Chinese 一/(一)/1./(1), restart/continue |
| `Samples/FieldAndTocSamples.cs` | Fields: TOC, SimpleField vs complex field, DATE/PAGE/REF/SEQ/MERGEFIELD/IF/STYLEREF, TOC styles |
| `Samples/FootnoteAndCommentSamples.cs` | Footnotes, endnotes, comments (4-file system), bookmarks, hyperlinks (internal + external) |
| `Samples/TrackChangesSamples.cs` | Revisions: insertions (w:t), deletions (w:delText!), formatting changes, accept/reject all, move tracking |
| `Samples/AestheticRecipeSamples.cs` | 13 aesthetic recipes from authoritative sources: ModernCorporate, AcademicThesis, ExecutiveBrief, ChineseGovernment (GB/T 9704), MinimalModern, IEEE Conference, ACM sigconf, APA 7th, MLA 9th, Chicago/Turabian, Springer LNCS, Nature, HBR — each with exact values from official style guides |

Note: `Samples/` path is relative to `scripts/dotnet/MiniMaxAIDocx.Core/`.

### Markdown references (read when you need specifications or design rules)

| File | When |
|------|------|
| `references/openxml_element_order.md` | XML element ordering rules (prevents corruption) |
| `references/openxml_units.md` | Unit conversion: DXA, EMU, half-points, eighth-points |
| `references/openxml_encyclopedia_part1.md` | Detailed C# encyclopedia: document creation, styles, character & paragraph formatting |
| `references/openxml_encyclopedia_part2.md` | Detailed C# encyclopedia: page setup, tables, headers/footers, sections, doc properties |
| `references/openxml_encyclopedia_part3.md` | Detailed C# encyclopedia: TOC, footnotes, fields, track changes, comments, images, math, numbering, protection |
| `references/typography_guide.md` | Font pairing, sizes, spacing, page layout, table design, color schemes |
| `references/cjk_typography.md` | CJK fonts, 字号 sizes, RunFonts mapping, GB/T 9704 公文 standard |
| `references/cjk_university_template_guide.md` | Chinese university thesis templates: numeric styleIds (1/2/3 vs Heading1), document zone structure (cover→abstract→TOC→body→references), font expectations, common mistakes |
| `references/design_principles.md` | **Aesthetic foundations**: 6 design principles (white space, contrast/scale, proximity, alignment, repetition, hierarchy) — teaches WHY, not just WHAT |
| `references/design_good_bad_examples.md` | **Good vs Bad comparisons**: 10 categories of typography mistakes with OpenXML values, ASCII mockups, and fixes |
| `references/track_changes_guide.md` | Revision marks deep dive |
| `references/troubleshooting.md` | **Symptom-driven fixes**: 13 common problems indexed by what you SEE (headings wrong, images missing, TOC broken, etc.) — search by symptom, find the fix |

© MiniMaxAI · MIT · MiniMax-AI/skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor