How do I install the Word2pdf skill?

Run npx skillmds@latest add phanghonghao/word2pdf in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Word2pdf safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Word2pdf?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Word2pdf free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Word2pdf?

phanghonghao (@phanghonghao) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Word2pdf by phanghonghao — Agent Skill

Name: Word2pdf
Author: phanghonghao

Word2pdf

Convert Word (.doc / .docx) to PDF. Auto-detects binary .doc (OLE2) vs .docx (Office Open XML) via magic bytes, then converts using Microsoft Word COM or LibreOffice headless. Use when user mentions "word2pdf", "Word转PDF", "Word to PDF", "doc转PDF", "docx转PDF", or needs to convert a Word document to PDF.

phanghonghao Updated Sep 21, 2026

File contents

Word to PDF Converter

Convert Word documents (.doc / .docx) to PDF with automatic format detection.

When to Use

User mentions: "word2pdf", "Word转PDF", "Word to PDF", "doc转PDF", "docx转PDF"
Need to convert a Word document to PDF for sharing or submission
Need to check whether a file is .doc or .docx before converting

How It Works

Format Detection — reads first 8 bytes to identify:
- D0 CF 11 E0 ... → .doc (OLE2 Compound Binary Format)
- 50 4B 03 04 → .docx (ZIP / Office Open XML)
Conversion — tries in order:
- Microsoft Word COM automation (win32com) — best fidelity for both formats
- LibreOffice headless (soffice --headless) — fallback for both formats

Usage

python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" <input.doc|input.docx> [output.pdf]

Arguments

Argument	Required	Description
`input`	Yes	Input Word file path (.doc or .docx)
`output`	No	Output PDF path (default: same name with `.pdf` extension)

Examples

# Convert .docx (auto-detect format, output = input_name.pdf)
python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "report.docx"

# Convert .doc (legacy binary format)
python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "old_document.doc"

# Convert with custom output path
python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "report.docx" "output.pdf"

Dependencies

Primary: Microsoft Word (installed) + pywin32
```
python -m pip install pywin32
```
Fallback: LibreOffice (any recent version)

Workflow

Validate input file exists
Detect format via magic bytes (report .doc or .docx)
Try Microsoft Word COM conversion
If unavailable, try LibreOffice headless
Report output path, file size, and page count

Rules

Always use PYTHONIOENCODING=utf-8 on Windows
Report detected format to user before converting
Report any conversion warnings or errors
If neither Word nor LibreOffice is available, inform the user to install one

---name: word2pdfdescription: Convert Word (.doc / .docx) to PDF. Auto-detects binary .doc (OLE2) vs .docx (Office Open XML) via magic bytes, then converts using Microsoft Word COM or LibreOffice headless. Use when user mentions "word2pdf", "Word转PDF", "Word to PDF", "doc转PDF", "docx转PDF", or needs to convert a Word document to PDF.---# Word to PDF ConverterConvert Word documents (.doc / .docx) to PDF with automatic format detection.## When to Use- User mentions: "word2pdf", "Word转PDF", "Word to PDF", "doc转PDF", "docx转PDF"- Need to convert a Word document to PDF for sharing or submission- Need to check whether a file is .doc or .docx before converting## How It Works1. **Format Detection** — reads first 8 bytes to identify: - `D0 CF 11 E0 ...` → `.doc` (OLE2 Compound Binary Format) - `50 4B 03 04` → `.docx` (ZIP / Office Open XML)2. **Conversion** — tries in order: - Microsoft Word COM automation (`win32com`) — best fidelity for both formats - LibreOffice headless (`soffice --headless`) — fallback for both formats## Usage```bashpython "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" <input.doc|input.docx> [output.pdf]```### Arguments| Argument | Required | Description ||----------|----------|-------------|| `input` | Yes | Input Word file path (.doc or .docx) || `output` | No | Output PDF path (default: same name with `.pdf` extension) |### Examples```bash# Convert .docx (auto-detect format, output = input_name.pdf)python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "report.docx"# Convert .doc (legacy binary format)python "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "old_document.doc"# Convert with custom output pathpython "<LOCAL_USER>/.claude/skills/word2pdf/word2pdf.py" "report.docx" "output.pdf"```## Dependencies- **Primary**: Microsoft Word (installed) + `pywin32` ```bash python -m pip install pywin32 ```- **Fallback**: LibreOffice (any recent version)## Workflow1. Validate input file exists2. Detect format via magic bytes (report `.doc` or `.docx`)3. Try Microsoft Word COM conversion4. If unavailable, try LibreOffice headless5. Report output path, file size, and page count## Rules1. Always use `PYTHONIOENCODING=utf-8` on Windows2. Report detected format to user before converting3. Report any conversion warnings or errors4. If neither Word nor LibreOffice is available, inform the user to install one

Frequently asked questions