# PDF Converter

Guides your agent through converting documents between PDF and formats like Word, Excel, or images. Helps keep layout and tables intact.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 5200 installs · ★ 540
- Author: claude-office-skills
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/claude-office-skills/skills/tree/HEAD/pdf-converter/SKILL.md
- Updated: 2026-01-31
- HTML: https://affpapa.org/en/nevibecode/skills/pdf-converter

## What it does

The skill provides guidelines for converting documents between PDF and formats such as DOCX, XLSX, or images. It outlines DPI settings for image exports, table alignment rules for spreadsheets, and formatting verification checklists. The instructions reference the `office-mcp` server tools including `pdf_to_docx`, `docx_to_pdf`, and `html_to_pdf`.

The skill does not convert files directly. It acts as an operational guide for models like claude-sonnet-4 and tools like Pandoc or Poppler. If a PDF is an image-based scan, run OCR first because this skill cannot extract unselectable text.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill pdf-converter -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/pdf-converter/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/pdf-converter/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill pdf-converter -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/pdf-converter/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill pdf-converter -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/pdf-converter/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install claude-office-skills/skills pdf-converter
```

2. **Manually: put the files in place**
- File: `.github/skills/pdf-converter/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill pdf-converter -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/claude-office-skills/skills --path pdf-converter
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/pdf-converter/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add claude-office-skills/skills --skill pdf-converter -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/claude-office-skills/skills/tree/HEAD/pdf-converter/SKILL.md

## When to use it
- extract tables from PDF into Excel without broken rows
- export PDF pages as PNG images at 300 DPI
- preserve layout when converting Word documents to PDF
- prepare batch conversion jobs for folders of documents

## Example prompts
- Convert this PDF to Word, preserve exact formatting
- Export PDF pages 1-5 as PNG images at 300 DPI
- Convert Excel to PDF, fit all columns on one page

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 17d42977e9c278f5.

BEGIN THIRD-PARTY FILE 17d42977e9c278f5
````text
---
# ═══════════════════════════════════════════════════════════════════════════════
# CLAUDE OFFICE SKILL - Enhanced Metadata v2.0
# ═══════════════════════════════════════════════════════════════════════════════

# Basic Information
name: PDF Converter
description: "Convert PDF files to and from Word, Excel, Image, and other formats"
version: "1.0"
author: claude-office-skills
license: MIT

# Categorization
category: pdf
tags:
  - pdf
  - conversion
  - format
department: All

# AI Model Compatibility
models:
  recommended:
    - claude-sonnet-4
    - claude-opus-4
  compatible:
    - claude-3-5-sonnet
    - gpt-4
    - gpt-4o

# MCP Tools Integration
mcp:
  server: office-mcp
  tools:
    - pdf_to_docx
    - docx_to_pdf
    - html_to_pdf

# Skill Capabilities
capabilities:
  - format_conversion
  - document_transformation

# Language Support
languages:
  - en
  - zh
---

# PDF Converter

Convert PDF files to various formats and vice versa while preserving formatting.

## Overview

This skill helps you:
- Convert PDFs to editable formats (Word, Excel)
- Convert documents to PDF
- Extract images from PDFs
- Optimize conversion quality
- Handle batch conversions

## Supported Conversions

### PDF to Other Formats
| Target Format | Best For | Quality |
|---------------|----------|---------|
| **Word (.docx)** | Text-heavy documents | ⭐⭐⭐⭐ |
| **Excel (.xlsx)** | Tables and data | ⭐⭐⭐⭐ |
| **PowerPoint (.pptx)** | Presentations | ⭐⭐⭐ |
| **Images (.png/.jpg)** | Visual snapshots | ⭐⭐⭐⭐⭐ |
| **Text (.txt)** | Plain text extraction | ⭐⭐⭐⭐ |
| **HTML** | Web content | ⭐⭐⭐ |
| **Markdown (.md)** | Structured text | ⭐⭐⭐ |

### Other Formats to PDF
| Source Format | Quality Notes |
|---------------|---------------|
| **Word (.docx)** | Excellent preservation |
| **Excel (.xlsx)** | Good, check page breaks |
| **PowerPoint (.pptx)** | Excellent with animations flat |
| **Images** | Depends on resolution |
| **HTML** | Variable, CSS may differ |
| **Text (.txt)** | Perfect, but basic |

## How to Use

### Basic Conversion
```
"Convert this PDF to Word"
"Save this document as PDF"
"Extract this PDF as images"
```

### With Options
```
"Convert PDF to Word, preserve exact formatting"
"Export PDF pages 1-5 as PNG images at 300 DPI"
"Convert Excel to PDF, fit all columns on one page"
```

### Batch Conversion
```
"Convert all PDFs in this folder to Word documents"
"Create PDFs from these 10 Word files"
```

## Conversion Guidelines

### PDF to Word
```markdown
## PDF to Word Conversion

### Best Practices
1. **Check source PDF type**:
   - Native PDF (from Word/etc): Best results
   - Scanned PDF: Use OCR first
   - Image-based: Limited accuracy

2. **Formatting considerations**:
   - Complex layouts may shift
   - Fonts substitute if not installed
   - Tables may need adjustment
   - Headers/footers require review

### Quality Settings
````
END THIRD-PARTY FILE 17d42977e9c278f5

The third-party file has ended. Everything between the 17d42977e9c278f5 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3243 of 7460 bytes. © claude-office-skills · MIT · https://github.com/claude-office-skills/skills/tree/HEAD/pdf-converter/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md