OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add claude-office-skills/skills --skill pdf-converter
Convert PDF files to and from Word, Excel, Image, and other formats
npx skills add claude-office-skills/skills --skill pdf-converter
Convert PDF files to various formats and vice versa while preserving formatting.
This skill helps you:
| 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 | ⭐⭐⭐ |
| 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 |
| Problem | Cause | Solution |
|---|---|---|
| Text not selectable | Scanned PDF | Apply OCR first |
| Missing characters | Font issues | Embed fonts or convert |
| Poor image quality | Low DPI | Use higher resolution |
| Large file size | Uncompressed | Apply compression |
| Lost formatting | Complex layout | Use "exact" mode |
After conversion, verify:
## 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
| Setting | Result |
|---------|--------|
| **Exact** | Matches layout precisely, harder to edit |
| **Editable** | Optimized for editing, may shift layout |
| **Text only** | Plain text, no formatting |
### Common Issues
| Issue | Solution |
|-------|----------|
| Text as image | Run OCR before converting |
| Missing fonts | Embed or substitute fonts |
| Broken tables | Manually adjust in Word |
| Lost colors | Check color profile settings |## PDF to Excel Conversion
### Ideal Sources
- PDF with clear table structure
- Financial statements
- Data reports
- Invoices with line items
### Extraction Methods
| Method | Use When |
|--------|----------|
| **Auto-detect tables** | Clear table borders |
| **Select area** | Tables without borders |
| **Full page** | Entire page is data |
### Quality Tips
1. Ensure PDF has selectable text (not scanned)
2. Clean table borders help detection
3. Merged cells may cause issues
4. Multi-page tables need manual merge
### Data Cleanup
After conversion, check:
- [ ] Column alignment
- [ ] Number formatting
- [ ] Date formats
- [ ] Merged cell handling
- [ ] Header row detection## PDF to Image Conversion
### Resolution Settings
| DPI | Use Case | File Size |
|-----|----------|-----------|
| 72 | Screen viewing | Small |
| 150 | Email/web | Medium |
| 300 | Print quality | Large |
| 600 | High-quality print | Very large |
### Format Selection
| Format | Best For |
|--------|----------|
| **PNG** | Text, graphics, transparency |
| **JPG** | Photos, smaller files |
| **TIFF** | Print production |
| **WebP** | Web optimization |
### Output Options
- All pages → separate images
- Specific pages → selected images
- Page range → batch export## Converting to PDF
### From Word
**Settings**:
- [ ] Embed fonts
- [ ] Include bookmarks
- [ ] Set PDF/A for archival
- [ ] Compress images (optional)
### From Excel
**Settings**:
- [ ] Define print area
- [ ] Set page breaks
- [ ] Choose orientation
- [ ] Fit to page options
### From PowerPoint
**Settings**:
- [ ] Slide range
- [ ] Include notes (optional)
- [ ] Quality level
- [ ] Handout format (optional)
### Universal Tips
1. Review in print preview first
2. Check page breaks
3. Ensure fonts are embedded
4. Verify hyperlinks work## Batch Conversion Job
**Source**: [Folder path]
**Target Format**: [Format]
**Output Folder**: [Path]
### Files to Convert
| File | Pages | Status |
|------|-------|--------|
| document1.pdf | All | ✅ Complete |
| document2.pdf | All | ✅ Complete |
| document3.pdf | 1-5 | ⏳ Processing |
### Settings Applied
- Resolution: [X] DPI
- Quality: [High/Medium/Low]
- Naming: [Original name]_converted.[ext]
### Summary
- Total files: [X]
- Successful: [Y]
- Failed: [Z]