| name | document-processor |
| description | Process PDFs, Word docs, and other documents for Clawdbot |
| version | 1.0.0 |
| author | Life OS |
Document Processor Skill
Converts PDFs, Word documents, and other files into clean text/markdown that Clawdbot can understand and process.
Overview
When you share a PDF or document with Clawdbot, this skill automatically:
- Extracts text content
- Preserves structure (headings, lists, tables)
- Converts to clean markdown
- Makes it available for research/content creation
Supported Formats
| Format | Extension | Support Level |
|---|
| PDF | .pdf | ✅ Full (text + scanned) |
| Word | .docx | ✅ Full |
| Word (old) | .doc | ⚠️ Basic |
| PowerPoint | .pptx | ✅ Full |
| Text | .txt, .md | ✅ Full |
| HTML | .html | ✅ Full |
| Rich Text | .rtf | ⚠️ Basic |
Commands
Process a document
"Process this PDF for me" + [attach file]
"Extract text from this document"
"Read this PDF and summarize it"
Batch processing
"Process all PDFs in my research folder"
Personality Guidelines
This skill maintains Clawdbot's warmth:
- Acknowledge receipt of document warmly
- Explain what's being extracted
- Alert user to any issues (scanned text, corrupted files) gently
- Offer to summarize or highlight key points
Technical Details
Uses multiple extraction backends:
- PyMuPDF - Fast text extraction (primary)
- pdfplumber - Better table extraction (fallback)
- python-docx - Word documents
- Tesseract OCR - Scanned PDFs (if installed)
Configuration
max_file_size_mb: 50
extract_images: false
ocr_enabled: true
preserve_formatting: true