A comprehensive OpenClaw skill for viewing, extracting, editing, and manipulating PDF files using Python libraries (pdfplumber, PyPDF2, and reportlab).

• 📄 Text Extraction - Extract text from entire PDFs or specific pages
• ✏️ Text Editing - Add text overlays to PDF pages with custom positioning and font size
• 📊 PDF Info - View metadata, page count, dimensions, and document properties
• 🔗 Merge PDFs - Combine multiple PDF files into one
• ✂️ Split PDFs - Split by individual pages or custom page ranges
• 🔄 Rotate Pages - Rotate pages at 90°, 180°, 270°, or -90° angles

Install required Python packages:

pip3 install pdfplumber PyPDF2 reportlab

1. Download pdf-tools-clawhub.zip
2. Extract to your OpenClaw skills directory:

   unzip pdf-tools-clawhub.zip -d ~/.openclaw/workspace/skills/
   mv ~/.openclaw/workspace/skills/pdf-tools-for-clawhub ~/.openclaw/workspace/skills/pdf-tools

3. The skill will be automatically loaded by OpenClaw

Simply ask your OpenClaw agent:

• "Extract text from this PDF"
• "Add 'CONFIDENTIAL' text to page 1"
• "Rotate pages 1-3 by 90 degrees"
• "Merge these 3 PDF files"
• "Split this PDF into separate pages"
• "Show me info about this PDF"

The agent will automatically use the appropriate script!

scripts/extract_text.py document.pdf
scripts/extract_text.py document.pdf -p 1 3 5
scripts/extract_text.py document.pdf -o output.txt

Add text overlay:

scripts/edit_text.py input.pdf -o output.pdf --overlay "New Text" --page 1 --x 100 --y 700
scripts/edit_text.py input.pdf -o output.pdf --overlay "Watermark" --page 1 --x 200 --y 400 --font-size 20

Replace text (limited due to PDF format complexity):

scripts/edit_text.py input.pdf -o output.pdf --replace "Old Text" "New Text"

Note: Text overlay is more reliable than replacement due to PDF format complexity.

scripts/pdf_info.py document.pdf
scripts/pdf_info.py document.pdf -f json

scripts/merge_pdfs.py file1.pdf file2.pdf file3.pdf -o merged.pdf

Split into individual pages:

scripts/split_pdf.py document.pdf -o output_dir/

Split by page ranges:

scripts/split_pdf.py document.pdf -o output_dir/ -m ranges -r "1-3,5-7,10-12"

scripts/rotate_pdf.py document.pdf -o rotated.pdf -r 90
scripts/rotate_pdf.py document.pdf -o rotated.pdf -r 180 -p 1 3 5

For detailed library documentation and advanced patterns, see references/libraries.md.

# Extract text
scripts/extract_text.py original.pdf -o extracted.txt
# Translate the text (using your preferred method)
# ...
# Create new PDF with translated text (requires custom script or reportlab)

# For each page, add overlay with watermark text
scripts/edit_text.py input.pdf -o watermarked.pdf --overlay "DRAFT" --page 1 --x 300 --y 400 --font-size 48

• Page numbers are 1-indexed in all scripts (page 1 = first page)
• Text extraction works best with text-based PDFs (not scanned images)
• Rotation angles must be 90, 180, 270, or -90 (counterclockwise)
• Text editing uses overlay method (more reliable) or simple replacement (limited)
• Cyrillic support requires fonts like DejaVuSans or Liberation (auto-detected)

• PDF text replacement is limited due to format complexity (encoding, positioning, fonts)
• For complex text editing, consider: extract → edit → regenerate PDF
• Scanned PDFs require OCR for text extraction (not included)

Found a bug or have a feature request? Please report it on the OpenClaw community forums or GitHub.

MIT License - feel free to modify and distribute.

Created by @cmpdchtr