PDF Processing Toolkit
A comprehensive PDF skill for extracting text and tables, creating PDFs, merging/splitting, watermarking, and filling forms.
Docs & OfficeIntermediate★ 150⑂ 10AI score 10/10Last updated: Aug 17, 2026
What it does
- Text & table extraction: pdfplumber recipes for layout-preserving text and tables, exported to pandas/Excel
- Document manipulation: pypdf for merge, split, rotate, metadata, watermarks, and encryption
- PDF creation: reportlab Canvas and Platypus flows for multi-page reports
- CLI recipes: pdftotext, qpdf, pdftk, pdfimages one-liners
- Deep-dive references: complex tables (tables.md), scanned-doc OCR (ocr.md), form filling (forms.md), advanced/troubleshooting (reference.md)
Who it's for
- Ops, finance, and legal staff who handle contracts, invoices, and reports as PDFs
- Developers and data engineers automating PDF pipelines
- Analysts pulling structured data out of scanned documents
Examples
- "Extract every table from these 30 invoice PDFs into one Excel sheet" → pdfplumber + pandas flow
- "Read the text from this scanned contract" → pdf2image + pytesseract OCR path (ocr.md)
- "Generate a 2-page report PDF and stamp our watermark on it" → reportlab build, then pypdf merge_page
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/appautomaton/document-SKILLs/HEAD/pdf/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the pdf folder from the GitHub repo appautomaton/document-SKILLs into my ~/.claude/skills/appautomaton-pdf/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/appautomaton/document-SKILLs.git && mkdir -p ~/.claude/skills && cp -r document-SKILLs/pdf ~/.claude/skills/pdf⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and go to your home directory:
cd ~ - Clone the repo:
git clone https://github.com/appautomaton/document-SKILLs.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the whole pdf folder (including the referenced md files):
cp -r document-SKILLs/pdf ~/.claude/skills/pdf - Install system tools — macOS:
brew install poppler qpdf tesseract; Ubuntu:sudo apt-get install poppler-utils qpdf tesseract-ocr - Install
uvso Python dependencies resolve automatically:curl -LsSf https://astral.sh/uv/install.sh | sh - Restart Claude Code and try a prompt like "extract the tables from this PDF".
View source on GitHub ↗License: MIT