PDF Processing Skill
Teaches Claude to read, merge, split, extract tables from, OCR and generate PDFs with Python and CLI tools.
Docs & OfficeBeginner★ 1,125⑂ 109AI score 10/10Last updated: Sep 3, 2026
What it does
- Triggers on any
.pdfrequest and picks the right tool: pypdf for merge/split/rotate/encrypt, pdfplumber for text and table extraction, reportlab for creating PDFs, plus qpdf/pdftotext/pdfimages/pdftk on the command line. - Covers watermarking, metadata reading, password protection and removal, image extraction, and OCR of scanned PDFs via pdf2image + pytesseract.
- Includes hard-won gotchas, e.g. never use Unicode sub/superscript glyphs in ReportLab—use
<sub>/<super>markup instead. - Delegates form filling to FORMS.md and advanced/JS (pdf-lib) workflows to REFERENCE.md.
Who it's for
- Office, legal and finance users handling contracts, invoices and reports
- Analysts who need PDF tables turned into spreadsheets
- Developers automating PDF report generation
Example uses
- "Merge these five quote PDFs into one file" → pypdf loop or
qpdf --empty --pages - "Pull every table out of this financial report into Excel" → pdfplumber + pandas to
.xlsx - "Make this scanned contract searchable" → convert pages to images and run pytesseract OCR
· · · 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/fcakyon/claude-codex-settings/HEAD/plugins/anthropic-office-skills/skills/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 plugins/anthropic-office-skills/skills/pdf folder from the GitHub repo fcakyon/claude-codex-settings into my ~/.claude/skills/fcakyon-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/fcakyon/claude-codex-settings.git /tmp/ccs && mkdir -p ~/.claude/skills && cp -r /tmp/ccs/plugins/anthropic-office-skills/skills/pdf ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Clone the repository:
git clone https://github.com/fcakyon/claude-codex-settings.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r claude-codex-settings/plugins/anthropic-office-skills/skills/pdf ~/.claude/skills/ - Verify the companion docs exist:
ls ~/.claude/skills/pdf(expect REFERENCE.md and FORMS.md). - Install Python deps:
pip install pypdf pdfplumber reportlab pandas openpyxl pytesseract pdf2image - Install CLI tools (macOS:
brew install poppler qpdf tesseract; Ubuntu:sudo apt install poppler-utils qpdf tesseract-ocr). - Restart Claude Code and try a prompt like "extract the tables from this PDF"—the skill activates automatically.
View source on GitHub ↗License: Apache-2.0