pdf Skill (Anthropic): Read, Merge, Fill and Create PDFs

Lets Claude read, merge, split, fill, watermark and create PDF files, using Python libraries and command-line tools.

Installs: 221.1K; on skills.sh
Stars: 186.4K; on GitHub
Files: 11; besides SKILL.md
Updated: Oct 2026; last repo commit

The skill triggers whenever you mention a .pdf file or ask for one. It guides Claude through reading and extracting text or tables, merging and splitting, rotating pages, adding watermarks, creating new PDFs, filling forms, encrypting or decrypting, extracting images, and OCR on scanned files.

It uses pypdf, pdfplumber and reportlab, plus command-line tools pdftotext, qpdf and pdftk, and pytesseract for OCR. Form filling has its own guide, forms.md, which runs 8 bundled Python scripts. The license is proprietary and the README calls the document skills source-available, so check LICENSE.txt in the repo before you reuse it.

Good for

Anyone who works with PDFs and wants Claude to extract tables or text
Teams filling the same PDF forms again and again
Developers who need PDF tasks scripted with pypdf and pdfplumber

Install pdf

Claude Code

Copy this prompt.

Install the pdf skill in Claude Code. Run this command:

npx skills add https://github.com/anthropics/skills --skill pdf

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Sections in SKILL.md

Overview
Quick Start
Python Libraries
pypdf - Basic Operations
pdfplumber - Text and Table Extraction
reportlab - Create PDFs
Command-Line Tools
pdftotext (poppler-utils)
qpdf
pdftk (if available)
Common Tasks
Extract Text from Scanned PDFs
Add Watermark
Extract Images
Password Protection
Quick Reference

Key facts

Author: Anthropic
License: Proprietary; see LICENSE.txt in the skill folder
Installs on skills.sh: 221,065 (Nov 2, 2026)
GitHub stars: 186,362 for the anthropics/skills repo (Nov 2, 2026)
Last repo commit: Oct 28, 2026
What installs: SKILL.md, LICENSE.txt, forms.md, reference.md and 8 Python scripts for form fields and images (11 bundled files)
Needs: Python with pypdf, pdfplumber and reportlab; poppler-utils, qpdf and pytesseract for the tools that use them

What it includes

Merge, split, rotate pages, read metadata, password-protect
The basic operations library.
Write · pypdf
Extract text with layout and tables, with a pandas path to Excel
The skill's quick reference names it for text and table extraction.
Files · pdfplumber
Create new PDFs, including multi-page files and sub/superscripts
Write · reportlab
Command-line text extraction, merge, split, rotate and decrypt
pdftotext comes from poppler-utils. pdftk is used if available.
Runs code · pdftotext, qpdf, pdftk
Converts pages to images, then runs pytesseract
Needs pytesseract and pdf2image installed.
Runs code · OCR on scanned PDFs
Common tasks with ready code for each
Write · Watermark, extract images, password
Fill PDF forms using 8 bundled scripts for fields, bounding boxes and annotations
Fillable-field checks, field info extraction, filling, and a validation image.
Runs code · forms.md and form scripts
Advanced pypdfium2, JavaScript pdf-lib and troubleshooting notes
Read · reference.md

From the official docs

Permissions

Low risk

The skill runs Python and command-line tools on your PDFs and writes new files. Work on copies of important documents.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It runs Python scripts and command-line tools
Approve commands in your client, and keep originals safe because it writes new and merged files.
It can encrypt, decrypt and password-protect PDFs
Keep any password out of shared chats and logs.

Questions

What does the pdf skill do?

It tells Claude how to handle PDFs: extract text and tables, merge, split, rotate, watermark, create, fill forms, encrypt, pull images and OCR scans.

How do I install it in Claude Code, the Claude app or Codex?

Use the install box above. The anthropics/skills README also lists a Claude Code plugin route (/plugin install document-skills@anthropic-agent-skills) and says its example skills are already available to paid plans in Claude.ai.

Does it need an API key?

SKILL.md mentions none. It runs local Python and command-line tools, and you may need to install the libraries it names.

Is it free to use?

The SKILL.md lists the license as proprietary and points to LICENSE.txt for the terms. The repo README calls the document skills source-available, not open source. Read LICENSE.txt before reuse.

Is it safe?

It runs Python and command-line tools on files you point at and writes new PDFs, including merged, split and password-protected copies. Work on copies of important files.

Can it fill in PDF forms?

Yes. The SKILL.md sends form tasks to forms.md, which uses 8 bundled scripts to check fillable fields and fill them.

Information

updated Nov 2, 2026

Repository: anthropics/skills
Folder: skills/pdf

anthropics/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 3

anthropics/skills pdf SKILL.md · github.com
anthropics/skills README · github.com
pdf forms.md · github.com