PDF

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, a...

概要

The PDF Processing Guide is a specialized skill designed for AI agents like Claude and Codex, hosted within the anthropics/skills repository on GitHub. This tool enables agents to perform a wide range of document manipulation tasks. Capabilities include reading and extracting structured data such as text and tables, merging multiple files into a single document, and splitting existing PDFs. It also supports advanced formatting tasks like rotating pages, adding watermarks, and extracting embedded images. For document administration, the skill facilitates form filling along with encryption and decryption processes. By leveraging this resource from the anthropics/skills collection, which features over 150,000 stars, developers can integrate robust PDF handling into automated data workflows.

ユースケース

Extracting structured tables and text from financial reports for data analysis.
Merging multiple individual documents into a single, watermarked PDF file.
Automating the filling of PDF forms and applying encryption for secure distribution.

導入方法

# Review source first
open https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

セキュリティ

This skill includes functions for encrypting and decrypting PDF documents to manage file access. Users should ensure that any sensitive data processed through the agent complies with their specific organizational security policies and data handling requirements.

関連Skills