Skip to content
Get packs

PDF Processing Guide

Read, merge, split, rotate, watermark, encrypt, and OCR PDF files with Python and CLI tools

Source Download skill
Repository
aden-hive/hive
Stars
11,132
Licence
Apache-2.0
Files
2 files

What it does

Once installed, the agent knows a practical playbook for working with PDF files: pulling text and tables out of PDFs, combining or splitting documents, rotating pages, adding watermarks, password-protecting files, extracting images, OCR-ing scanned pages, and creating new PDFs with formatted text. It gives the agent ready-made Python and command-line snippets (pypdf, pdfplumber, reportlab, pytesseract, poppler-utils, qpdf) to run for these tasks. It also includes a warning about rendering subscript and superscript characters correctly in ReportLab PDFs.

Great for

  • Developers or analysts who need to batch-extract tables or text from PDF reports into spreadsheets
  • Office workers who want the agent to merge, split, or rotate PDFs without learning the tools
  • Anyone with scanned documents who wants text recovered via OCR

Skip it if

  • Users who need to remove a password from a PDF they do not own or have permission to open, since the skill shows how to decrypt files and that can enable misuse
  • Workflows requiring guaranteed accuracy on complex or legally sensitive documents, because text extraction and OCR can miss or misorder content and the guide does not describe verification steps
  • Environments where the agent cannot install Python packages or system tools, since most examples will fail without them

Try asking

  • “Merge these three PDF reports into one file called merged.pdf”
  • “Extract all tables from invoice.pdf and save them to an Excel spreadsheet”
  • “OCR this scanned contract and give me the text page by page”
  • “Split report.pdf so each page becomes its own PDF file”
Step-by-step guide: how to use PDF Processing GuideInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the Apache-2.0 licence and an attribution note.

    pdf.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pdf.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pdf.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Install the listed Python packages and command-line tools before asking for PDF work, otherwise examples will error out.
  • Only point the agent at PDFs you own or are authorized to modify, especially when asking for password removal.
  • Check important extracted text or tables against the original PDF, since OCR and table detection can introduce errors.

What's inside

  • REFERENCE.md
  • SKILL.md

Redistributed unmodified from aden-hive/hive under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.