Skip to content
Get packs

PDF Processing Guide

Lets an agent read, merge, split, rotate, create, OCR and fill PDF files using Python and command-line tools

Source Download skill
Repository
eigent-ai/eigent
Stars
15,719
Licence
Apache-2.0
Files
12 files

What it does

Once installed, the agent knows a step-by-step playbook for working with PDF files: pulling text and tables out of them, combining or splitting documents, rotating pages, adding watermarks, creating new PDFs, extracting images, and running OCR on scanned pages so they become searchable. For PDF forms, it points the agent to a separate guide and helper scripts that check whether a form has fillable fields, convert pages to images, and place entries onto the form.

Great for

  • Office workers who regularly merge, split or extract data from PDF reports and invoices
  • Developers building scripts that process PDFs in bulk
  • Anyone who needs to fill out PDF forms with an AI agent's help

Skip it if

  • Sensitive or confidential documents sent to a cloud agent, since the content is processed by whatever tools the agent runs (the skill itself does not send data over the internet)
  • Users who need certified or legally binding form handling, because the scripts are example code and results are not verified
  • Users without Python and the listed PDF libraries installed, since most steps will fail until those are set up

Try asking

  • “Merge these three PDFs into one file in the right order”
  • “Extract all tables from report.pdf into an Excel spreadsheet”
  • “Fill out the PDF application form using the data in this text file”
  • “Run OCR on this scanned PDF so I can search its text”
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 12 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 libraries and command-line tools before asking for PDF work, otherwise the agent will hit errors.
  • Review any generated output, especially filled forms and extracted tables, since the scripts are examples and may misplace data.
  • Keep original PDFs as backups before asking the agent to overwrite, rotate or encrypt files.

What's inside

  • forms.md
  • LICENSE.txt
  • reference.md
  • scripts/check_bounding_boxes.py
  • scripts/check_fillable_fields.py
  • scripts/convert_pdf_to_images.py
  • scripts/create_validation_image.py
  • scripts/extract_form_field_info.py
  • scripts/extract_form_structure.py
  • scripts/fill_fillable_fields.py
  • scripts/fill_pdf_form_with_annotations.py
  • SKILL.md

Redistributed unmodified from eigent-ai/eigent 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.