1. Habit
  2. Skills
  3. PDF Processing skill
shareAI-lab · 170 installs

PDF Processing skill
Runs by itself, every time a new PDF arrives.

Every new PDF becomes text you can search.

Install the PDF Processing skill and make it a habit: follow https://gethabit.dev/skills/shareai-lab/pdf.md

  1. 1Copy
  2. 2Paste into Claude Code, Codex or Cursor
  3. 3It runs by itself

170 installs79K starsMIT licenceSource on GitHub ↗

PDF Processing

by shareAI-lab · 170 installs

The skill

Pulls the text out of PDF files, even scanned ones.

Only when you ask.

Time saved

Every new PDF becomes text you can search. Time saved, and nothing stays stuck in a file.

↻ Runs by itselfevery time a new PDF arrives

How the habit works.
You don't have to.

Three questionsWhen does it start? How does it check its work? What does it remember?

01

It starts by itself

new PDF added. Runs in Claude Code routine.

  • ↻ new PDF added
  • new .pdf in the inbox folder

02

It checks its work

text output non-empty. If a check fails, it tells you.

  • ✓pdftotext or PyMuPDF runs without error
  • ✓the output text file exists
  • ✓an empty extraction triggers an OCR fallback

03

It remembers

extraction log. The next run reads it first: PDFs already processed.

loops/pdf-text-extract-loop/log.md

One run, step by step.
Then it stops.

Stop ruleStops after the new PDFs of one run, at most 20 files.

  1. 01

    Check the tools

    Confirm pdftotext or PyMuPDF is installed before extracting.

  2. 02

    Extract text

    Run pdftotext to a file, or PyMuPDF page by page for large files.

  3. 03

    OCR if empty

    If extraction returns empty, use pytesseract OCR on the scanned pages.

  4. 04

    Write the output

    Write the text file and log the processed PDF.

What it may do.
Nothing more.

Safe by defaultIt writes only in its own folder and asks you before anything goes out.

Is it for you?
Use it when it fits.

Quick checkRead both lists. If the left one sounds like you, the PDF Processing skill helps.

Use it when

  • ✓ You extract text from a PDF
  • ✓ You create a PDF from Markdown
  • ✓ You merge or split PDFs

Skip it when

  • – You need to fill PDF form fields
  • – You need a designed, styled PDF layout

Questions

PDF Processing skill, answered.

What if a PDF is scanned?

If text extraction returns empty, the skill uses pytesseract OCR.

Can it also create or merge PDFs?

Yes. It can create from Markdown or HTML and merge or split with PyMuPDF.

How do I install the PDF Processing skill?

Copy the prompt at the top into your agent. It installs the skill from shareAI-lab/learn-claude-code and sets up the habit. Or run npx skills add shareAI-lab/learn-claude-code --skill pdf.

Is the PDF Processing skill free?

Yes. It is published under MIT. Habit is free too.

PDF Processing. Now as a habit.

Install the PDF Processing skill and make it a habit: follow https://gethabit.dev/skills/shareai-lab/pdf.md

  • Free
  • No account
  • Undo in one line

All shareAI-lab skills →More docs skills →

Works in

  • Claude Code
  • Codex
  • Cursor
  • ChatGPT
  • Claude app

Made by shareAI-lab, published under MIT. Habit links to the original and never changes it. Is this your skill?

Copying didn't work here. Select the line and copy it by hand.