PDF toolkit

Give it a PDF. Get text pulled out, pages merged, split, filled, redacted or checked, with the original kept safe.

PDF toolkit is a free AI skill for the job "Make documents, sheets and slides". Give the instructions to an AI assistant that supports the required files and tools, then review its output.

Free · No account · MIT licence · Made by Burhan Sebin · Level: beginner · Thinking: low

Made by Burhan Sebin. See the original on GitHub; we copied it as it is, with its licence.

What it does

Do what you need to a PDF, such as pull text, merge, split, fill forms, redact or check it, while the original stays untouched. Each run gives you proof, not a promise. The skill first confirms what you want, which pages count (human page labels often differ from physical page numbers), and whether the file is confidential. It records the source's hash and size, picks the tools you actually have, and writes new files to explicit paths. After the work it checks structure, content and how pages look, and reports hashes, page counts, tools used, OCR language and any limits. It never asks for private keys in chat. Needs PDF tools installed.

You give it

The source PDF or PDFs
The operation and page ranges
Output location and naming
OCR language (optional)
Whether the file is confidential

You get

New output files at stated paths
Hashes, sizes and page counts
An operation log
Checks for structure and appearance, with limits noted

Use it when

You need to merge several PDFs in a set order.
You must redact names from a contract and prove the text is gone.
A scanned file needs searchable text with the right OCR language.
You need to fill a form and check the result renders.

How to use it

Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
Ask for the job in your own words. Your AI opens the skill when it fits.
It works best when your AI can run code and save files.