PDF converter

Give it a PDF and the format you want. Get a faithful Markdown, HTML, Word or JSON copy with tables kept intact.

PDF converter 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 · CC BY 4.0 licence · Made by sickn33

Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.

What it does

A PDF turned into Markdown, HTML, Word or JSON that still reads like the original, with tables intact and labels still tied to their values. It matters when plain text extraction would scramble columns or lose which number belongs to which row. The skill sorts the PDF first: scanned, table-heavy, slide-based, medical, academic or multi-column. It then picks a route for the output you asked for, using opendataloader-pdf as the main converter and other tools to check, run OCR or repair noisy spots. It spot-checks sections against the page, retries with better settings if needed, and only then hands over the file. It runs as a command line tool and needs installing.

You give it

The PDF file
The output format you want
Pages to include (optional)
What matters most, such as tables or layout (optional)

You get

A converted file in your chosen format
Tables and labels kept together
A note on the PDF type and route used
Spot-check results on sample sections

Use it when

You have a table-heavy report PDF and need it in Markdown.
A scanned document needs OCR and then a Word copy.
You are feeding a PDF to an AI and need clean structured text.
A multi-column paper loses its reading order when you copy it.

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 read files.