Screen capture taker

Ask for a screen, a window or a part of one. Get a saved screenshot.

Screen capture taker 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 · Apache 2.0 licence · Made by OpenAI · Level: beginner · Thinking: low

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

What it does

A saved screenshot of exactly what you asked for: the whole desktop, one app window, or a region of the screen. Say where to save it, or leave it out and the file goes to your system's default screenshot folder. If Claude only needs the image to look at, it goes in a temporary folder instead. The skill ships with ready scripts for Windows, Mac and Linux, so Claude does not have to work out the right command each time. On a Mac it first checks screen recording permission once, so you are not asked again and again. It prefers a browser or design tool's own capture where one exists, and uses this for desktop apps and full-screen shots.

You give it

What to capture (screen, app window or region)
A save path or file name (optional)
The app name for window shots (optional)

You get

A saved image file
The file path, so you can find it
A temporary copy when Claude only needs to look
Mac permission set up once

Use it when

You want a picture of a desktop app window saved to a folder you choose.
Claude needs to look at your screen to help debug something visual.
You need a capture of one region, not the whole display.
You want screenshots taken the same way on Windows, Mac and Linux.

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 capture your screen.