Skip to content
TakoAPI
Back to skills

screenshot-skill

by sunrddd-a11y

Coding Agents & IDEs
584Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Capture screenshots on Windows using mss and Pillow.

Description

What This Skill Does

Captures screenshots on Windows using mss and Pillow. Supports full-screen, region, and multi-monitor capture with output as a PIL Image, PNG file, or base64 string. Can be used as a Python module or CLI tool.

mss captures screens faster than most Python screenshot libraries, making it practical for high-frequency captures in desktop automation pipelines.

When to Use It

  • Capturing screen state before and after desktop automation steps
  • Sending live screen content to GPT-4o for visual analysis
  • Saving a cropped screen region during UI testing
  • Auto-saving numbered screenshots at each step of a recorded workflow
  • Getting monitor resolution and layout info for multi-display setups

Example Workflow

INPUT

User asks: take a screenshot and tell me what's on my screen

AGENT
  1. 1

    Initialize ScreenCapture context manager

  2. 2

    Capture full screen and encode to base64 JPEG at quality 85

  3. 3

    Send base64 image to OpenAI GPT-4o vision API with a description prompt

  4. 4

    Return the model's text description of the screen content

OUTPUT

A text description of the current screen content generated by the vision model

Installation

clawhub install sunrddd-a11y/screenshot-skill

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links