screen-capture

Automate screen captures and OCR analysis across macOS and Python.

14|4|Updated Dec 23, 2025
One-click install
npx skills add https://github.com/lotosbin/claude-skills --skill screen-capture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: screen-capture
Source: https://github.com/lotosbin/claude-skills/tree/main/.claude/skills/screen-capture
Command: npx skills add https://github.com/lotosbin/claude-skills --skill screen-capture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a unified approach to capturing screen content across macOS and Python-based tools, enabling OCR and image analysis without manual steps.

Core Features & Use Cases

  • Screen capture (macOS): Use the native screencapture tool for full-screen, region, and window captures.
  • Screen capture (Python): Cross-platform screenshot options via pyautogui, mss, and pyscreenshot.
  • Text extraction & analysis: OCR with pytesseract and image processing with PIL/OpenCV to extract and analyze on-screen content.
  • Use cases: Quickly capture design screens for review, extract on-screen text for indexing, and create visual data for reports.

Quick Start

Capture the current screen using your preferred method and save it for processing.

Frequently Asked Questions about screen-capture

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate screen capture and extract text from images on macOS?

Automate screen capture and OCR text extraction by using macOS screencapture for full-screen or region images, then applying pytesseract to extract on-screen text. This workflow eliminates manual screenshot steps and enables automated content indexing.

What is the best way to take cross-platform screenshots with Python?

Take cross-platform screenshots with Python using libraries like pyautogui, mss, or pyscreenshot. These tools allow you to capture screen content programmatically outside of macOS, providing a unified approach for automated image capture workflows.

How does OCR with pytesseract and OpenCV process captured screen images?

OCR with pytesseract and OpenCV processes captured screen images by using PIL and OpenCV for image processing and enhancement, then pytesseract extracts the text. This allows you to analyze on-screen content and extract text for indexing or reporting automatically.

Can I use Python to capture specific screen regions instead of the full screen?

Yes, you can capture specific screen regions instead of the full screen. The skill supports region captures alongside full-screen and window captures, utilizing macOS screencapture or Python libraries like pyautogui and mss to target specific areas of the display.

Does this screen capture approach work with macOS native screencapture and Python libraries together?

Yes, this screen capture approach works with macOS native screencapture and Python libraries together. It provides a unified approach to capturing screen content across macOS and Python-based tools, suitable for environments requiring both native and cross-platform automation.

When should I use macOS screencapture versus Python libraries like mss for screen capture?

Use macOS screencapture for native full-screen, window, or region captures on macOS environments. Choose Python libraries like mss, pyautogui, or pyscreenshot when you need cross-platform screenshot options or integrated Python-based image processing workflows.