본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

screen-vision

ls18166407597-design 제작

AI & LLMs
—아직 평가 없음
내 평가

요약

macOS Local OCR & Automation Tool using Vision Framework.

설명

이 스킬이 하는 일

A macOS tool that runs OCR on screen content using Apple's built-in Vision framework. It extracts text and [X, Y] coordinates locally, sending only the recognized text to the AI rather than full screenshots. Supports mixed Chinese and English recognition.

Running OCR locally via the Vision framework avoids sending screenshots to an AI API, which eliminates token costs and keeps screen content private.

사용 시점

  • Reading text from a non-standard desktop app that has no API
  • Monitoring a balance or progress indicator on screen without manual checking
  • Clicking a button in a GUI app by locating its label text
  • Automating repetitive UI interactions across any macOS application
  • Extracting text from a screen region that can't be copy-pasted

예시 워크플로

입력

User asks: help me click the Confirm button in this app

에이전트
  1. 1

    Runs vision_ocr.swift to scan the current screen

  2. 2

    Receives recognized text with [X, Y] coordinates for each element

  3. 3

    Locates the text matching 'Confirm' and retrieves its coordinates

  4. 4

    Passes coordinates to click.swift to perform a physical mouse click

출력

The Confirm button is clicked at the detected screen coordinates

요구 사항

  • macOS Screen Recording permission enabled for your terminal app (System Settings > Privacy & Security > Screen Recording)
  • macOS Accessibility permission enabled for your terminal app (System Settings > Privacy & Security > Accessibility)

설치

clawhub install ls18166407597-design/screen-vision

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크