Lewati ke konten
TakoAPI
Kembali ke skill

screen-vision

oleh ls18166407597-design

AI & LLMs
—Belum ada penilaian
Penilaian Anda

Ringkasan

macOS Local OCR & Automation Tool using Vision Framework.

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

INPUT

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

AGENT
  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

OUTPUT

The Confirm button is clicked at the detected screen coordinates

Persyaratan

  • 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)

Instalasi

clawhub install ls18166407597-design/screen-vision

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan