Saltar al contenido
TakoAPI
Volver a skills

screen-vision

por ls18166407597-design

AI & LLMs
—Aún sin valoraciones
Tu valoración

Resumen

macOS Local OCR & Automation Tool using Vision Framework.

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

The Confirm button is clicked at the detected screen coordinates

Requisitos

  • 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)

Instalación

clawhub install ls18166407597-design/screen-vision

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces