Which Apple platforms does the ios-vision skill support?

It supports the entire xOS ecosystem, including iOS, iPadOS, watchOS, and tvOS development.

How does it handle Vision framework coordinate systems?

The skill provides specific API references and patterns for coordinate conversion between Vision's normalized coordinates and UIKit/SwiftUI space.

Does it support advanced features like subject lifting?

Yes, it includes patterns for VisionKit subject segmentation and background removal (VNGenerateForegroundInstanceMaskRequest).

Can this skill help with real-time camera scanning?

Yes, it provides implementation patterns for DataScannerViewController and live Vision request handling for camera feeds.

iOS Computer Vision Router

Name: iOS Computer Vision Router
Author: CharlesWiltgen

byCharlesWiltgen

•

148

Mobile Development

Implements and optimizes Apple Vision framework features including image analysis, object detection, and advanced OCR for Apple platform development.

关于

This skill provides specialized guidance for developers implementing computer vision capabilities across iOS, iPadOS, watchOS, and tvOS. It streamlines the use of the Vision and VisionKit frameworks, offering ready-to-use patterns for complex tasks like 2D/3D pose tracking, subject segmentation, real-time OCR with DataScannerViewController, and barcode detection. By routing queries between implementation patterns, API references, and diagnostics, it helps developers resolve performance bottlenecks, coordinate conversion issues, and edge-detection bugs in vision-centric applications.

主要功能

Comprehensive diagnostics for Vision framework troubleshooting
148 GitHub stars
High-performance text recognition and OCR implementation
Real-time barcode and QR code scanning logic
Advanced pose detection for hand and body landmarks (2D/3D)
Automated subject segmentation and background lifting

使用场景

Implementing automated document scanning and structured data extraction
Developing live camera features using DataScannerViewController for text and barcodes
Building interactive apps that require precise hand or body tracking

关于

主要功能

Comprehensive diagnostics for Vision framework troubleshooting
148 GitHub stars
High-performance text recognition and OCR implementation
Real-time barcode and QR code scanning logic
Advanced pose detection for hand and body landmarks (2D/3D)
Automated subject segmentation and background lifting

使用场景

Implementing automated document scanning and structured data extraction
Developing live camera features using DataScannerViewController for text and barcodes
Building interactive apps that require precise hand or body tracking