Summary
Covers both the modern Swift-native Vision API (iOS 18+) with async/await and the legacy VNRequest pattern for backward compatibility. You get text recognition with language correction and custom vocabulary, face detection with landmarks, barcode scanning across a dozen symbologies, document scanning with structured layout understanding (paragraphs, tables, lists), plus object tracking for video. The modern API is cleaner,`try await request.perform(on: image)` instead of handler boilerplate,but you'll need the legacy patterns if you're supporting pre-iOS 18. Includes VisionKit's DataScannerViewController for live camera scanning and VNCoreMLRequest patterns for running custom Core ML models through Vision's pipeline.
Install to Claude Code
npx -y skills add dpearson2699/swift-ios-skills --skill vision-framework --agent claude-codeInstalls into .claude/skills of the current project.
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.md
Select a file.
Featured
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
