skills.rest
mordechai30
mordechai30COMMUNITY
Explore all skills by this author →
GitHub

local-image-analysis

Analyze local images with metadata extraction, OCR, and semantic reasoning.

Updated Aug 27, 2026
Search Tags:#ocr#macos#mlx#privacy#image-analysis#computer-vision
One-click install
npx skills add https://github.com/mordechai30/.agents --skill local-image-analysis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: local-image-analysis
Source: https://github.com/mordechai30/.agents/tree/main/skills/local-image-analysis
Command: npx skills add https://github.com/mordechai30/.agents --skill local-image-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, and includes scripts (resource) components.

What problem does it solve?

This skill provides a secure, offline way to analyze images on macOS, ensuring sensitive visual data never leaves your local machine while providing advanced metadata, OCR, and semantic understanding.

Core Features & Use Cases

  • Deterministic Metadata: Extracts filesystem dates, EXIF data, and technical image properties like resolution and ICC profiles.
  • Auge Integration: Performs high-accuracy OCR and image classification using native macOS Vision frameworks.
  • Local Semantic Analysis: Uses a local MLX-VLM server (e.g., Qwen2-VL) to answer natural language questions about image content without cloud dependencies.

Quick Start

Use the local-image-analysis skill to analyze the image at the provided path and answer a specific question about its contents.

Frequently Asked Questions about local-image-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run local OCR and image analysis on macOS without sending data to the cloud?▼

Local OCR and image analysis on macOS can run completely offline by combining native Vision frameworks for text recognition and a local MLX-VLM server for semantic reasoning, keeping visual data private while extracting metadata and digitizing content.

What do I need to set up to use MLX-VLM for private image querying?▼

To use MLX-VLM for private image querying, you need a local MLX-VLM server instance running on macOS and the Auge command-line tool installed, enabling high-accuracy OCR and natural language visual content analysis without cloud connectivity.

Does this offline image analysis approach extract EXIF data and filesystem metadata?▼

Yes, offline image analysis extracts deterministic metadata including filesystem dates, EXIF data, resolution, and ICC profiles, providing comprehensive technical image properties alongside OCR text and semantic understanding.

Can I use Apple Vision frameworks for automated document classification locally?▼

Yes, Apple Vision frameworks support automated document classification and high-accuracy OCR locally on macOS, processing image files to digitize text and categorize documents without cloud connectivity.

What are the limitations of local MLX-VLM semantic reasoning for computer vision tasks?▼

Local MLX-VLM semantic reasoning requires a local server instance and the Auge command-line tool, limiting usage to environments where these dependencies are installed and restricting it to macOS platforms supporting Apple Vision frameworks.

Related Skills

Explore More Data & Analytics Skills→
PicoMLXPicoMLX
24

swift-mlx-lm

Run local LLM and VLM inference on Apple Silicon using MLX in Swift.

Official
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
kjayleekjaylee

mlx-brain

Execute large language models locally on macOS using the MLX framework.

Community
Intermediate
lenadlmlenadlm

image-ocr

Extract text from images using Tesseract and cloud OCR APIs.

Community
Intermediate