What it does

This skill provides high-performance image classification and object recognition by leveraging the Microsoft ResNet-50 model running on Cloudflare Workers AI. It allows your AI agent to "see" and categorize photos, identifying thousands of different classes including animals, vehicles, electronics, and scenes.

Why use this skill

Unlike general-purpose LLMs that may be slow or expensive for simple visual processing, this skill provides a specialized, lightweight solution. It is 100% free to use with a standard Cloudflare account, making it ideal for high-volume tasks that would otherwise drain your API credits. It returns structured confidence scores and ranked predictions, which are significantly more reliable for automation than unstructured text descriptions.

Supported Features

• Single & Batch Processing: Classify individual files or entire directories in one command.
• Confidence Scoring: Get decimal-accurate probability scores for every identification.
• Structured Output: Automatically saves results to JSON for easy parsing by other scripts or agents.
• Extensive Vocabulary: Recognizes over 1,000 distinct ImageNet categories.

The output is a clean, ranked list of the most likely objects or scenes detected in the image, accompanied by visual confidence bars for quick human or machine verification.