1

    cf-ai-classify

    by Kevin Cline

    Fast, free image classification using ResNet-50 on Cloudflare Workers AI with 1,000+ object categories.

    Updated Apr 2026
    Security scanned
    One-time purchase

    $12

    One-time purchase · Own forever

    ⚡ Also available via Agensi Pro — your AI agent can load this skill on demand via MCP. Learn more →

    Included in download

    • Moderate user uploads by detecting off-topic or restricted content
    • Sort and organize assets based on detected objects like "car" or "dog"
    • terminal, network, env_vars automation included
    • Includes example output and usage patterns
    • Instant install

    See it in action

    Classifying: golden_retriever.jpg
    Top predictions:
    1. [##############################] 95.3% golden retriever
    2. [######################--------] 73.1% Labrador retriever
    3. [########----------------------] 27.4% dog
    4. [###---------------------------] 11.2% tennis ball

    About This Skill

    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.

    📖 Learn more: Best DevOps & Deployment Skills for Claude Code →

    Use Cases

    • Automate metadata tagging for large image libraries
    • Moderate user uploads by detecting off-topic or restricted content
    • Sort and organize assets based on detected objects like "car" or "dog"
    • Validate that uploaded images match expected categories in inventory systems

    Reviews

    No reviews yet — be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    gist.github.com
    dash.cloudflare.com
    api.cloudflare.com

    Creator

    K
    Kevin Cline

    ClawdWorks

    Builder of autonomous AI agents and Claude Code skills. ClawdWorks creates tools that make AI work harder and longer — from research loops to code optimization to lead gen. Powered by Claude Opus 4.6 + Codex 5.4.

    Frequently Asked Questions

    Similar Skills

    $12

    One-time