image

Analyze, edit, generate, and convert images using Python scripts.

Updated May 17, 2026
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill image-tiankong0101-byte
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/image
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill image-tiankong0101-byte

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, and includes scripts (resource) components.

What problem does it solve?

This Skill solves everyday image work by combining analysis, editing, generation, and design help in one place, so you can handle visual tasks without switching tools.

Core Features & Use Cases

  • Image Analysis: Describe images, detect objects, perform OCR, and inspect colors or differences.
  • Image Processing: Resize, crop, rotate, compress, convert formats, and make basic enhancements.
  • Image Generation and Editing: Create new images or modify existing ones using Nano Banana Pro / Gemini image generation.
  • Graphic Design Support: Produce brand assets, social graphics, logos, and illustrations with clear requirements and iterative refinement.

Quick Start

Ask the image skill to analyze, edit, or generate an image for your specific visual task, and include any source image plus the desired output style or size.

Frequently Asked Questions about image

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

FAQPage Schema
How do I perform image analysis like object detection or OCR on a picture?

Image analysis tasks like object detection and OCR are handled by processing your source picture to extract text, identify objects, inspect colors, and detect visual differences.

What's the best way to resize, compress, or convert image formats without losing quality?

Resize, compress, and convert image formats using local Python scripts with Pillow for deterministic output handling, ensuring basic enhancements and modifications are applied reliably.

Can I create social graphics and brand logos using this image editing workflow?

Create social graphics, brand assets, logos, and illustrations by providing clear design requirements and iterating on visual generation outputs to refine the final artwork.

Does this image processing approach work for comparing differences between two images?

Comparing differences between images is supported natively, allowing you to inspect colors and detect visual discrepancies within your visual content workflows.