One-click install
npx skills add https://github.com/felipesantiago-coder/fluxo-quadra --skill image-edit-felipesantiago-coder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-edit
Source: https://github.com/felipesantiago-coder/fluxo-quadra/tree/main/skills/image-edit
Command: npx skills add https://github.com/felipesantiago-coder/fluxo-quadra --skill image-edit-felipesantiago-coder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

This Skill eliminates the need for manual design work or complex editing software when modifying existing images, allowing users to make targeted changes, create variations, and transform visual content using simple text prompts.

Core Features & Use Cases

  • AI-Powered Text-Guided Editing: Modify existing images by describing desired changes in natural language, with support for background replacement, style transfer, element modification, and lighting adjustments.
  • Multiple Input/Output Options: Accepts both remote image URLs and local base64 data URLs, with support for 7 different output sizes to fit various use cases.
  • Batch Processing and CLI Tool: Includes functionality for batch editing multiple images at once, plus a command-line tool for quick, no-code image editing tasks.
  • Use Case: A marketing team can use this Skill to quickly generate 3 variations of a product photo with different backgrounds and styles for social media campaigns, without needing access to professional design tools.

Quick Start

Use the image-edit skill to transform the attached product photo to have a modern minimalist style with a white background.

Frequently Asked Questions about image-edit

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

FAQPage Schema
How do I edit existing images using text prompts?

AI image modification allows you to transform existing images by describing changes in natural language. This Skill accepts image URLs or base64 inputs and applies text-guided edits like background replacement and style transfer.

What is the best way to batch process multiple images for AI variations?

Batch image processing automates editing multiple images at once using text prompts. This Skill includes batch functionality and a CLI tool to generate image variations and apply modifications without manual design work.

Does z-ai-web-dev-sdk support base64 inputs for image editing?

Yes, z-ai-web-dev-sdk supports both remote image URLs and local base64 data URLs for AI image modification. It processes these inputs to generate variations across 7 different output sizes.

Can I use a CLI tool for AI image modification without writing code?

Yes, command-line image editing is supported through the included CLI tool. It enables quick, no-code AI image transformations using text prompts directly from your terminal.

What are the limitations of text prompt image editing?

Text prompt image editing requires the z-ai-web-dev-sdk backend dependency and accepts specific input formats. Output is constrained to 7 supported sizes, and complex modifications may require precise natural language descriptions.

How do I generate image variations for marketing campaigns?

AI image variation generation creates multiple versions of a product photo using text prompts. This Skill supports style transfer and background replacement to quickly produce visual content for marketing and social media campaigns.