skills.rest
filipexyz
filipexyzCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

image

Generate and manipulate visual assets with AI image models.

6|2|Updated Jan 29, 2026
Search Tags:#design#image#ai#visuals#generation#gemini#openai
One-click install
npx skills add https://github.com/filipexyz/ravi --skill image-filipexyz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image
Source: https://github.com/filipexyz/ravi/tree/main/src/plugins/internal/ravi-system/skills/image
Command: npx skills add https://github.com/filipexyz/ravi --skill image-filipexyz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the friction of generating, editing, and managing AI-created visual assets directly within your agentic workflow, eliminating the need for external tools or manual file handling.

Core Features & Use Cases

  • Generative Creation: Create high-quality images from text prompts using OpenAI or Gemini models.
  • Image Manipulation: Edit existing images, remove backgrounds, or transform visual styles.
  • Asset Management: Automatically handle image artifacts, including splitting contact sheets and managing aspect ratios for UI mockups or marketing content.

Quick Start

Ask the agent to generate a high-quality image of a futuristic city skyline with cinematic lighting.

Frequently Asked Questions about image

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

FAQPage Schema
How do I generate AI images from text prompts within an agentic workflow?▼

Generate AI images from text prompts by directing your agent to use models like OpenAI DALL-E or Gemini for text-to-image synthesis, automatically handling the visual asset creation without external tools.

Can I edit existing images and remove backgrounds using AI image generation?▼

Edit existing images and remove backgrounds through image-to-image manipulation, transforming visual styles directly within the agent chat session using supported AI models.

How does batch processing for UI image atlases and contact sheets work?▼

Batch processing for image atlases works by automatically splitting contact sheets and managing aspect ratios, handling asset lifecycles to deliver UI mockups or marketing content.

Does this AI image generation skill support both OpenAI and Gemini models?▼

AI image generation supports both OpenAI and Gemini models, integrating with the Ravi runtime to manage automated provider selection and artifact delivery to chat sessions.

What is the best way to manage AI visual asset lifecycles and delivery?▼

Manage AI visual asset lifecycles and delivery by leveraging the Ravi runtime, which automates artifact handling, provider selection, and direct delivery of generated images to chat sessions.

Are there limitations when using AI image models for marketing design asset creation?▼

Limitations depend on the selected AI image model's capabilities for marketing design, though the skill automates aspect ratio management and artifact delivery to streamline the visual asset workflow.

Related Skills

Explore More Design & Creative Skills→
freestyleflyfreestylefly
869

seedream

Generate AI images from prompts using the Volcengine Seedream model.

Community
Advanced
pablitonogpablitonog
1

canva

Integrates with the Canva API to create, search, and export visual assets programmatically.

Community
Intermediate
Ivanblancoinusual-2106Ivanblancoinusual-2106

V3 Deep Integration

Integrate claude-flow as a specialized extension of agentic-flow.

Community
Advanced
barkleesandersbarkleesanders
5

gemini-imagegen

Generate and edit images using Google's Gemini 3 Pro model.

Community
Intermediate