skills.rest
daniel-carreon
daniel-carreonCOMMUNITY
Explore all skills by this author →
Website𝕏@DanielCarreongGitHub

image-generation

Generate and edit images from text prompts using OpenRouter's Gemini models.

3|2|Updated Apr 2, 2026
Search Tags:#design#image#edit#generate#illustration#whiteboard#draw
One-click install
npx skills add https://github.com/daniel-carreon/sf-slides --skill image-generation-daniel-carreon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/daniel-carreon/sf-slides/tree/main/.claude/skills/image-generation
Command: npx skills add https://github.com/daniel-carreon/sf-slides --skill image-generation-daniel-carreon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generate AI images from text prompts and edit existing images using OpenRouter's Gemini models, enabling rapid creation of visuals without external tools.

Core Features & Use Cases

  • Text-to-image generation: Create high-quality illustrations, banners, and thumbnails from natural language prompts.
  • Image editing: Modify existing images (e.g., background changes, style edits) via prompts.
  • Draw/whiteboard integration: Optionally inject generated images directly onto the Draw/whiteboard canvas or create new pages.
  • Upload & sharing: Uploads to Supabase storage and returns a public URL for chat sharing.

Quick Start

Provide a text prompt and optional flags to generate an image, then upload it for sharing or inject it into the Draw canvas.

Frequently Asked Questions about image-generation

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

FAQPage Schema
How do I generate AI images from text prompts for thumbnails or banners?▼

To generate AI images from text, provide a natural language prompt to create high-quality illustrations, banners, or thumbnails using OpenRouter's Gemini models, optionally uploading the result to get a public URL.

Can I edit existing images by changing their background or style?▼

Yes, you can edit existing images by providing modification prompts to change backgrounds or apply style edits directly through the OpenRouter Gemini models integration.

Does AI image generation work with a whiteboard or Draw canvas?▼

AI image generation works with the Draw canvas by optionally injecting generated images directly onto the whiteboard surface or creating entirely new pages for visual modification.

How do I share AI generated illustrations using a public URL?▼

To share AI generated illustrations, utilize the upload feature to store the output in Supabase storage, which returns a public URL for immediate chat sharing and distribution.

What is the best way to select different Gemini models for image generation?▼

The best way to select different Gemini models for image generation is by using the included script flags, which allow you to specify the exact OpenRouter model for your visual creation task.

Related Skills

Explore More Design & Creative Skills→
MicrockMicrock
322

nanobanana-skill

Generate or edit images via nanobanana using prompts, aspect ratios, and models.

Community
Advanced
Merit-SystemsMerit-Systems
16

upload-and-share

Uploads local files to StableUpload and retrieves public URLs for sharing via agentcash MCP.

Official
Intermediate
parhummparhumm
25

frontend-component-fix

Diagnose frontend UI bugs and generate patch artifacts for React-like components.

Community
Advanced
JocDLCJocDLC
4

image-generation

Generate and edit images with OpenRouter Gemini models via CLI parameters.

Community
Intermediate