imagen_skill

This skill generates images using Google Gemini to create UI mockups, icons, diagrams, and illustrations for any project.
  • Python

109

GitHub Stars

6

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill sanjay3290/ai-skills --skill imagen

  • .env.example175 B
  • .gitignore280 B
  • examples.md8.9 KB
  • README.md4.5 KB
  • reference.md8.0 KB
  • SKILL.md2.6 KB

Overview

This skill generates images using Google Gemini's image generation model to produce PNG assets for UI mockups, icons, illustrations, diagrams, concept art, and placeholders. It integrates into coding sessions to create visual assets on demand and returns file paths for immediate use in projects. Cross-platform support works on Windows, macOS, and Linux with a simple Python script and an environment API key.

How this skill works

You provide a text prompt describing the desired image and optional parameters (output path, size). The skill calls the Google Gemini image generation API (gemini-3-pro-image-preview), saves the returned PNG to the specified location, and returns the file path or an error message. Configuration uses the GEMINI_API_KEY environment variable and a lightweight Python script for local execution.

When to use it

  • Generate hero images, backgrounds, or concept art for web and app design
  • Create icons, avatars, or UI assets when building frontend components
  • Produce diagrams or visual representations for documentation and READMEs
  • Generate placeholder images for layouts, prototypes, and demos
  • Create visual ideas, mood boards, or quick concept explorations

Best practices

  • Craft clear, specific prompts including style, color palette, and composition for predictable results
  • Specify output size or resolution for production vs placeholder needs
  • Save generated images into project asset folders and use version control for selected assets only
  • Use iterative prompts: adjust and re-run to refine details or try multiple variations
  • Keep API keys secure by storing GEMINI_API_KEY in environment variables and not in source files

Example use cases

  • Frontend development: generate a hero image and return a path for HTML/CSS inclusion
  • Documentation: create a microservices architecture diagram as a PNG for the docs folder
  • UI assets: produce several icon variations for a toolbar or mobile app
  • Prototyping: create placeholder avatars and landscape images for mockups
  • Concept art: generate multiple mood variations to choose a direction for visual design

FAQ

The skill outputs PNG files by default.

How do I control image resolution?

Pass a size parameter to the script (e.g., 2K) or include resolution details in the prompt; the script accepts common size flags for the Gemini call.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational