skills.rest
PytaichukBohdan
PytaichukBohdanCOMMUNITY
Explore all skills by this author →
GitHub

gemini-image-generation

Generate frontend design images via the Gemini API with configurable prompts.

Updated Mar 25, 2026
Search Tags:#figma#image-generation#frontend-design#design-context#ai-art#gemini-api#prompt-crafting
One-click install
npx skills add https://github.com/PytaichukBohdan/figma_board_connection --skill gemini-image-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-image-generation
Source: https://github.com/PytaichukBohdan/figma_board_connection/tree/main/.claude/skills/image-generation
Command: npx skills add https://github.com/PytaichukBohdan/figma_board_connection --skill gemini-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Design teams and developers often struggle to produce visuals that match a product's branding and context, spending hours crafting images. This skill automates high-quality image generation by leveraging Gemini API and smart prompt crafting that understands your frontend codebase and design cues.

Core Features & Use Cases

  • Smart Prompt Crafting: Analyze user requests and project context to generate optimized prompts for Gemini.
  • Design Context Integration: Leverage Figma boards or design systems to pull colors, typography, and style cues.
  • Model Flexibility & Output: Support multiple Gemini models and automatic kebab-case filenames for outputs.
  • Workflow & Output: Deterministic generation with configurable prompts and local persistence.

Quick Start

Trigger the skill by asking for a hero image and it will craft a Gemini-powered prompt and generate the resulting image.

Frequently Asked Questions about gemini-image-generation

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

FAQPage Schema
How do I generate images for frontend design using Gemini API?▼

To generate images for frontend design, this skill leverages the Gemini API and smart prompt crafting to analyze your project context and produce tailored visuals. It uses local configuration for deterministic results and robust error handling.

Can I use Figma boards to apply design context to AI image generation?▼

You can use Figma boards to apply design context to AI image generation by leveraging the skill's design context integration. It pulls colors, typography, and style cues from Figma to tailor the Gemini-generated visuals.

What's the best way to automate hero image creation for websites?▼

Automate hero image creation for websites by triggering this skill with a simple request. It automatically crafts an optimized Gemini-powered prompt based on your design context and generates the matching visual output.

How do I configure the Gemini API for deterministic image generation?▼

Configure the Gemini API for deterministic image generation by setting up API access, selecting a model, and establishing persistent local configuration. This ensures consistent visual outputs and robust error handling.

Does this image generation skill support multiple Gemini models?▼

Yes, this image generation skill supports multiple Gemini models. You can configure model selection alongside prompt crafting and persistent local configuration to achieve deterministic generation and automatic kebab-case filenames.

Related Skills

Explore More Design & Creative Skills→
qianleigoodqianleigood
30

gemini-browser-image

Automate Gemini image generation and editing in a real browser.

Community
Advanced
MohammedSaudAlsahliMohammedSaudAlsahli

image-to-code

Transform design images into responsive website frontend mockups and structures.

Community
Advanced
royvillasanaroyvillasana
34

ai-prototype-prompter

Convert Figma design data into structured prompts for AI UI prototyping tools.

Community
Intermediate
ceslepceslep

ckm:banner-design

Generate creative banner designs for specified platforms, styles, and dimensions.

Community
Advanced