Skills

image-gen

Installation
Summary

Generate website images and edit them with Gemini 3 Native Image Generation.

  • Supports hero banners, service cards, infographics with legible text (94% at 4K), and multi-turn editing across 10+ aspect ratios and resolutions up to 4K
  • Two active models: Gemini 3 Pro Image Preview for 4K and complex compositions; Gemini 2.5 Flash Image for fast iteration
  • Handles up to 14 reference images (max 5 human for consistency), style transfer, color changes, element addition/removal, and aspect ratio adjustments
  • Includes Australian-specific imagery patterns and prevents 5 documented errors: resolution case sensitivity, aspect ratio handling, human reference limits, SynthID watermarks, and Google Search grounding constraints
  • Requires SDK migration from deprecated @google/generative-ai to @google/genai; responseModalities must include both TEXT and IMAGE
SKILL.md

Image Generation Skill

Generate and edit website images using Gemini Native Image Generation.

⚠️ Critical: SDK Migration Required

IMPORTANT: The @google/generative-ai package is deprecated as of November 30, 2025. All new projects must use @google/genai.

Migration Required:

// ❌ OLD (deprecated, support ended Nov 30, 2025)
import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(API_KEY);

// ✅ NEW (required)
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: API_KEY });
Related skills

More from jezweb/claude-skills

Installs
354
Repository
jezweb/claude-skills
GitHub Stars
776
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubFail
SocketPass
SnykWarn