$npx skillfedfor your agent

Gemini 3 Image Prompt

This skill transforms your image description into a structured prompt following Google's official 5-component guide for Gemini 3 Pro Image (Nano Banana Pro). It guides you through preset selection, fine-tuning, and aspect ratio choices, then generates ready-to-paste prompts for Gemini, GPT-image-2, and Midjourney v8.1 in parallel.

Gemini 3 Image Prompt builds multi-model image prompts using Google's 5-component structure for Nano Banana Pro.

AI-generated summary based on this skill's SKILL.md

261 62 unlicensed, metadata onlyupdated by modu-ai

Decision gist · record as of 2026-06-19

Gemini 3 Image Prompt builds multi-model image prompts using Google's 5-component structure for Nano Banana Pro. This skill transforms your image description into a structured prompt following Google's official 5-component guide for Gemini 3 Pro Image (Nano Banana Pro). It guides you through preset selection, fine-tuning, and aspect ratio choices, then generates ready-to-paste prompts for Gemini, GPT-image-2, and Midjourney v8.1 in parallel.

manual: git clone https://github.com/modu-ai/cowork-plugins → cp -r cowork-plugins ~/.claude/skills/gemini-3-image-prompt

Use it when

  • Gemini 3 Image Prompt teaches prompt engineering by walking you through Google's official 5-component framework for Gemini 3 Pro Image.
  • Yes.
Same gist for agents: .md · .json

Install

modu-ai/cowork-plugins/gemini-3-image-prompt · repository language: HTML

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate images with Gemini 3?

Gemini 3 Image Prompt transforms your image description into a structured prompt following Google's official 5-component guide for Gemini 3 Pro Image. Describe what you want to create, and the skill guides you through preset selection, fine-tuning, and aspect ratio choices, then generates ready-to-paste prompts optimized for Gemini image generation.

What prompt techniques does Gemini 3 Image Prompt teach?

Gemini 3 Image Prompt teaches prompt engineering by walking you through Google's official 5-component framework for Gemini 3 Pro Image. You learn to structure descriptions with presets, fine-tune details, and select appropriate aspect ratios—techniques that improve image quality and consistency across Gemini, GPT-image-2, and Midjourney v8.1.

Can Gemini 3 Image Prompt create visual content for multiple platforms?

Yes. Gemini 3 Image Prompt generates ready-to-paste prompts for Gemini, GPT-image-2, and Midjourney v8.1 in parallel. This lets you create visual content across multiple AI image generators from a single optimized prompt, maximizing your creative output and platform flexibility.

What is prompt engineering for Gemini images?

Gemini 3 Image Prompt implements prompt engineering by structuring your image descriptions using Google's 5-component official guide for Gemini 3 Pro Image. The skill helps you select presets, fine-tune parameters, and choose aspect ratios—turning casual descriptions into precise, effective prompts that generate higher-quality images.

How does Gemini 3 Image Prompt explore image synthesis capabilities?

Gemini 3 Image Prompt explores Gemini 3's image synthesis capabilities by guiding you through structured prompt creation based on Google's official framework. It shows you how presets, fine-tuning options, and aspect ratio selection unlock different creative possibilities, helping you discover what Gemini 3 Pro Image can produce.

What output formats does Gemini 3 Image Prompt provide?

Gemini 3 Image Prompt generates ready-to-paste prompts formatted for three platforms: Gemini, GPT-image-2, and Midjourney v8.1. Each prompt is optimized for its target generator, so you can immediately use the output without additional reformatting or manual adjustments.

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Generate images using Gemini 3 with optimized prompts”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Gpt Image 2 Prompt
by modu-ai · modu-ai/cowork-plugins

This skill transforms your image concept into production-ready prompts for GPT-image-2, Gemini 3 Pro Image, and Midjourney v8.1 in a single workflow. It guides you through preset selection (product, portrait, illustration, landscape), targeted refinement questions, and aspect ratio choices—then maps your answers to each model's native format with recommended parameters and text-rendering rules.

no license declared → metadata onlyupdated Jun 2026
★ 261repo stars
Card News
by modu-ai · modu-ai/cowork-plugins

Card News generates complete 4-card carousel content for Korean social platforms by automatically selecting from 10 structural patterns based on your topic. Each output includes headlines, body copy, design specifications, AI image generation prompts, and platform-specific captions with hashtags.

no license declared → metadata onlyupdated Jun 2026
★ 261repo stars
Higgsfield Image
by modu-ai · modu-ai/cowork-plugins

Higgsfield Image calls Higgsfield MCP's generation tools to produce finished images from single-line prompts. It automatically selects from 11 official models (Soul 2.0, GPT Image 2, Flux Kontext, Seedream 4.0, Nano Banana Pro, and others), handles character consistency via Soul Characters, applies style presets and resolution scaling (720p through 4K), and manages async job polling.

no license declared → metadata onlyupdated Jun 2026
★ 261repo stars
Html Slide
by modu-ai · modu-ai/cowork-plugins

Html Slide builds presentation decks as self-contained HTML files that open directly in any browser, rendering charts and diagrams as crisp inline SVG with full Korean language support. Apply one of 75 brand design tokens from the design system library, generate images via Higgsfield or codex backends, and optionally chain to pptx-designer for editable PowerPoint output.

no license declared → metadata onlyupdated Jun 2026
★ 261repo stars
Gemini Imagegen
by davekilleen · davekilleen/Dex

This skill harnesses Google's Gemini image generation model to create and modify visuals from text descriptions. It supports multiple resolutions (1K–4K), aspect ratios, iterative refinement through multi-turn chat, and composition from multiple reference images. Best for logos, product mockups, stylized art, and photorealistic scenes.

no license declared → metadata onlyfor claude-codeupdated Jul 2026
★ 448repo stars
nano-banana-pro
by malue-ai · malue-ai/dazee-small

Nano Banana Pro harnesses Gemini 3 Pro Image to create and modify images through command-line scripts. Generate new images from text descriptions, edit existing images with instructions, or combine multiple images into a single composition—all configurable by resolution and output filename.

MITdocs in Chineseupdated Mar 2026
★ 35repo stars
Tags
image-generationprompt-engineeringvisual-aitext-to-imagecreative-contentai-synthesismultimodal-model