# image-prompt-generator

image-prompt-generator — a skill for creating professional images through Google's Gemini API. Use it when you need thumbnails, blog headers, social posts, or creative visuals — it takes you from concept to file.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 295 installs · ★ 30 repo stars
- Author: cdeistopened
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/cdeistopened/skill-stack/tree/HEAD/public/skills/image-prompt-generator/SKILL.md
- Updated: 2026-07-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/image-prompt-generator

## What it does

The skill walks through five steps: it generates 4–6 visual concepts, you pick one you like, then it develops the idea into a detailed prompt covering composition, colour palette, style and texture. Next it offers visual style options (risograph by default—halftone dots and colour shift for a printed look; also minimalism, watercolour or editorial) before triggering generation via Gemini.

You'll need a Google Gemini API key from Google AI Studio. Install these packages: `google-generativeai`, `python-dotenv`, `pillow`. For polished final images, the skill recommends `gemini-3-pro-image-preview` (supports 16:9 aspect ratio, higher quality); for drafts and iteration, use `gemini-2.5-flash-image` (faster, cheaper).

Inside is training on writing prompts like a creative director: concrete details instead of tags, full sentences, material and lighting descriptions. The skill steers away from clichés—no lightbulbs for ideas, no handshakes for partnership. Generated images save alongside the content they serve.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cdeistopened/skill-stack --skill image-prompt-generator -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/image-prompt-generator/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/image-prompt-generator/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cdeistopened/skill-stack --skill image-prompt-generator -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/image-prompt-generator/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cdeistopened/skill-stack --skill image-prompt-generator -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/image-prompt-generator/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cdeistopened/skill-stack public/skills/image-prompt-generator
```

2. **Manually: put the files in place**
- File: `.github/skills/image-prompt-generator/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cdeistopened/skill-stack --skill image-prompt-generator -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cdeistopened/skill-stack --path public/skills/image-prompt-generator
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/image-prompt-generator/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add cdeistopened/skill-stack --skill image-prompt-generator -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cdeistopened/skill-stack/tree/HEAD/public/skills/image-prompt-generator/SKILL.md

## When to use it
- Generate a thumbnail in the right format for video or article
- Create multiple blog cover variations in one run
- Find a visual concept that avoids stock imagery and clichés
- Adapt an image across different styles—risograph, watercolour, minimalism
- Write a visual brief that an AI model will actually understand

## Example prompts
- Brainstorm 4–6 concepts for a blog post about time management
- Refine the compass-and-coffee-stain idea into a risograph-style prompt
- Generate a final 16:9 image using `gemini-3-pro-image-preview`

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 27d47cb953ed4ac9.

BEGIN THIRD-PARTY FILE 27d47cb953ed4ac9
````text
---
name: image-prompt-generator
description: Generate AI images using Gemini image generation API. Use this skill when content needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts, select direction, generate in multiple styles, then produce via API.
---

# Image Prompt Generator

Generate professional, non-generic images using Google's Gemini API for image generation.

## Prerequisites & Setup

### Getting Your Gemini API Key

1. Go to [Google AI Studio](https://aistudio.google.com/app/apikey)
2. Sign in with your Google account
3. Click "Create API Key"
4. Copy the generated key

### Configuring the API Key

**Option 1: Environment file (recommended)**

Create a `.env` file in your project root:

```bash
GEMINI_API_KEY=your_api_key_here
```

**Option 2: Direct environment variable**

```bash
export GEMINI_API_KEY=your_api_key_here
```

### Install Dependencies

```bash
pip install google-generativeai python-dotenv pillow
```

### Available Models

| Model | API Name | Best For |
|-------|----------|----------|
| **Flash** | `gemini-2.5-flash-image` | Speed, drafts, iteration |
| **Pro** | `gemini-3-pro-image-preview` | **Final assets, 16:9 aspect ratio, quality** |

**CRITICAL**: Use `gemini-3-pro-image-preview` for:
- Thumbnails (need 16:9 aspect ratio)
- Final production images
- Any image where aspect_ratio config is needed

---

## Workflow Overview

1. **Brainstorm Concepts** - Generate 4-6 high-level visual ideas
2. **Select Direction** - User picks the concept they like
3. **Optimize Prompt** - Refine into a strong, detailed prompt
4. **Style Variations** - Adapt to 2-3 different visual styles
5. **Generate Images** - Run via Gemini API

## Step 1: Brainstorm Concepts

When the user provides a topic or use case, generate 4-6 high-level visual concepts. Each concept should be:

- **One sentence** describing the visual idea
- **Concrete and immediate** - you can picture it instantly
- **Conceptual but not abstract** - a clear object/scene with meaning
- **Non-generic** - avoid cliches (no lightbulbs for ideas, no handshakes for partnership)

**Format:**

```
1. **[Short label]** - One sentence description of the visual concept and why it works.
````
END THIRD-PARTY FILE 27d47cb953ed4ac9

The third-party file has ended. Everything between the 27d47cb953ed4ac9 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2265 of 12496 bytes. © cdeistopened · MIT · https://github.com/cdeistopened/skill-stack/tree/HEAD/public/skills/image-prompt-generator/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
