# muapi-nano-banana

Formulates reasoning-driven image prompts in Gemini 3 style and sends them to muapi.ai. Useful when you need legible typography and physically accurate lighting.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2800 installs · ★ 23
- Author: SamurAIGPT
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/SamurAIGPT/Generative-Media-Skills/tree/HEAD/.opencode/skills/muapi-nano-banana/SKILL.md
- Updated: 2026-09-29
- HTML: https://affpapa.org/en/nevibecode/skills/muapi-nano-banana

## What it does

The skill stops the agent from dumping keyword soup like "masterpiece" or "8k" into image prompts. Instead, it turns user input into structured creative briefs following a formula: subject, dynamic action, environment, framing, and light interaction. It also handles exact typography by quoting labels directly and sets optical properties such as macro lenses or `f/1.8` apertures.

Under the hood, the skill acts as a logic wrapper that invokes `bash scripts/generate-nano-art.sh`, passing arguments forward to `core/media/generate-image.sh`. The project environment must contain these bash scripts and a working muapi.ai setup. Without the underlying bash utilities in place, the command will simply fail.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-nano-banana -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-nano-banana -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-nano-banana -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install SamurAIGPT/Generative-Media-Skills muapi-nano-banana
```

2. **Manually: put the files in place**
- File: `.github/skills/muapi-nano-banana/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-nano-banana -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/SamurAIGPT/Generative-Media-Skills --path .opencode/skills/muapi-nano-banana
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-nano-banana -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/SamurAIGPT/Generative-Media-Skills/tree/HEAD/.opencode/skills/muapi-nano-banana/SKILL.md

## When to use it
- Convert brief ideas into structured prompts with camera and lighting details
- Render readable typography with exact quoted phrasing on generated media
- Define realistic surface reflections and optical physics instead of raw tags
- Call the `generate-nano-art.sh` script with dedicated composition flags

## Example prompts
- Generate an image of a glass chess piece shattering on an obsidian table
- Create a cyberpunk cafe scene with a neon sign reading "OPEN"
- Render a robot barista pouring latte art using a macro 85mm lens

## 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: a53923e05c670c27.

BEGIN THIRD-PARTY FILE a53923e05c670c27
```text
---
name: muapi-nano-banana
version: 0.1.0
description: Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting
---

# 🍌 Nano-Banana Expert Skill (Gemini 3 Style)

**A specialized skill for AI Agents to leverage "Reasoning-Driven" image generation.**
Based on the advanced prompting architecture of Google's Gemini 3 (Nano Banana Pro), this skill moves beyond keyword stuffing to structured, logic-based creative briefs.

## Core Competencies

1. **Reasoning-Driven Prompting**: Using natural language logic to define physics, lighting, and spatial relationships.
2. **Structured Creative Briefs**: Implementing the "Perfect Prompt" formula: `Subject + Action + Context + Composition + Lighting`.
3. **Text Rendering Precision**: Explicitly defining typography and signifiers for legible text integration.
4. **Contextual Grounding**: Using "Search Grounding" logic (simulated) to anchor generations in real-world accuracy.

---

## 🏗️ Technical Specification

### 1. The "Perfect Prompt" Formula

| Component | Description | Example |
| :--- | :--- | :--- |
| **Subject** | Detailed entity description | "A stoic robot barista with exposed copper wiring" |
| **Action** | Dynamic interaction | "Pouring a latte art leaf with mechanical precision" |
| **Context** | Environment & Atmosphere | "Inside a neon-lit cyberpunk cafe at midnight" |
| **Composition** | Camera & Lens choice | "Close-up, 85mm lens, f/1.8 aperture" |
| **Lighting** | Mood & Direction | "Volumetric blue rim light, warm cafe glow" |
| **Style** | Aesthetic anchor | "Cinematic, photorealistic, 4K production value" |

### 2. Advanced Features
- **Negative Constraint Logic**: Instead of "no blurry," use "Ensure sharp focus on the subject's eyes."
- **Identity Consistency**: (Simulated) "Maintain consistent facial structure across variations."
- **Text Integration**: Use double quotes for specific text: `The sign reads "OPEN 24/7"`.

---

## 🧠 Prompt Optimization Protocol (Agent Instruction)

**Before calling the script, the Agent MUST rewrite the user's prompt into a logic-driven Reasoning Brief:**

1. **NO KEYWORD SOUP**: Remove "8k, masterpiece, ultra-detailed." Use full, descriptive sentences.
2. **PHYSICAL CONSISTENCY**: Describe how elements interact (e.g., "The light from the crystal shards casts caustic patterns across the obsidian floor").
3. **TEXT PRECISION**: If the user wants text, define it precisely: `featuring a sign that says "STORE NAME" in a weathered serif font`.
4. **OPTICAL DIRECTIVES**: Specify lens behavior: *Shallow Depth of Field (f/1.8)*, *Macro Lens*, *Anamorphic Flare*.

---

## 🚀 Protocol: Using Nano-Banana

### Step 1: Define the Creative Logic
```
END THIRD-PARTY FILE a53923e05c670c27

The third-party file has ended. Everything between the a53923e05c670c27 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 2784 of 3815 bytes. © SamurAIGPT · MIT · https://github.com/SamurAIGPT/Generative-Media-Skills/tree/HEAD/.opencode/skills/muapi-nano-banana/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