muapi-nano-banana

Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting

Paste into Claude, ChatGPT or Cursor.

Read the source80 lines
muapi-nano-banana/SKILL.md80 lines3.7 KBpushed 100d agoRawView on GitHub
1---
2name: muapi-nano-banana
3version: 0.1.0
4description: Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting
5---
6 
7# 🍌 Nano-Banana Expert Skill (Gemini 3 Style)
8 
9**A specialized skill for AI Agents to leverage "Reasoning-Driven" image generation.**
10Based 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.
11 
12## Core Competencies
13 
141. **Reasoning-Driven Prompting**: Using natural language logic to define physics, lighting, and spatial relationships.
152. **Structured Creative Briefs**: Implementing the "Perfect Prompt" formula: `Subject + Action + Context + Composition + Lighting`.
163. **Text Rendering Precision**: Explicitly defining typography and signifiers for legible text integration.
174. **Contextual Grounding**: Using "Search Grounding" logic (simulated) to anchor generations in real-world accuracy.
18 
19---
20 
21## 🏗️ Technical Specification
22 
23### 1. The "Perfect Prompt" Formula
24 
25| Component | Description | Example |
26| :--- | :--- | :--- |
27| **Subject** | Detailed entity description | "A stoic robot barista with exposed copper wiring" |
28| **Action** | Dynamic interaction | "Pouring a latte art leaf with mechanical precision" |
29| **Context** | Environment & Atmosphere | "Inside a neon-lit cyberpunk cafe at midnight" |
30| **Composition** | Camera & Lens choice | "Close-up, 85mm lens, f/1.8 aperture" |
31| **Lighting** | Mood & Direction | "Volumetric blue rim light, warm cafe glow" |
32| **Style** | Aesthetic anchor | "Cinematic, photorealistic, 4K production value" |
33 
34### 2. Advanced Features
35- **Negative Constraint Logic**: Instead of "no blurry," use "Ensure sharp focus on the subject's eyes."
36- **Identity Consistency**: (Simulated) "Maintain consistent facial structure across variations."
37- **Text Integration**: Use double quotes for specific text: `The sign reads "OPEN 24/7"`.
38 
39---
40 
41## 🧠 Prompt Optimization Protocol (Agent Instruction)
42 
43**Before calling the script, the Agent MUST rewrite the user's prompt into a logic-driven Reasoning Brief:**
44 
451. **NO KEYWORD SOUP**: Remove "8k, masterpiece, ultra-detailed." Use full, descriptive sentences.
462. **PHYSICAL CONSISTENCY**: Describe how elements interact (e.g., "The light from the crystal shards casts caustic patterns across the obsidian floor").
473. **TEXT PRECISION**: If the user wants text, define it precisely: `featuring a sign that says "STORE NAME" in a weathered serif font`.
484. **OPTICAL DIRECTIVES**: Specify lens behavior: *Shallow Depth of Field (f/1.8)*, *Macro Lens*, *Anamorphic Flare*.
49 
50---
51 
52## 🚀 Protocol: Using Nano-Banana
53 
54### Step 1: Define the Creative Logic
55Provide the agent with a subject and a specific scenario.
56 
57### Step 2: Invoke the Script
58The `generate-nano-art.sh` script translates the logic into a structured Gemini 3-style prompt.
59 
60```bash
61# Generating a reasoning-driven image
62bash scripts/generate-nano-art.sh \
63 --subject "a glass chess piece" \
64 --action "shattering into liquid shards" \
65 --context "on a obsidian table" \
66 --style "macro photography"
67```
68 
69---
70 
71## ⚠️ Constraints & Guardrails
72 
73- **No Keyword Soup**: **MANDATORY** - Do not use "trending on artstation, masterpiece, 8k". Use natural language descriptions.
74- **Physics Logic**: Ensure the prompt describes *physically possible* lighting and reflection interactions.
75- **Full Sentences**: The model parses relationships; use "light reflecting off the water" instead of "water, reflection".
76 
77---
78 
79## ⚙️ Implementation Details
80This skill applies a "Logic Wrapper" around the `core/media/generate-image.sh` primitive, converting fragmented inputs into a coherent, reasoning-ready narrative prompt.

Discussion