메뉴
Nano-Banana AI service integration for content generation, image creation, and AI-powered workflows. Use when integrating AI services for content creation.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/ForceInjection/domain-driven-design-skills --skill moai-ai-nano-banana명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Conduct deep academic research for philosophy, neuroscience, cognitive science, and theoretical computer science (computability, complexity, AI theory, logic). Use when user asks to: research academic topics, find scholarly papers, conduct literature reviews, analyze citations, synthesize research findings, explore philosophical arguments, investigate consciousness/cognition, study computability/decidability/Turing machines, or analyze academic debates. Triggers on: 'research papers', 'literature review', 'academic sources', 'scholarly articles', 'philosophy of mind', 'computability theory', 'neuroscience studies', 'find papers on', 'what does the research say'.
Create clear action plans with steps, success criteria, and risk awareness. Use before implementing features, making changes, starting projects, or anytime you need a roadmap to success. Triggers on "plan this", "how should we approach", "what's the strategy", "steps to complete", or when facing complex multi-step work.
Add keyboard navigation to a feature using CommandRegistryService. Use when implementing keyboard shortcuts, vim-style navigation, or hotkeys for a page or component.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | moai-ai-nano-banana |
| description | Nano-Banana AI service integration for content generation, image creation, and AI-powered workflows. Use when integrating AI services for content creation. |
| version | 1.1.0 |
| category | integration |
| allowed-tools | Read, Write, Edit, Bash, Grep, Glob |
| tags | ["ai","content-generation","image-generation","nano-banana","ai-service","gemini-3-pro"] |
| related-skills | ["moai-docs-generation","moai-domain-uiux"] |
| updated | "2025-12-23T00:00:00.000Z" |
| status | active |
| author | MoAI-ADK Team |
Nano Banana Pro (gemini-3-pro-image-preview) integration for high-quality image generation with 1K/2K/4K resolution support, style prefixes, and batch processing.
Core Capabilities:
CLI Quick Start:
# Single image generation
python scripts/generate_image.py -p "Dashboard UI design" -o ui.png -r 4K
# With style prefix
python scripts/generate_image.py -p "Logo" -o logo.png --style "minimalist, vector"
# Batch generation
python scripts/batch_generate.py -c prompts.json -d output/ --concurrency 2
When to Use:
Single Image Generation (scripts/generate_image.py):
# Basic usage
python scripts/generate_image.py -p "A fluffy cat" -o cat.png
# High resolution with aspect ratio
python scripts/generate_image.py -p "Dashboard UI" -o ui.png -r 4K -a 16:9
# With style prefix for consistent aesthetics
python scripts/generate_image.py -p "Mountain landscape" -o landscape.png \
--style "photorealistic, dramatic lighting"
# With Google Search grounding
python scripts/generate_image.py -p "Mount Fuji at sunset" -o fuji.png -g
# Verbose mode
python scripts/generate_image.py -p "Tech logo" -o logo.png -r 4K -a 1:1 \
--style "minimalist, vector art" -v
Batch Generation (scripts/batch_generate.py):
# From JSON config
python scripts/batch_generate.py -c prompts.json -d output/
# From YAML config with concurrency
python scripts/batch_generate.py -c prompts.yaml -d output/ --concurrency 3
# From command line prompts
python scripts/batch_generate.py --prompts "Cat" "Dog" "Bird" -d output/ \
--style "watercolor painting"
# With report generation
python scripts/batch_generate.py -c prompts.json -d output/ --report report.json
Batch Config File Example (prompts.json):
{
"defaults": {
"style": "photorealistic, high detail",
"resolution": "4K",
"aspect_ratio": "16:9"
},
"images": [
"A serene mountain landscape",
{
"prompt": "Modern tech company logo",
"filename": "logo.png",
"resolution": "4K",
"aspect_ratio": "1:1",
"style": "minimalist, vector art"
}
]
}
Direct API Integration:
from google import genai
from google.genai import types
import os
client = genai.Client(api_key=os.getenv('GOOGLE_API_KEY'))
response = client.models.generate_content(
model="gemini-3-pro-image-preview",
contents="Modern dashboard UI with dark theme",
config=types.GenerateContentConfig(
response_modalities=['TEXT', 'IMAGE'],
image_config=types.ImageConfig(
aspect_ratio="16:9",
image_size="4K" # 1K, 2K, 4K (uppercase K required)
)
)
)
for part in response.candidates[0].content.parts:
if part.inline_data is not None:
with open("output.png", "wb") as f:
f.write(part.inline_data.data)
Model: gemini-3-pro-image-preview (Nano Banana Pro)
Supported Resolutions:
Supported Aspect Ratios:
Special Features:
Common Style Prefixes:
The scripts include automatic retry with exponential backoff:
Non-retryable errors (immediate failure):
Using generate_image.py as a module:
from scripts.generate_image import generate_image
# Single image with all options
result = generate_image(
prompt="Modern tech startup office",
output_path="office.png",
aspect_ratio="16:9",
resolution="4K",
style="photorealistic, natural lighting",
enable_grounding=False,
max_retries=5,
verbose=True
)
if result["success"]:
print(f"Generated: {result['output_path']}")
print(f"Time: {result['generation_time_seconds']}s")
Using batch_generate.py programmatically:
import asyncio
from scripts.batch_generate import (
ImageTask, run_batch_generation, save_batch_report
)
# Create tasks
tasks = [
ImageTask(
prompt="Dashboard UI",
output_path="output/dashboard.png",
resolution="4K",
aspect_ratio="16:9",
style="modern, clean",
task_id=1
),
ImageTask(
prompt="Mobile app icon",
output_path="output/icon.png",
resolution="4K",
aspect_ratio="1:1",
style="minimalist",
task_id=2
)
]
# Run batch
result = asyncio.run(run_batch_generation(
tasks,
concurrency=2,
max_retries=5,
verbose=True
))
# Save report
save_batch_report(result, "report.json")
---
## Configuration
Environment Variables:
```bash
# Required
GOOGLE_API_KEY=your_google_ai_api_key
# Optional (for .env file support)
pip install python-dotenv
Get your API key from: https://aistudio.google.com/apikey
Dependencies:
pip install google-genai python-dotenv pyyaml
Complementary Skills:
moai-docs-generation - Automated documentation with imagesmoai-domain-uiux - UI/UX design asset generationmoai-domain-frontend - Frontend visual componentsmoai-workflow-templates - Template-based image workflowsIntegration Points:
Skill Files:
SKILL.md - Main documentation (this file)scripts/generate_image.py - Single image generation CLIscripts/batch_generate.py - Batch generation CLIexamples.md - Additional workflow examplesExternal Documentation:
Version: 1.1.0 Last Updated: 2025-12-23 Status: Active