image-generation
Generate images using FAL.ai nanobanana pro. Use when creating product shots, social graphics, brand assets, or any visual content. Integrates with automation system for direct asset generation in Claude Code.
What this skill does
# Image Generation Skill
## Overview
Image Generation uses FAL.ai nanobanana pro to create professional-quality images from text descriptions. This skill teaches you how to craft effective prompts and use the automation system to generate assets directly in Claude Code.
**Keywords**: image generation, nanobanana pro, prompt engineering, AI art, visual content creation, asset generation, automation
## Core Models
### nanobanana pro — Recommended
- **Quality**: Highest, most detailed
- **Speed**: 30-60 seconds
- **Best For**: Product photography, hero images, final assets
- **Use Case**: When quality matters most
### nanobanana pro
- **Quality**: High, good detail
- **Speed**: 5-15 seconds
- **Best For**: Testing, iterations, social media
- **Use Case**: When speed matters
### nanobanana pro
- **Quality**: Latest, improved
- **Speed**: 20-40 seconds
- **Best For**: Production work
- **Use Case**: When you want the latest model
## Prompt Engineering Framework
### The 5-Part Prompt Formula
Every effective prompt has 5 components:
**1. Subject** — What is the main thing?
```
"A luxury leather watch"
"A modern logo"
"An Instagram post graphic"
```
**2. Description** — What does it look like?
```
"with gold accents and brown leather strap"
"geometric style, minimalist design"
"vibrant colors, eye-catching composition"
```
**3. Style** — What's the artistic style?
```
"professional product photography"
"modern illustration"
"digital design"
"photorealistic"
```
**4. Technical Details** — Quality and format specs
```
"studio lighting, sharp focus, 4K, centered composition"
"high contrast, trending design, professional quality"
"detailed, well-lit, professional photography"
```
**5. Mood/Aesthetic** — What's the feeling?
```
"luxury and professional"
"energetic and modern"
"clean and minimalist"
"warm and inviting"
```
### Complete Prompt Example
```
A luxury leather watch with gold accents and brown strap,
professional product photography, studio lighting with rim light,
centered composition, sharp focus, 4K, luxury and professional mood
```
### Prompt Engineering Techniques
**Technique 1: Be Specific**
```
❌ Bad: "A watch"
✅ Good: "A luxury leather watch with gold accents on white background"
```
**Technique 2: Use Descriptive Adjectives**
```
❌ Bad: "A logo"
✅ Good: "A modern, geometric, minimalist logo in blue and white"
```
**Technique 3: Reference Styles**
```
❌ Bad: "A nice graphic"
✅ Good: "A graphic in the style of modern Instagram design trends"
```
**Technique 4: Specify Quality**
```
❌ Bad: "A photo"
✅ Good: "A professional 4K product photograph with studio lighting"
```
**Technique 5: Include Composition**
```
❌ Bad: "A person"
✅ Good: "A person in rule of thirds composition, natural lighting, centered"
```
## Claude Code Integration
### How to Use in Claude Code
Claude Code can directly generate images using the automation system:
```python
from claude_integration import generate_asset
# Generate a single image
result = generate_asset(
category="product-photos",
name="luxury-watch",
prompt="A luxury leather watch with gold accents on white background, professional product photography, studio lighting, 4K, sharp focus",
size="1024x1024",
num_variations=1
)
print(f"Generated: {result['images']}")
```
### Setup for Claude Code
**Ensure these files are in your project:**
```
your-project/
├── vibe-creative-automation/
│ ├── fal_api.py
│ ├── creative_cli.py
│ ├── claude_integration.py
│ └── requirements.txt
└── assets/ (will be created automatically)
```
**Set environment variable:**
```bash
export FAL_API_KEY="your_key_here"
```
**Install dependencies:**
```bash
pip install requests
```
### Claude Code Workflow
When you ask Claude: **"Generate 3 variations of a product photo for my watch"**
Claude will:
1. **Read Image Generation skill** to understand prompting
2. **Read Creative Strategist** to get your style
3. **Craft the prompt** combining both
4. **Call automation system** with the prompt
5. **Generate 3 images** using FLUX model
6. **Save to folder** like `assets/product-photos/luxury-watch/`
7. **Show you results** with file paths
### Example: Claude Code Generates Product Photos
```python
from claude_integration import generate_asset
# Your Creative Strategist style (from your style guide)
YOUR_STYLE = {
"primary_style": "photorealistic",
"mood": "professional and luxurious",
"lighting": "studio lighting with rim light",
"composition": "centered"
}
# Generate product photo using your style
prompt = f"""
A luxury leather watch with gold accents,
{YOUR_STYLE['primary_style']},
{YOUR_STYLE['mood']},
{YOUR_STYLE['lighting']},
{YOUR_STYLE['composition']},
white background,
4K,
sharp focus,
professional product photography
"""
result = generate_asset(
category="product-photography",
name="luxury-watch",
prompt=prompt,
size="1024x1024",
num_variations=3
)
for img_path in result['images']:
print(f"✅ Generated: {img_path}")
```
### Batch Generation Example
```python
from claude_integration import batch_generate_assets
# Generate multiple assets at once
assets = [
{
"type": "custom",
"category": "product-photos",
"name": "watch",
"prompt": "Luxury watch, professional photography, studio lighting, 4K"
},
{
"type": "custom",
"category": "product-photos",
"name": "wallet",
"prompt": "Premium leather wallet, professional photography, studio lighting, 4K"
},
{
"type": "custom",
"category": "product-photos",
"name": "sunglasses",
"prompt": "Designer sunglasses, professional photography, studio lighting, 4K"
}
]
results = batch_generate_assets(assets)
for result in results:
print(f"{result['asset_name']}: {result['images']}")
```
## Image Sizes
Choose the right size for your use case:
| Size | Use Case | Speed | Detail |
|------|----------|-------|--------|
| 512x512 | Testing, thumbnails | Fast | Good |
| 768x768 | Social media, web | Medium | Good |
| 1024x1024 | Product photos, hero images | Medium | Excellent |
| 1536x1536 | Large prints, high-res | Slow | Excellent |
| 2048x2048 | 4K, maximum detail | Very Slow | Maximum |
## Generation Parameters
### Guidance Scale (3.5 - 7.5)
Controls how strictly the model follows your prompt:
```
3.5 — More creative freedom, less literal
5.0 — Balanced (recommended)
7.5 — Strict adherence to prompt, more literal
```
**Example:**
```python
# More creative
result = generate_asset(..., guidance_scale=3.5)
# Balanced (default)
result = generate_asset(..., guidance_scale=5.0)
# Strict
result = generate_asset(..., guidance_scale=7.5)
```
### Inference Steps (20 - 50)
More steps = higher quality but slower:
```
20 — Fast, acceptable quality
28 — Balanced (default)
40 — High quality
50 — Maximum quality
```
**Example:**
```python
# Fast generation
result = generate_asset(..., inference_steps=20)
# Balanced (default)
result = generate_asset(..., inference_steps=28)
# High quality
result = generate_asset(..., inference_steps=40)
```
## Practical Prompt Examples
### Product Photography
```
A luxury leather watch with gold accents on white background,
professional product photography, studio lighting with rim light,
centered composition, sharp focus, 4K, highly detailed
```
### Social Media Graphic
```
Instagram post graphic for product launch, vibrant colors,
eye-catching composition, modern design, 1080x1080 format,
trending aesthetic, professional quality
```
### Logo Design
```
Modern tech company logo, geometric style, blue and white colors,
minimalist design, scalable, professional, clean lines,
suitable for all media
```
### Illustration
```
Colorful illustration of a person working at a computer,
modern illustration style, bright colors, friendly mood,
professional quality, trending design
```
### Hero Image
```
A futuristic tech workspace with Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".