playbooks

home / skills / jjuidev / jss / ai-artist

ai-artist skill

/.claude/skills/ai-artist

This skill generates AI artwork using Nano Banana prompts with validation and multiple modes to tailor mood and style.

npx playbooks add skill jjuidev/jss --skill ai-artist

Review the files below or copy the command above to add this skill to your agents.

Files (24)
SKILL.md
3.5 KB
---
name: ai-artist
description: "Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent."
version: 3.1.0
license: MIT
---

# AI Artist - Nano Banana Image Generation

Generate images using 129 curated prompts from awesome-nano-banana-pro-prompts collection.

**Validation interview is mandatory** (use `--skip` to bypass).

## Workflow

**IMPORTANT:** Follow `references/validation-workflow.md` when this skill is activated.

## Quick Start

```bash
python3 scripts/generate.py "<concept>" -o <output.png> [--mode MODE]
```

### Generation Modes

| Mode | Description |
|------|-------------|
| `search` | Find best matching prompt from 129 curated prompts (default) |
| `creative` | Remix elements from top 3 matching prompts |
| `wild` | Out-of-the-box creative interpretation (random style transform) |
| `all` | Generate all 3 variations |

### Examples

```bash
# Default search mode
python3 scripts/generate.py "tech conference banner" -o banner.png -ar 16:9

# Creative remix (combines multiple prompts)
python3 scripts/generate.py "AI workshop" -o workshop.png --mode creative

# Wild/experimental (random artistic transformation)
python3 scripts/generate.py "product showcase" -o product.png --mode wild

# Generate all 3 variations at once
python3 scripts/generate.py "futuristic city" -o city.png --mode all -v
```

### Options

| Flag | Description |
|------|-------------|
| `-o, --output` | Output path (required) |
| `-m, --mode` | search, creative, wild, or all |
| `-ar, --aspect-ratio` | 1:1, 16:9, 9:16, etc. |
| `--model` | flash (fast) or pro (quality/4K) |
| `-v, --verbose` | Show matched prompts and details |
| `--dry-run` | Show prompt without generating |
| `--skip` | Bypass validation interview |

---

## Prompt Database

**129 curated prompts** extracted from awesome-nano-banana-pro-prompts:

```bash
# Search prompts
python3 scripts/search.py "<query>" --domain awesome

# View all prompts
cat data/awesome-prompts.csv
```

### Categories include:
- **Profile/Avatar**: Thought-leader headshots, mirror selfies
- **Infographics**: Bento grid, chalkboard, ingredient labels
- **Social Media**: Quote cards, banners, thumbnails
- **Product**: Commercial shots, e-commerce, Apple-style
- **Artistic**: Ukiyo-e, patent documents, vaporwave, cyberpunk
- **Character**: Anime, chibi, comic storyboards

---

## Wild Mode Transformations

The `wild` mode randomly applies one of these artistic transformations:

- Japanese Ukiyo-e woodblock print
- Premium liquid glass Bento grid infographic
- Vintage 1800s patent document
- Surreal dreamscape with volumetric god rays
- Cyberpunk neon aesthetic with holograms
- Hand-drawn chalkboard explanation
- Isometric 3D diorama
- Cinematic movie poster
- Vaporwave aesthetic with glitch effects
- Apple-style product showcase

---

## References

| Topic | File |
|-------|------|
| **Validation Workflow** | `references/validation-workflow.md` |
| All Prompts | `data/awesome-prompts.csv` |
| Nano Banana Guide | `references/nano-banana.md` |
| Image Prompting | `references/image-prompting.md` |
| Source | `references/awesome-nano-banana-pro-prompts.md` |

---

## Scripts

| Script | Purpose |
|--------|---------|
| `generate.py` | Main image generation with 3 modes |
| `search.py` | Search prompts database |
| `extract_prompts.py` | Extract prompts from markdown |
| `core.py` | BM25 search engine |

Overview

This skill generates high-quality images using Nano Banana and a curated set of 129 professional prompts. A mandatory validation interview refines style, mood, and colors for reliable outputs (use --skip to bypass). Three generation modes—search, creative, and wild—let you prioritize accuracy, remixing, or experimental transforms across styles like Ukiyo-e, cyberpunk, and cinematic.

How this skill works

Provide a concept string and the tool matches it to the best prompts from the 129 curated entries or combines top matches depending on mode. The validation interview collects constraints (style, mood, palette, aspect ratio) and applies them to the selected prompt(s) before generation. Wild mode applies random artistic transformations; creative mode remixes elements from top matches; search mode finds the closest single prompt.

When to use it

  • When you need rapid, professional-looking concept art or banners from a short text brief.
  • When you want consistent outputs tuned by a brief validation interview for brand or campaign work.
  • When exploring multiple stylistic variations quickly with search, creative, or wild approaches.
  • When producing social media assets, avatars, product showcases, or stylized art pieces.
  • When you need reproducible prompts from a curated, production-ready prompt database.

Best practices

  • Complete the validation interview for consistent color, mood, and composition control; use --skip only for quick experiments.
  • Start in search mode to identify the closest prompt, then use creative mode to remix elements or wild for experimental directions.
  • Use aspect ratio and model flags (--model flash or pro) to control framing and quality for final assets.
  • Run --dry-run or -v to inspect matched prompts and tweak your concept before committing to generation.
  • Keep prompts concise and include target uses (e.g., banner, avatar, poster) to improve matching accuracy.

Example use cases

  • Create a 16:9 tech conference banner in cinematic style using search mode for precise matches.
  • Generate social media quote cards with a Bento grid infographic aesthetic by remixing top prompts in creative mode.
  • Produce a vintage patent-style product illustration using wild mode for a retro technical look.
  • Make a character avatar in Ukiyo-e or anime style by validating facial expressions and color palette in the interview.
  • Explore unexpected artistic directions for a product showcase by running wild mode transformations.

FAQ

Is the validation interview mandatory?

Yes, the interview is mandatory to ensure outputs match your constraints; use --skip only for quick experimental runs.

What does wild mode do?

Wild mode applies a random artistic transformation from a curated set (Ukiyo-e, cyberpunk, vaporwave, etc.) for highly creative results.