Nanobanana Image Generation Skill
Generate or edit images using Google Gemini API through the nanobanana tool.
Requirements
- GEMINI_API_KEY: Must be configured in
~/.nanobanana.env or export GEMINI_API_KEY=<your-api-key>
- Python3 with dependent packages installed: google-genai, Pillow, python-dotenv. They could be installed via
python3 -m pip install -r ${CLAUDE_SKILL_DIR}/requirements.txt if not installed yet.
- Executable:
${CLAUDE_SKILL_DIR}/nanobanana.py
Instructions
For image generation
Ask the user for:
- What they want to create (the prompt)
- Desired aspect ratio/size (optional, defaults to 9:16 portrait)
- Output filename (optional, auto-generates UUID if not specified)
- Model preference (optional, defaults to gemini-3.1-flash-image-preview)
- Resolution (optional, defaults to 1K)
Run the nanobanana script with appropriate parameters:
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "description of image" --output "filename.png"
Show the user the saved image path when complete
For image editing
Ask the user for:
- Input image file(s) to edit
- What changes they want (the prompt)
- Output filename (optional)
Run with input images:
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"
Available Options
Aspect Ratios (--size)
1024x1024 (1:1) - Square
832x1248 (2:3) - Portrait
1248x832 (3:2) - Landscape
864x1184 (3:4) - Portrait
1184x864 (4:3) - Landscape
896x1152 (4:5) - Portrait
1152x896 (5:4) - Landscape
768x1344 (9:16) - Portrait (default)
1344x768 (16:9) - Landscape
1536x672 (21:9) - Ultra-wide
Models (--model)
gemini-3.1-flash-image-preview (default) - Latest, fast generation
gemini-3-pro-image-preview - Higher quality, supports thinking/reasoning
Resolution (--resolution)
Other Options
--no-search - Disable Google Search grounding (enabled by default)
--no-think - Disable thinking/reasoning mode
Examples
Generate a simple image
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "A serene mountain landscape at sunset with a lake"
Generate with specific size and output
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
--prompt "Modern minimalist logo for a tech startup" \
--size 1024x1024 \
--output "logo.png"
Generate landscape image with high resolution
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
--prompt "Futuristic cityscape with flying cars" \
--size 1344x768 \
--resolution 2K \
--output "cityscape.png"
Edit existing images
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
--prompt "Add a rainbow in the sky" \
--input photo.png \
--output "photo-with-rainbow.png"
Use pro model for higher quality
python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
--prompt "Detailed portrait of a cat in watercolor style" \
--model gemini-3-pro-image-preview \
--output "cat-portrait.png"
Error Handling
If the script fails:
- Check that
GEMINI_API_KEY is exported or set in ~/.nanobanana.env
- Verify input image files exist and are readable
- Ensure the output directory is writable
- If no image is generated, try making the prompt more specific about wanting an image
Best Practices
- Be descriptive in prompts - include style, mood, colors, composition
- For logos/graphics, use square aspect ratio (1024x1024)
- For social media posts, use 9:16 for stories or 1:1 for posts
- For wallpapers, use 16:9 or 21:9
- Start with 1K resolution for testing, upgrade to 2K/4K for final output
- Use gemini-3-pro-image-preview for best quality, gemini-3.1-flash-image-preview (default) for speed
1---
2name: nanobanana-skill
3description: 'Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑". Do NOT use for diagrams (架构图/流程图/时序图) — draw those with Mermaid or code instead.'
4allowed-tools: Read, Write, Glob, Grep, Task, Bash(cat:*), Bash(ls:*), Bash(tree:*), Bash(python3:*)
5metadata:
6 source: https://skillmd.com/skills/feiskyer/nanobanana-skill
7---
8
9# Nanobanana Image Generation Skill
10
11Generate or edit images using Google Gemini API through the nanobanana tool.
12
13## Requirements
14
151. **GEMINI_API_KEY**: Must be configured in `~/.nanobanana.env` or `export GEMINI_API_KEY=<your-api-key>`
162. **Python3 with dependent packages installed**: google-genai, Pillow, python-dotenv. They could be installed via `python3 -m pip install -r ${CLAUDE_SKILL_DIR}/requirements.txt` if not installed yet.
173. **Executable**: `${CLAUDE_SKILL_DIR}/nanobanana.py`
18
19## Instructions
20
21### For image generation
22
231. Ask the user for:
24 - What they want to create (the prompt)
25 - Desired aspect ratio/size (optional, defaults to 9:16 portrait)
26 - Output filename (optional, auto-generates UUID if not specified)
27 - Model preference (optional, defaults to gemini-3.1-flash-image-preview)
28 - Resolution (optional, defaults to 1K)
29
302. Run the nanobanana script with appropriate parameters:
31
32 ```bash
33 python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "description of image" --output "filename.png"
34 ```
35
363. Show the user the saved image path when complete
37
38### For image editing
39
401. Ask the user for:
41 - Input image file(s) to edit
42 - What changes they want (the prompt)
43 - Output filename (optional)
44
452. Run with input images:
46
47 ```bash
48 python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"
49 ```
50
51## Available Options
52
53### Aspect Ratios (--size)
54
55- `1024x1024` (1:1) - Square
56- `832x1248` (2:3) - Portrait
57- `1248x832` (3:2) - Landscape
58- `864x1184` (3:4) - Portrait
59- `1184x864` (4:3) - Landscape
60- `896x1152` (4:5) - Portrait
61- `1152x896` (5:4) - Landscape
62- `768x1344` (9:16) - Portrait (default)
63- `1344x768` (16:9) - Landscape
64- `1536x672` (21:9) - Ultra-wide
65
66### Models (--model)
67
68- `gemini-3.1-flash-image-preview` (default) - Latest, fast generation
69- `gemini-3-pro-image-preview` - Higher quality, supports thinking/reasoning
70
71### Resolution (--resolution)
72
73- `1K` (default)
74- `2K`
75- `4K`
76
77### Other Options
78
79- `--no-search` - Disable Google Search grounding (enabled by default)
80- `--no-think` - Disable thinking/reasoning mode
81
82## Examples
83
84### Generate a simple image
85
86```bash
87python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "A serene mountain landscape at sunset with a lake"
88```
89
90### Generate with specific size and output
91
92```bash
93python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
94 --prompt "Modern minimalist logo for a tech startup" \
95 --size 1024x1024 \
96 --output "logo.png"
97```
98
99### Generate landscape image with high resolution
100
101```bash
102python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
103 --prompt "Futuristic cityscape with flying cars" \
104 --size 1344x768 \
105 --resolution 2K \
106 --output "cityscape.png"
107```
108
109### Edit existing images
110
111```bash
112python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
113 --prompt "Add a rainbow in the sky" \
114 --input photo.png \
115 --output "photo-with-rainbow.png"
116```
117
118### Use pro model for higher quality
119
120```bash
121python3 ${CLAUDE_SKILL_DIR}/nanobanana.py \
122 --prompt "Detailed portrait of a cat in watercolor style" \
123 --model gemini-3-pro-image-preview \
124 --output "cat-portrait.png"
125```
126
127## Error Handling
128
129If the script fails:
130
131- Check that `GEMINI_API_KEY` is exported or set in ~/.nanobanana.env
132- Verify input image files exist and are readable
133- Ensure the output directory is writable
134- If no image is generated, try making the prompt more specific about wanting an image
135
136## Best Practices
137
1381. Be descriptive in prompts - include style, mood, colors, composition
1392. For logos/graphics, use square aspect ratio (1024x1024)
1403. For social media posts, use 9:16 for stories or 1:1 for posts
1414. For wallpapers, use 16:9 or 21:9
1425. Start with 1K resolution for testing, upgrade to 2K/4K for final output
1436. Use gemini-3-pro-image-preview for best quality, gemini-3.1-flash-image-preview (default) for speed