Tooluck logoTooluck
SKILL.md

nanobanana-skill

Agent skill fromfeiskyer/claude-code-settings

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.

How to install nanobanana-skill

install nanobanana-skill
# install the claude-code-settings pack with the skills CLI
npx skills add feiskyer/claude-code-settings

# or add only this skill to Claude Code: copy the folder

skills/nanobanana-skill/

# into

~/.claude/skills/nanobanana-skill/ (all projects)

.claude/skills/nanobanana-skill/ (one project)

skills/nanobanana-skill/SKILL.md

MITFull file
1# Nanobanana Image Generation Skill
2
3Generate or edit images using Google Gemini API through the nanobanana tool.
4
5## Requirements
6
71. **GEMINI_API_KEY**: Must be configured in `~/.nanobanana.env` or `export GEMINI_API_KEY=<your-api-key>`
82. **Python3 with dependent packages installed**: google-genai, Pillow, python-dotenv. They could be installed via `python3 -m pip install -r ${CLAUDE_SKILL_DIR}/requirements.txt` if not installed yet.
93. **Executable**: `${CLAUDE_SKILL_DIR}/nanobanana.py`
10
11## Instructions
12
13### For image generation
14
151. Ask the user for:
16 - What they want to create (the prompt)
17 - Desired aspect ratio/size (optional, defaults to 9:16 portrait)
18 - Output filename (optional, auto-generates UUID if not specified)
19 - Model preference (optional, defaults to gemini-nano-banana-2.1)
20 - Resolution (optional, defaults to 1K)
21
222. Run the nanobanana script with appropriate parameters:
23
24 ```bash
25 python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "description of image" --output "filename.png"
26 ```
27
283. Show the user the saved image path when complete
29
30### For image editing
31
321. Ask the user for:
33 - Input image file(s) to edit
34 - What changes they want (the prompt)
35 - Output filename (optional)
36
372. Run with input images:
38
39 ```bash
40 python3 ${CLAUDE_SKILL_DIR}/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"
41 ```
42
43## Available Options
44
45### Aspect Ratios (--size)
46
47- `1024x1024` (1:1) - Square
48…

Excerpt shown under the repository's MIT license.

More skills in claude-code-settings

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Leonxlnx /

taste-skill
113k

Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

CCCXCU1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates