nano-banana
You have access to image generation tools powered by Google's Gemini Image models.
Install / Use
npx skills add accucrazy/openclaw-taiwanInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
OtherSupported Platforms
Our assessment of nano-banana
nano-banana scores 57/100 on our quality scale, 292nd of 301 Other skills we index.
Its SKILL.md is 1.3 KB long, split into 6 sections with 1 code example: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- The repository was last updated about 9 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-10-18 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 74/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
nano-banana compared with similar skills
All 4 of these similar skills score higher than nano-banana; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| nano-banana (this skill)by accucrazy | 57 | 0 | 9mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 110.8k | 1d ago | CLAUDE.md |
| LocalAIby mudler | 100 | 50.2k | today | MCP Server |
| algorithmic-artby anthropics | 100 | 177.9k | 44d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 44d ago | SKILL.md |
Frequently asked questions
- How do I install nano-banana?
- Run
npx skills add accucrazy/openclaw-taiwan. The install tabs above show the steps for each supported agent. - Which AI agents does nano-banana work with?
- It is written for Gemini CLI, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is nano-banana safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 74/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is nano-banana still maintained?
- The repository was last updated about 9 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubNano Banana Image Generation
You have access to image generation tools powered by Google's Gemini Image models.
Available Tools
nano_banana_generate
Generate images from text descriptions. Use this when the user asks to:
- Create, generate, or draw an image
- Make a picture, illustration, or artwork
- Visualize something as an image
Parameters:
prompt(required): Detailed description of the image to generatemodel(optional): "flash" for speed (default), "pro" for quality
Example:
{
"prompt": "A cute orange tabby cat sleeping on a sunny windowsill, watercolor style",
"model": "flash"
}
nano_banana_edit
Edit existing images using text prompts. Use this when the user wants to modify an image.
Important Notes
- Always use nano_banana_generate when the user asks for image generation - do NOT draw with ASCII art
- After generating, use the
messagetool with the returnedimagePathto share the image - Be specific in prompts: include style, composition, colors, and subject details
- If generation fails, inform the user and offer alternatives
Workflow
- User asks for an image → Call
nano_banana_generatewith a detailed prompt - Tool returns
imagePath→ Usemessagetool to send the image to the user - If error occurs → Inform user and suggest trying again with different prompt
Related Skills
taste-skill
110.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
LocalAI
50.2kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.