Agent skill

Nano Banana

Generate or edit images using Google Nano Banana (Gemini image generation API).

Install Nano Banana

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nano-banana .claude/skills/nano-banana && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .claude/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/nano-banana .agents/skills/nano-banana && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .agents/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/nano-banana .cursor/skills/nano-banana && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .cursor/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/OpenMinis/MinisSkills.git --path nano-banana

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/nano-banana .gemini/skills/nano-banana && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .gemini/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/nano-banana .github/skills/nano-banana && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .github/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add OpenMinis/MinisSkills --skill nano-banana -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install OpenMinis/MinisSkills nano-banana --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenMinis/MinisSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/nano-banana .opencode/skills/nano-banana && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "nano-banana" agent skill from https://github.com/OpenMinis/MinisSkills/tree/main/nano-banana into .opencode/skills/nano-banana/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: nano-banana
GitHub stars: 446
Token cost: ~1.5k tokens
SKILL.md length: 503 words
Files: 4 (incl. scripts)
Skills in repo: 49
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate or edit images using Google Nano Banana (Gemini image generation API).

Works in 3 steps: Aspect ratio / resolution config → Environment variable loading → Saving images
This skill whenever the user asks to generate an image
SKILL.md covers Quick Workflow, Environment Setup, Model Selection and ⚠️ Known API Pitfalls, plus 5 more sections
Runs Python scripts from its folder; calls python3 and pip; needs GEMINI_API_KEY

What it does

Nano Banana is an agent skill from OpenMinis/MinisSkills. Generate or edit images using Google Nano Banana (Gemini image generation API). Trigger this skill whenever the user asks to generate an image, draw something, create artwork, edit a photo, or mentions "nano banana", "nanobanana", or any AI image generation/editing need — even if they don't explicitly mention Nano Banana. Proactively use this skill for any image creation or transformation request.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/batch.py`, `scripts/edit.py` and `scripts/gen.py`).

It sits in Media & Creative, covering Image generation. It works with Google Gemini and Python. The repository describes itself as: Skills collection for Minis. The licence is MIT.

When your agent uses it

This skill whenever the user asks to generate an image
Mentions nano banana
Any AI image generation/editing need — even if they dont explicitly mention Nano Banana
Any image creation

Example prompts

“nano banana”
“nanobanana”
“/nano-banana”

Requirements

Python 3
A credential in GEMINI_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Aspect ratio / resolution config
Environment variable loading
Saving images

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- aistudio.google.com
- ai.google.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- GEMINI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nano Banana loads about 1.5k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 503 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~103
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 503 words, ~1,485 tokens.

Download SKILL.mdSave it as .claude/skills/nano-banana/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: nano-banana
description: Generate or edit images using Google Nano Banana (Gemini image generation API). Trigger this skill whenever the user asks to generate an image, draw something, create artwork, edit a photo, or mentions "nano banana", "nanobanana", or any AI image generation/editing need — even if they don't explicitly mention Nano Banana. Proactively use this skill for any image creation or transformation request.

Nano Banana — Image Generation Skill

Generate or edit images locally using the Google Gemini image generation API (a.k.a. Nano Banana).

Quick Workflow

Check environment (API key + dependencies)
Identify the mode: text-to-image / image editing / batch generation
Choose the right model
Use the bundled scripts directly — no need to rewrite them
Run the script and save output to /var/minis/attachments/
Display the result inline in the conversation

Environment Setup

Check API Key

bash

source /etc/profile && echo $GEMINI_API_KEY | head -c 10

⚠️ Always run source /etc/profile first — environment variables are stored there and won't be available otherwise.

If not set, direct the user to Google AI Studio to obtain a key, then:

bash

echo 'export GEMINI_API_KEY="your_key_here"' >> /etc/profile

Check Dependencies

bash

pip show google-genai pillow 2>&1 | grep -E "^Name|not found"

If missing:

bash

pip install google-genai pillow

Model Selection

Model	Model ID	Best For
Nano Banana 2 (recommended)	`gemini-3.1-flash-image-preview`	Fast, high quality, 2K support — default choice
Nano Banana Pro	`gemini-3-pro-image-preview`	Complex prompts, professional assets, precise text rendering
Nano Banana (original)	`gemini-2.5-flash-image`	Ultra-low latency, simple tasks

Default to gemini-3.1-flash-image-preview unless the user explicitly requests another version.

⚠️ Known API Pitfalls

1. Aspect ratio / resolution config

❌ Wrong (old API, throws AttributeError):

python

# types.ImageGenerationConfig does not exist!
image_generation_config=types.ImageGenerationConfig(aspect_ratio="16:9")

✅ Correct:

python

config=types.GenerateContentConfig(
    response_modalities=["IMAGE"],
    image_config=types.ImageConfig(
        aspect_ratio="16:9",  # options: 1:1, 4:3, 3:4, 16:9, 9:16
        image_size="2K",      # options: 1K, 2K (default: 1K)
    ),
)

2. Environment variable loading

❌ Running python3 script.py directly may not have the API key
✅ Always prefix with source /etc/profile && python3 script.py

3. Saving images

part.as_image() returns a PIL Image object — call .save(path) directly. No need to handle base64 manually.

Bundled Scripts

Run any script with:

bash

source /etc/profile && python3 <skill-path>/nano-banana/scripts/<script>.py [args]

📄 `gen.py` — Text to Image

Usage:  gen.py "prompt" [output_path] [aspect_ratio] [resolution]
Example: gen.py "a panda drinking tea in a bamboo forest" /var/minis/attachments/out.png 1:1 2K

📄 `edit.py` — Image Editing (image + prompt → image)

Usage:   edit.py <input_image> "edit instruction" [output_path]
Example: edit.py /var/minis/attachments/photo.jpg "add a wizard hat to the cat" /var/minis/attachments/edited.png

📄 `batch.py` — Batch Generation (multiple prompts → multiple images)

Edit the TASKS list at the top of the script, then run it.

Step-by-Step

When the user makes an image generation request:

Understand the request — text-to-image, image editing, or batch?
Check API key — source /etc/profile && echo $GEMINI_API_KEY | head -c 10
Verify scripts exist — ls <skill-path>/nano-banana/scripts/
If scripts are missing, use file_write to recreate them from the source in this skill
Run the appropriate script:
- Text-to-image: source /etc/profile && python3 <skill-path>/nano-banana/scripts/gen.py "prompt" /var/minis/attachments/out.png 16:9 2K
- Image editing: source /etc/profile && python3 <skill-path>/nano-banana/scripts/edit.py <image_path> "instruction" /var/minis/attachments/out.png
- Batch: edit TASKS in scripts/batch.py, then run it
Display the result — ![description](minis://attachments/out.png)

Show full SKILL.md (170 more words)Show less

Prompt Tips

Describe a scene, don't just stack keywords — "An elderly Japanese potter focused at the wheel, soft afternoon light through a studio window, photorealistic" beats "Japan pottery old man realistic"
Specify style explicitly — for photography add camera details ("50mm lens, shallow depth of field"); for illustration name the style ("Ghibli-style watercolor")
Text in images — spell out exactly what text should appear; the model renders it more accurately when it's explicit
Iterate with edit.py — make small adjustments on an existing image rather than regenerating from scratch
Aspect ratio guide — 16:9 for banners/social media, 1:1 for avatars/covers, 9:16 for phone wallpapers, 3:4 for portrait cards

Troubleshooting

Issue	Cause & Fix
`AttributeError: ImageGenerationConfig`	Deprecated API — use `image_config=types.ImageConfig(...)` instead
`KeyError: GEMINI_API_KEY`	Run `source /etc/profile` before executing the script
Only text returned, no image	Ensure `response_modalities` includes `"IMAGE"`
Poor image quality	Switch to `gemini-3-pro-image-preview` or refine the prompt
Rate limit error	Free tier has limits — wait a moment and retry
Save fails	Confirm `/var/minis/attachments/` directory exists

References

Official docs: https://ai.google.dev/gemini-api/docs/image-generation
Get an API key: https://aistudio.google.com/apikey

Files

SKILL.md and 3 other files (scripts) in nano-banana of OpenMinis/MinisSkills.

SKILL.md
scripts/batch.py
scripts/edit.py
scripts/gen.py

Open the folder on GitHubat commit ae8c5db

Compare with similar skills

Nano Banana next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nano Banana compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Nano Banana this skillOpenMinis/MinisSkills	446	—	~1.5k	Automated safety check: Pass	MIT	3 days ago
Gemini Imagetyrchen/geektime-bootcamp-ai	236	—	~1.1k	Automated safety check: Pass	None	6 mo ago
Gemini Interactions APIAyuilos/Miffan	225	—	~4.6k	Automated safety check: Pass	AGPL-3.0	today
Gflow CLIffroliva/gflow-cli	278	—	~4.8k	Automated safety check: Notes	MIT	today
Nanobananakenneth-liao/ai-launchpad-marketplace	126	—	~4k	Automated safety check: Notes	None	6 mo ago
Nano Banana Usecnemri/google-genai-skills	127	—	~587	Automated safety check: Pass	MIT	8 mo ago

Similar skills

Gemini Image
tyrchen/geektime-bootcamp-ai
Reference guide for using google-genai Python library to generate images with gemini-3-pro-image-preview model.
236 GitHub stars~1.1k tokensUpdated 6 mo ago
Media & CreativeAuto-check passed
Gemini Interactions API
Ayuilos/Miffan
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses…
225 GitHub stars~4.6k tokensUpdated today
Media & CreativeAuto-check passed
Gflow CLI
ffroliva/gflow-cli
A skill your agent uses when the user wants to drive Google Flow (Veo image-to-video, Veo text-to-video, Imagen / Nano Banana image generation) from the terminal or a script — including…
278 GitHub stars~4.8k tokensUpdated today
Media & CreativeAuto-check: notes
Nanobanana
kenneth-liao/ai-launchpad-marketplace
AI image generation and editing using Google Gemini models. An agent skill from kenneth-liao/ai-launchpad-marketplace.
126 GitHub stars~4k tokensUpdated 6 mo ago
Media & CreativeAuto-check: notes
Nano Banana Use
cnemri/google-genai-skills
Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts.
127 GitHub stars~587 tokensUpdated 8 mo ago
Media & CreativeAuto-check passed
Nanobanana Skill
feiskyer/claude-code-settings
Generate or edit images via Google Gemini (nanobanana). An agent skill from feiskyer/claude-code-settings.
1.7k GitHub stars~1.1k tokensUpdated 13 days ago
Media & CreativeAuto-check passed

Questions about Nano Banana

What does Nano Banana do?

Generate or edit images using Google Nano Banana (Gemini image generation API). Nano Banana is an agent skill from OpenMinis/MinisSkills. Generate or edit images using Google Nano Banana (Gemini image generation API).

When should I use Nano Banana?

Nano Banana fits situations like: this skill whenever the user asks to generate an image; mentions nano banana; any AI image generation/editing need — even if they dont explicitly mention Nano Banana; any image creation.

How do I install Nano Banana in Claude Code?

Run `npx skills add OpenMinis/MinisSkills --skill nano-banana -a claude-code`. Or copy the skill folder (nano-banana in OpenMinis/MinisSkills) into .claude/skills/nano-banana in your project. Claude Code loads it when a task matches its description.

How do I install Nano Banana in Codex?

Run `npx skills add OpenMinis/MinisSkills --skill nano-banana -a codex`. Or copy the skill folder (nano-banana in OpenMinis/MinisSkills) into .agents/skills/nano-banana in your project. Codex loads it when a task matches its description.

Can I use Nano Banana in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenMinis/MinisSkills --skill nano-banana -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nano-banana, .gemini/skills/nano-banana, .github/skills/nano-banana and .opencode/skills/nano-banana in your project.

What does Nano Banana need to run?

Going by SKILL.md and its folder, Nano Banana needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and pip) and credentials named GEMINI_API_KEY. Our summary lists: Python 3; A credential in GEMINI_API_KEY.

Does Nano Banana access the network?

SKILL.md names 2 domains. As links in the text: aistudio.google.com and ai.google.dev. This is read from the text; nothing was executed.

Is Nano Banana safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Nano Banana use?

Nano Banana is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nano Banana use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nano Banana?

Skills that share tags, products or a category with Nano Banana: Gemini Image (tyrchen/geektime-bootcamp-ai, 236 stars), Gemini Interactions API (Ayuilos/Miffan, 225 stars), Gflow CLI (ffroliva/gflow-cli, 278 stars) and Nanobanana (kenneth-liao/ai-launchpad-marketplace, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nano Banana?

OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 446 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.

Source: OpenMinis/MinisSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Nano Banana

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Nano Banana — Image Generation Skill

Quick Workflow

Environment Setup

Check API Key

Check Dependencies

Model Selection

⚠️ Known API Pitfalls

1. Aspect ratio / resolution config

2. Environment variable loading

3. Saving images

Bundled Scripts

📄 gen.py — Text to Image

📄 edit.py — Image Editing (image + prompt → image)

📄 batch.py — Batch Generation (multiple prompts → multiple images)

Step-by-Step

Prompt Tips

Troubleshooting

References

Files

Compare with similar skills

Similar skills

More from OpenMinis/MinisSkills

Related

Questions about Nano Banana

📄 `gen.py` — Text to Image

📄 `edit.py` — Image Editing (image + prompt → image)

📄 `batch.py` — Batch Generation (multiple prompts → multiple images)