Nano Banana

What it does

When your agent uses it

• Users ask to generate images
• Edit images with AI
• Run Python scripts with uv
• Phrases include generate an image

Example prompts

• “generate an image”
• “create a picture”
• “make an image of”
• “/nano-banana”

Requirements

• Python 3
• A credential in GOOGLE_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Small scripts: Each script should do ONE thing (generate, refine, save)
2. 2Evaluate output: Always save images and print status to decide next steps
3. 3Use tmp/: Save generated images to tmp/ directory by default
4. 4Stateless execution: Each script runs independently, no cleanup needed

What it can do on your machine

Read from SKILL.md and the folder at commit 281c063. 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

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GOOGLE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nano Banana loads about 1.4k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 417 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.1k

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

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from NikiforovAll/claude-code-rules at commit 281c063, republished under its Apache-2.0 licence (© NikiforovAll). 417 words, ~1,417 tokens.

name

nano-banana

description

This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation request.

uv run - << 'EOF'
# /// script
# dependencies = ["google-genai", "pillow"]
# ///
from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["A cute banana character with sunglasses"],
    config=types.GenerateContentConfig(
        response_modalities=['IMAGE']
    )
)

for part in response.parts:
    if part.inline_data is not None:
        image = part.as_image()
        image.save("tmp/generated.png")
        print("Image saved to tmp/generated.png")
EOF

uv run - << 'EOF'
# /// script
# dependencies = ["google-genai", "pillow"]
# ///
from google import genai
from google.genai import types

client = genai.Client()

# Generate image
response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["YOUR PROMPT HERE"],
    config=types.GenerateContentConfig(
        response_modalities=['IMAGE']
    )
)

# Save result
for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        image = part.as_image()
        image.save("tmp/output.png")
        print("Saved: tmp/output.png")
EOF

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

config=types.GenerateContentConfig(
    response_modalities=['TEXT', 'IMAGE']
)

uv run - << 'EOF'
# /// script
# dependencies = ["google-genai", "pillow"]
# ///
from google import genai
from google.genai import types
from PIL import Image

client = genai.Client()

# Load existing image
img = Image.open("input.png")

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        "Add a party hat to this character",
        img
    ],
    config=types.GenerateContentConfig(
        response_modalities=['IMAGE']
    )
)

for part in response.parts:
    if part.inline_data is not None:
        part.as_image().save("tmp/edited.png")
        print("Saved: tmp/edited.png")
EOF

© NikiforovAll, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/handbook-nano-banana/skills/nano-banana of NikiforovAll/claude-code-rules.

• SKILL.md
• references/guide.md

Open the folder on GitHubat commit 281c063