agentleFS
mikeOnBreezemikeOnBreeze/cc-crossbeam/.claude/skills/nano-banana/SKILL.md

nano-banana

Skill297 starsChanged 9 months agoMITView on GitHub

This skill enables image generation and editing using Google's Gemini Nano Banana models. Use this skill when the user asks to generate images from text prompts, edit existing images, or modify pictures. Supports text-to-image generation, image editing with prompts, and multi-image reference for consistency.

  • Reads credentials
  • Installs packages

40 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use agency-docs-updater, brand-agency and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • KISHOR403Skill

    agency-docs-updater

    End-to-end pipeline for publishing Claude Code lab meetings. Automatically finds/creates Fathom transcript, downloads video, uploads to YouTube, generates fact-checked Russian summary, creates MDX documentation, and pushes to agency-docs for Vercel deployment. Single invocation replaces 5+ manual steps.

    Also in 3 projects that use this

  • KISHOR403Skill

    brand-agency

    Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.

    Also in 3 projects that use this

  • krishagelSkill

    elevenlabs-tts

    Generate high-quality audio from text using Eleven Labs API. Use for podcasts, narration, voice-overs, and audio summaries.

    Also in 5 projects that use this

  • +9 more from KISHOR403

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All generated images include SynthID watermarking (invisible, added by Gemini)

    line 114
  2. Very specific:

    Ensure dependencies are installed: pip install -r scripts/requirements.txt

    line 117

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nano Banana

Image generation and editing skill powered by Google Gemini's Nano Banana models.

Prerequisites

This skill requires a GEMINI_API_KEY in the project's .env or .env.local file:

GEMINI_API_KEY=your_api_key_here

To obtain an API key, visit: https://aistudio.google.com/apikey

Capabilities

1. Text-to-Image Generation

Generate images from text descriptions using scripts/generate_image.py:

python scripts/generate_image.py "a serene Japanese garden with cherry blossoms" \
  --aspect-ratio 16:9

Parameters:

  • prompt (required): Text description of the image to generate
  • --output: Output directory or file path (default: current directory)
  • --filename: Custom filename (default: auto-generated with timestamp)
  • --aspect-ratio: Image aspect ratio (default: 1:1)
  • --model: Model to use (default: gemini-3-pro-image-preview)

2. Image Editing

Edit existing images with text prompts using scripts/edit_image.py:

python scripts/edit_image.py "remove the background and make it transparent" \
  --images photo.png

python scripts/edit_image.py "change the sky to sunset colors" \
  --images landscape.jpg \
  --output edited_landscape.png

Multiple Image Support (for consistency/reference):

python scripts/edit_image.py "create a collage combining these images" \
  --images img1.png img2.png img3.png \
  --aspect-ratio 16:9

Parameters:

  • prompt (required): Text description of the edit
  • --images (required): One or more input image paths
  • --output: Output directory or file path (default: current directory)
  • --filename: Custom filename (default: auto-generated)
  • --aspect-ratio: Output aspect ratio (optional)
  • --model: Model to use

Supported Parameters

Aspect Ratios

1:1 | 2:3 | 3:2 | 3:4 | 4:3 | 4:5 | 5:4 | 9:16 | 16:9 | 21:9

Models

  • gemini-3-pro-image-preview (default) - Nano Banana Pro: Higher quality, advanced reasoning, supports up to 14 reference images
  • gemini-2.5-flash-image - Nano Banana: Faster generation, lower cost, good for quick iterations

Usage Examples

Generate a logo:

python scripts/generate_image.py "minimalist tech company logo, blue gradient, modern" \
  --aspect-ratio 1:1 --filename logo.png

Generate social media content:

python scripts/generate_image.py "cozy coffee shop interior, warm lighting" \
  --aspect-ratio 9:16

Edit a product photo:

python scripts/edit_image.py "place this product on a wooden table with soft lighting" \
  --images product.png --aspect-ratio 4:3

Quick iteration with Flash model:

python scripts/generate_image.py "abstract art, vibrant colors" \
  --model gemini-2.5-flash-image

Resources

scripts/

  • generate_image.py - Text-to-image generation script
  • edit_image.py - Image editing with text prompts
  • requirements.txt - Python dependencies (install with pip install -r requirements.txt)

references/

  • api_reference.md - Detailed API documentation, error codes, and troubleshooting

Notes

  • All generated images include SynthID watermarking (invisible, added by Gemini)
  • Pro model supports up to 14 reference images for style/subject consistency
  • Images are saved as JPEG by default (based on API response)
  • Ensure dependencies are installed: pip install -r scripts/requirements.txt

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.