agentleFS
ruizricaruizrica/agent-pi/skills/nano-banana/SKILL.md

nano-banana

Skill274 starsChanged 8 months agoMITView on GitHub

Generate or edit images with OpenRouter using the google/gemini-3.1-flash-image-preview model. Use when the user asks for image generation, wants a new visual from a text prompt, or wants modifications to an existing screenshot or image and expects an image file back.

40 other projects use a version of this.

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

  • jechearteSkill

    elevenlabs-tts

    Generate realistic audio from text using ElevenLabs Text-to-Speech API. Use when the user needs to convert text to speech, create voiceovers, generate narration, or produce audio content. Triggers include "generate audio", "text to speech", "TTS", "voiceover", "narration", "ElevenLabs", "audio from text", "read this text aloud

    Also in 5 projects that use this

  • +9 more from KISHOR403

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants an image back, either from a fresh prompt or from editing an existing image.

    line 9
  2. Distinctive:

    Make sure the prompt is explicit enough to produce the desired image.

    line 24
  3. Distinctive:

    If editing an image, first save or locate the input image path in the workspace.

    line 25
  4. Distinctive:

    After running it, tell the user the output file path.

    line 50
  5. Distinctive:

    If the model returns no image, inspect the JSON warning and summarize the failure clearly.

    line 51
  6. Distinctive:

    Prefer PNG outputs unless the user asks for another format.

    line 55
  7. Distinctive:

    If the user’s request is ambiguous, clarify what should change and what must remain untouched.

    line 57

“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

Use this skill when the user wants an image back, either from a fresh prompt or from editing an existing image.

Model

  • Provider: OpenRouter
  • Model: google/gemini-3.1-flash-image-preview
  • Friendly name: Nano Banana

Supported workflows

  1. Text-to-image: user provides a prompt, you generate an image.
  2. Image edit: user provides an image or screenshot plus instructions, you generate a modified image.

Before you run

  • Make sure the prompt is explicit enough to produce the desired image.
  • If editing an image, first save or locate the input image path in the workspace.
  • The script writes generated files to .context/generated-images/ by default.

Usage

Generate a new image

node agent/skills/nano-banana/generate-image.js \
  --prompt "A clean product hero shot of a matte black coffee grinder on a soft beige background, studio lighting" \
  --output .context/generated-images/coffee-grinder.png

Edit an existing image

node agent/skills/nano-banana/generate-image.js \
  --prompt "Keep the layout the same, but change the CTA button to green, replace the headline with 'Ship faster', and make the page look more premium" \
  --input-image path/to/screenshot.png \
  --output .context/generated-images/edited-screenshot.png

Response handling

  • The script prints JSON with an output field containing the saved image path.
  • After running it, tell the user the output file path.
  • If the model returns no image, inspect the JSON warning and summarize the failure clearly.

Notes

  • Prefer PNG outputs unless the user asks for another format.
  • Preserve existing composition when the user asks for modifications to a screenshot.
  • If the user’s request is ambiguous, clarify what should change and what must remain untouched.

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.