How do I install the Nano Banana Pro skill?

Run npx skillmds@latest add mouadja02/nano-banana-pro in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Nano Banana Pro safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Nano Banana Pro?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Nano Banana Pro free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Nano Banana Pro?

mouadja02 (@mouadja02) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Nano Banana Pro by mouadja02 — Agent Skill

Name: Nano Banana Pro
Author: mouadja02

File contents

Nano Banana Pro — Gemini Image Generation & Editing

Attribution: Sourced from steipete/agent-scripts by Peter Steinberger.

When to Use

Generating images from text prompts via Gemini Flash Image API
Editing existing images with targeted modifications
Iterating on image prompts using the draft→iterate→final workflow

Generate new images or edit existing ones using Google's Gemini Flash Image API (Gemini 3.1 Flash Image).

Prerequisites

uv installed (brew install uv)
GEMINI_API_KEY environment variable set

Usage

Generate new image:

uv run generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 512|1K|2K|4K] [--api-key KEY]

Edit existing image:

uv run generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 512|1K|2K|4K]

Default Workflow (draft → iterate → final)

Goal: fast iteration without burning time on 4K until the prompt is correct.

Draft (1K): quick feedback loop

uv run generate_image.py --prompt "<draft prompt>" --filename "$(date +%Y-%m-%d-%H-%M-%S)-draft.png" --resolution 1K

Iterate: adjust prompt in small diffs; keep filename new per run.

Final (4K): only when prompt is locked

uv run generate_image.py --prompt "<final prompt>" --filename "$(date +%Y-%m-%d-%H-%M-%S)-final.png" --resolution 4K

Resolution Options

Input	API Value
"thumbnail", "tiny", "512"	`512`
Default (no mention)	`1K`
"1080p", "1K"	`1K`
"2K", "2048", "medium"	`2K`
"high-res", "4K", "ultra"	`4K`

Prompt Templates

Generation:

"Create an image of: <subject>. Style: <style>. Composition: <camera/shot>. Lighting: <lighting>. Background: <background>. Color palette: <palette>. Avoid: <list>."

Editing (preserve everything else):

"Change ONLY: <single change>. Keep identical: subject, composition/crop, pose, lighting, color palette, background, and overall style. Do not add new objects."

Preflight & Common Failures

# Preflight
command -v uv
echo ${GEMINI_API_KEY:0:5}...  # show prefix only

Common failures:

Error: No API key provided. → set GEMINI_API_KEY or pass --api-key
Error loading input image: → wrong path; verify --input-image points to a real image
quota/permission/403 → wrong key, no access, or quota exceeded

---name: nano-banana-prodescription: Gemini image gen/edit via Nano Banana: text/image input, 512-4K workflows, draft→iterate→final.---# Nano Banana Pro — Gemini Image Generation & Editing> **Attribution:** Sourced from [steipete/agent-scripts](https://github.com/steipete/agent-scripts) by [Peter Steinberger](https://github.com/steipete).## When to Use- Generating images from text prompts via Gemini Flash Image API- Editing existing images with targeted modifications- Iterating on image prompts using the draft→iterate→final workflowGenerate new images or edit existing ones using Google's Gemini Flash Image API (Gemini 3.1 Flash Image).## Prerequisites- `uv` installed (`brew install uv`)- `GEMINI_API_KEY` environment variable set## Usage**Generate new image:**```bashuv run generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 512|1K|2K|4K] [--api-key KEY]```**Edit existing image:**```bashuv run generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 512|1K|2K|4K]```## Default Workflow (draft → iterate → final)Goal: fast iteration without burning time on 4K until the prompt is correct.1. **Draft (1K)**: quick feedback loop ```bash uv run generate_image.py --prompt "<draft prompt>" --filename "$(date +%Y-%m-%d-%H-%M-%S)-draft.png" --resolution 1K ```2. **Iterate**: adjust prompt in small diffs; keep filename new per run.3. **Final (4K)**: only when prompt is locked ```bash uv run generate_image.py --prompt "<final prompt>" --filename "$(date +%Y-%m-%d-%H-%M-%S)-final.png" --resolution 4K ```## Resolution Options| Input | API Value ||-------|-----------|| "thumbnail", "tiny", "512" | `512` || Default (no mention) | `1K` || "1080p", "1K" | `1K` || "2K", "2048", "medium" | `2K` || "high-res", "4K", "ultra" | `4K` |## Prompt Templates**Generation:**> "Create an image of: `<subject>`. Style: `<style>`. Composition: `<camera/shot>`. Lighting: `<lighting>`. Background: `<background>`. Color palette: `<palette>`. Avoid: `<list>`."**Editing (preserve everything else):**> "Change ONLY: `<single change>`. Keep identical: subject, composition/crop, pose, lighting, color palette, background, and overall style. Do not add new objects."## Preflight & Common Failures```bash# Preflightcommand -v uvecho ${GEMINI_API_KEY:0:5}... # show prefix only```Common failures:- `Error: No API key provided.` → set `GEMINI_API_KEY` or pass `--api-key`- `Error loading input image:` → wrong path; verify `--input-image` points to a real image- `quota/permission/403` → wrong key, no access, or quota exceeded

Frequently asked questions

Nano Banana Pro