Home / nicepkg / ai-workflow · GitHub

nano-banana-pro SKILL.md skillA

nano-banana-pro from nicepkg/ai-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add nicepkg/ai-workflow/nano-banana-pro@git:20260118.be84779

Pins git:20260118.be84779 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: nicepkg/ai-workflow
Path: workflows/talk-to-slidev-workflow/.claude/skills/nano-banana-pro/SKILL.md
Versions recorded: 1
Latest version: git:20260118.be84779, committed Jan 18, 2026
Size: 3,221 bytes
Repository stars: 291
License: MIT

Generate images using Google's Nano Banana Pro (gemini-3-pro-image-preview). Accepts text prompts and optionally images (for editing/transformation) as INPUT. Returns generated IMAGES as OUTPUT. Use when user asks to create, generate, edit, or draw images, infographics, visualizations, diagrams, charts, or illustrations. Excellent for data-accurate infographics and text rendering.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Nano Banana Pro Image Generator

Generate images using Google's advanced Nano Banana Pro model (`gemini-3-pro-image-preview`).

## Prerequisites

The user must have `GEMINI_API_KEY` environment variable set with a valid Google AI API key.

## Usage

The script is located in the same directory as this SKILL.md file. Run it with `uv run`:

```bash
uv run /path/to/skills/nano-banana-pro/generate_image.py "your prompt" -o output.png
```

When this skill is invoked, locate `generate_image.py` in the skill directory and run it.

### Parameters

| Parameter | Required | Description |
|-----------|----------|-------------|
| `prompt` | Yes | Text description of the image to generate or transformation to apply |
| `-o`, `--output` | Yes | Output filename (you decide the path based on context) |
| `-i`, `--image` | No | Input image(s) for editing/transformation or as context/reference (can be used multiple times) |
| `--aspect-ratio` | No | One of: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9` (default: `1:1`) |
| `--size` | No | Image size: `1K`, `2K`, `4K` (default: `1K`) |

### Examples

Basic image generation:
```bash
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add nicepkg/ai-workflow/nano-banana-pro@sha256:a99df82d313a463f

The line at the top of this page pins the label git:20260118.be84779, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_psdvpbsw5vphk4gj.svg)](https://markdownregistry.com/a/art_psdvpbsw5vphk4gj)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jan 18, 2026.

version	committed	commit	size	audit
git:20260118.be84779 latest	2026-01-18	be84779	3,221 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3221 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

nicepkg/ai-workflow · 291 stars · license MIT · pushed 2026-01-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_psdvpbsw5vphk4gj
GET https://markdownregistry.com/api/v1/resolve?ref=nicepkg/ai-workflow/nano-banana-pro
GET https://markdownregistry.com/api/v1/blob/a99df82d313a463f293f9e3cb983f511b806e8bea47bbd83131479af4dc0a4f5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nicepkg/ai-workflow

add-new-skills-to-workflow SKILL.md skill

nicepkg/ai-workflow · .claude/skills/add-new-skills-to-workflow/SKILL.md · Add new skills to an existing workflow and update all related documentation. Use when user wants to add skills from…

git:20260120.0b3efef · audit A · 291 stars

legacy-to-ai-ready SKILL.md skill

nicepkg/ai-workflow · .claude/skills/legacy-to-ai-ready/SKILL.md · Transform legacy codebases into AI-ready projects with Claude Code configurations. Use when (1) analyzing old projects…