Gemini Image Simple

Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.

Security Scan

The skill is internally consistent: it implements its stated image-generation/editing functionality, requires only GEMINI_API_KEY, has no install step, and its code matches the SKILL.md instructions.

Purpose & Capability

Skill name/description (generate/edit images with Gemini) match the included script and required environment variable. The script calls Google's generativelanguage API, uses only GEMINI_API_KEY, and reads/writes image files as expected.

Instruction Scope

SKILL.md instructs the agent to set GEMINI_API_KEY and run the provided Python script. The runtime instructions and script only read local image files (when editing), access the declared environment variable, and send/receive image data to the Google API endpoint. There is no code or instruction to read unrelated system files, other environment variables, or send data to unexpected endpoints.

Install Mechanism

No install spec is provided (instruction-only plus one script). This minimizes disk-writing/install risk. The script uses only Python stdlib; no external downloads or package installs are present.

Credentials

Only GEMINI_API_KEY is required, which is proportional to the skill's need to authenticate to the Gemini/Generative Language API. No unrelated credentials or config paths are requested.

Persistence & Privilege

The skill does not request always: true, does not modify other skills, and has no installation hooks or persistent privileges. It runs only when invoked.

Assessment

This skill appears to do what it claims, but exercise normal caution before installing code from an unknown source: (1) Review the script (already included) and confirm you trust the publisher; (2) Store your GEMINI_API_KEY securely — the script places the key in the request URL as a query parameter, which can be logged by intermediaries (consider using a more secure header-based auth if you control the environment); (3) Be aware model names are preview/beta and usage will consume your API quota and may be billed; (4) Avoid sending sensitive images to third-party APIs; (5) If you need stricter assurance, run the script in an isolated environment or container and/or replace the URL/auth handling with your organization’s approved client/secret management. Overall the package is coherent and low risk given the included source matches the documentation.

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) - the highest quality image generation model.

Why This Skill

Feature	This Skill	Others (nano-banana-pro, etc.)
Dependencies	None (stdlib only)	google-genai, pillow, etc.
Requires pip/uv	❌ No	✅ Yes
Works on Fly.io free	✅ Yes	❌ Fails
Works in containers	✅ Yes	❌ Often fails
Image generation	✅ Full	✅ Full
Image editing	✅ Yes	✅ Yes
Setup complexity	Just set API key	Install packages first

Bottom line: This skill works anywhere Python 3 exists. No package managers, no virtual environments, no permission issues.

Quick Start

# Generate
python3 /data/clawd/skills/gemini-image-simple/scripts/generate.py "A cat wearing a tiny hat" cat.png

# Edit existing image  
python3 /data/clawd/skills/gemini-image-simple/scripts/generate.py "Make it sunset lighting" edited.png --input original.png

Usage

Generate new image

python3 {baseDir}/scripts/generate.py "your prompt" output.png

Edit existing image

python3 {baseDir}/scripts/generate.py "edit instructions" output.png --input source.png

Supported input formats: PNG, JPG, JPEG, GIF, WEBP

Environment

Set GEMINI_API_KEY environment variable. Get one at https://aistudio.google.com/apikey

How It Works

Uses Nano Banana Pro (nano-banana-pro-preview) - Google's highest quality image generation model:

• Pure urllib.request for HTTP (no requests library)
• Pure json for parsing (stdlib)
• Pure base64 for encoding (stdlib)

That's it. No external packages. Works on any Python 3.10+ installation.

Model

Currently using: nano-banana-pro-preview (also known as Gemini 3 Pro Image)

Other available models (can be changed in generate.py if needed):

• gemini-3-pro-image-preview - Same as Nano Banana Pro
• imagen-4.0-ultra-generate-001 - Imagen 4.0 Ultra
• imagen-4.0-generate-001 - Imagen 4.0
• gemini-2.5-flash-image - Gemini 2.5 Flash with image gen

Examples

# Landscape
python3 {baseDir}/scripts/generate.py "Misty mountains at sunrise, photorealistic" mountains.png

# Product shot
python3 {baseDir}/scripts/generate.py "Minimalist product photo of a coffee cup, white background" coffee.png

# Edit: change style
python3 {baseDir}/scripts/generate.py "Convert to watercolor painting style" watercolor.png --input photo.jpg

# Edit: add element
python3 {baseDir}/scripts/generate.py "Add a rainbow in the sky" rainbow.png --input landscape.png