corespeed-nanobanana

Generate and edit images using Google Gemini models via Corespeed AI Gateway. Supports text-to-image generation, image editing, multi-image input, and text r...

Security Scan

The skill's code, environment requirements, and instructions align with its stated purpose (using a Corespeed AI Gateway to run Google Gemini models); nothing requests unrelated credentials or does unexpected system-level actions.

Purpose & Capability

Name/description (Gemini image & text generation via Corespeed AI Gateway) match the required binary (uv), the two env vars (CS_AI_GATEWAY_BASE_URL, CS_AI_GATEWAY_API_TOKEN), and the included script which uses the Google genai client pointed at the gateway.

Instruction Scope

Runtime instructions and the script are scoped to sending prompts and input images to the configured gateway and saving returned media/text locally. The script logs prompt snippets and input/output file paths and sizes; it will upload any input files provided and send prompt text to the gateway — this is expected for the skill but means those artifacts are transmitted to the gateway host.

Install Mechanism

The skill is instruction-only (no forced installer), but SKILL.md metadata suggests 'pip install uv' and the script relies on uv to create a venv and install google-genai at runtime. This is a typical, moderate-risk behavior (packages come from PyPI). No arbitrary download URLs or archive extraction were observed.

Credentials

Only the gateway base URL and API token are required and actually used by the script. No unrelated secrets, system config paths, or extra credentials are requested.

Persistence & Privilege

always is false and the skill doesn't attempt to modify other skills or system-wide configuration. It writes its own output files only (user-specified paths).

Assessment

This skill sends prompts and any input images to the CS_AI_GATEWAY_BASE_URL using CS_AI_GATEWAY_API_TOKEN — only install it if you trust the gateway host. Verify the gateway URL and token come from a trusted Corespeed instance (or your own gateway). Be aware the tool will upload provided input files and will print full file paths and short prompt text to stdout; if those are sensitive, run in an isolated environment, use ephemeral credentials, or avoid supplying sensitive images/text. Installing/running will cause uv and google-genai packages to be installed in an isolated venv — review those packages if you require stricter supply-chain controls.

Corespeed NanoBanana — Gemini Image & Text Generation

Auth: Set CS_AI_GATEWAY_BASE_URL and CS_AI_GATEWAY_API_TOKEN environment variables.

Workflow

1. Pick a model from the table below (default: gemini-2.5-flash-image for image generation)
2. Run the script with your prompt

Usage

uv run {baseDir}/scripts/gemini.py --prompt "your prompt" -f output.ext [-i input.ext] [--model MODEL]

• --prompt, -p — Text prompt (required)
• --filename, -f — Output filename (required)
• --input, -i — Input image file(s), repeat for multiple
• --model, -m — Model name (default: gemini-2.5-flash-image)
• --modalities — Response type: auto, image, text, image+text (default: auto)
• --json — Output structured JSON (recommended for agent consumption)

Output format is determined by file extension: .png/.jpg → image generation, .txt/.md → text output.

Image Generation

# Text-to-image
uv run {baseDir}/scripts/gemini.py -p "a watercolor fox in autumn forest" -f fox.png

# Image editing
uv run {baseDir}/scripts/gemini.py -p "Remove background, add beach sunset" -f edited.png -i photo.jpg

# Multi-image compositing
uv run {baseDir}/scripts/gemini.py -p "Blend these two scenes together" -f blend.png -i scene1.png -i scene2.png

Image Analysis

# Describe an image
uv run {baseDir}/scripts/gemini.py -p "Describe this image" -f desc.txt -i photo.jpg --model gemini-2.5-flash

# Compare images
uv run {baseDir}/scripts/gemini.py -p "What are the differences?" -f diff.txt -i before.jpg -i after.jpg --model gemini-2.5-flash

Text Generation

# Use the most capable model for complex tasks
uv run {baseDir}/scripts/gemini.py -p "Write a haiku about coding" -f haiku.txt --model gemini-2.5-pro

Models

Model	Type	Best For
gemini-2.5-flash-image	Image + Text	Image generation & editing (default)
gemini-2.5-flash	Text	Fast analysis, vision, general tasks
gemini-2.5-pro	Text	Complex reasoning, highest quality
gemini-2.5-flash-lite	Text	Fastest, simple tasks

Notes

• No manual Python setup required. The script uses PEP 723 inline metadata. uv run automatically creates an isolated virtual environment and installs the google-genai dependency on first run.
• Image output is returned inline as base64 from the Gemini API — no separate download step.
• Use timestamps in filenames: yyyy-mm-dd-hh-mm-ss-name.ext.
• Script prints MEDIA: line for OpenClaw to auto-attach generated images.
• Do not read generated media back; report the saved path only.
• Only gemini-2.5-flash-image can generate images. Other models are text-only.
• Use --json for structured output: {"ok": true, "files": [...], "text": "...", "model": "...", "tokens": {...}}

Support

Built by Corespeed. If you need help or run into issues:

• 💬 Discord: discord.gg/mAfhakVRnJ
• 🐦 X/Twitter: @CoreSpeed_io
• 🐙 GitHub: github.com/corespeed-io/skills