Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
90
86%
Does it follow best practices?
Impact
96%
2.82xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Resolution mapping and filename format
Absolute script path
0%
100%
uv run used
0%
100%
Standard quality → 1K
0%
100%
Medium quality → 2K
0%
100%
Ultra/print quality → 4K
0%
100%
Uppercase K in resolutions
0%
100%
Timestamp filename format
0%
100%
Descriptive filename suffix
0%
100%
No cd to skill dir
100%
100%
Prompts passed as-is
60%
100%
Image editing with input-image parameter
--input-image used
0%
100%
No pre-read of input
100%
100%
Editing instructions in prompt
100%
100%
No post-read of output
100%
100%
Output filenames differ from input
100%
100%
Absolute script path
0%
100%
uv run used
0%
100%
Timestamp filename pattern
0%
0%
All three photos edited
100%
100%
No cd to skill directory
100%
100%
API key argument and prompt fidelity
--api-key argument used
0%
100%
Key not set as env var
80%
100%
Prompt passed unchanged
100%
100%
High resolution → 4K
0%
100%
Uppercase K in resolution
0%
100%
Absolute script path
0%
100%
uv run used
0%
100%
Timestamp filename format
0%
100%
example_call.sh uses --api-key
60%
100%
Prompt preserved in example
100%
100%
9f7f750
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.