Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →feiskyer/nanobanana-skill
Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑".
Passed 6 of 11 test cases with the skill, and 4 of 11 without it.
and 4 more in the full report
6 fixed5 passed either way8 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to edit an existing portrait photo at `/photos/headshot.png` to add a subtle warm background glow, saving to `/photos/headshot_glow.png`. Should an explicit aspect ratio flag be set?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends leaving aspect ratio unspecified | Passed | Passed |
| Passes --input /photos/headshot.png | Missed | Passed |
The instructions your model reads when the skill loads.
Use the bundled nanobanana.py to generate or edit images with Gemini image models. The default path targets Nano Banana 2 (gemini-3.1-flash-image-preview) with thinking summaries and Google Search grounding on, because those defaults are the main reason to use this skill instead of a generic image prompt.
GEMINI_API_KEY in ~/.nanobanana.env (GEMINI_API_KEY=sk-dummy) or the shell environment.requirements.txt.nanobanana.py in this same skill directory. Resolve its absolute path once before running it.The CLI can print --help without credentials. It validates local input files before creating an API client and exits non-zero when the API returns no image.
Model gemini-3.1-flash-image-preview, search grounding on, thinking summaries on at level high, resolution 1K, and no aspect ratio unless the request implies a shape. Do not make the user choose a model, search mode, or thinking mode unless they asked for that level of control.
Leaving aspect ratio unspecified is usually better for edits, because Gemini can match the input image shape. For text-only generation, set one only when the user implies a format such as poster, square post, banner, phone wallpaper, or ultrawide hero.
Worth overriding: --model gemini-3-pro-image-preview for very detail-heavy or typography-sensitive work (slower); --resolution 512px for quick ideation (Nanobanana 2 models only), 2K/4K for polished deliverables; --thinking-level low when latency beats refinement; search off when the user wants a purely imaginative result. Run python3 /absolute/path/to/nanobanana.py --help for the exact accepted values, including the full aspect-ratio and model lists.
Generate from text:
python3 /absolute/path/to/nanobanana.py \
--prompt "Create a high-end coffee bag package design with tactile paper texture and clear typography" \
--output /absolute/path/to/output/package.png
Edit or composite — pass every reference with --input. Nanobanana 2 mixes multiple references well, so do not narrow a blend, lineup, storyboard, or consistency pass down to a single image:
python3 /absolute/path/to/nanobanana.py \
--prompt "Turn these product photos into a clean ecommerce hero image with a soft studio shadow and subtle headline area" \
--input /absolute/path/to/ref1.png /absolute/path/to/ref2.png \
--aspect-ratio 4:5 \
--output /absolute/path/to/output/hero.png
test cases passed, vs 4 / 11 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.