nanobanana-skill
Generate, edit, or composite images with Gemini/Nanobanana. Default for image requests without a named provider; do not override a different provider the user chose.
- Installs
- 120
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/feiskyer/codex-settings --skill nanobanana-skill- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads nanobanana-skill automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Nanobanana Image Skill
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.
Requirements
GEMINI_API_KEYin~/.nanobanana.env(GEMINI_API_KEY=sk-dummy) or the shell environment.- Python dependencies from
requirements.txt. - The executable is
nanobanana.pyin 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.
Defaults
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.
Run it
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
Grounded generation, saving the model's text and metadata alongside the image:
python3 /absolute/path/to/nanobanana.py \
--prompt "Use Google Search to ground an editorial illustration about the most recent lunar mission and create a clean magazine cover concept" \
--text-output /absolute/path/to/output/cover.txt \
--metadata-output /absolute/path/to/output/cover.json \
--output /absolute/path/to/output/cover.png
Then report the saved path(s), whether search grounding stayed enabled, where any text or thought summaries landed, and any warning from the run. If the model returns text but no image, say so plainly and suggest a more explicitly image-focused prompt rather than presenting the run as a success.
Prompting
Good Nanobanana prompts are production briefs, not art wishes: subject, visual style, composition or camera framing, any required text, the output's use case, and constraints such as brand colors, negative space, or realism level.
Create a premium sparkling water can advertisement. Use a cold studio product-photo look, silver highlights, condensation droplets, and a clean dark-teal background. Leave negative space in the upper-right for headline copy.
For edits, say what to preserve as well as what to change:
Keep the shoe silhouette and logo placement intact. Replace the background with a bright outdoor basketball court, add dynamic afternoon shadows, and keep the image looking like a real sports campaign photo.
When a run fails
Check credential presence without printing its value, input readability, and output writability. For an unsupported option, consult the helper's accepted values. Correct assistant-chosen options within the requested result, but do not silently switch a user-selected model or provider. Before a bounded retry, check whether the earlier attempt already produced output; report the actual error if recovery would require new authority or changing the request.
FAQ
What does the nanobanana-skill skill do?
Generate, edit, or composite images with Gemini/Nanobanana. Default for image requests without a named provider; do not override a different provider the user chose.
How do I install nanobanana-skill?
Run npx skills add https://github.com/feiskyer/codex-settings --skill nanobanana-skill in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/nanobanana-skill/ (personal) or .claude/skills/nanobanana-skill/ (project).
Which AI agents can use nanobanana-skill?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is nanobanana-skill safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains nanobanana-skill?
It is published by feiskyer in feiskyer/codex-settings. It has 120 recorded installs.
More from feiskyer/codex-settings
deep-research
feiskyer/codex-settings
用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。用于确实需要分头取证的研究，不用于单次查证或已给定材料的总结。
autonomous-skill
feiskyer/codex-settings
Use when work must continue across multiple Codex sessions with .autonomous/ tracking, resumable execution, or autonomous handoff. Use for long-running, multi-session, or resume-later tasks.
youtube-transcribe-skill
feiskyer/codex-settings
Open the skill to read its SKILL.md instructions.
spec-kit-skill
feiskyer/codex-settings
Open the skill to read its SKILL.md instructions.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image