Nano Banana

Organization

social-media-skills

nano-banana

Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media — the image-prompt-craft mini-skill. Run when the user wants a nano-banana / Gemini image prompt, an AI image for a post (quote graphic, carousel slide, thumbnail, infographic, product shot, ad creative), or conversational image editing. Reads brand-profile for brand colours/style. Strengths: best-in-class legible in-image text (route typography/layout-led design to ideogram), multi-image consistency, conversational editing, and Google's photoreal lane (Imagen deprecated); surreal art stays Midjourney's. Teaches prompt anatomy, the text-first approach, reference-image consistency, and per-platform aspect ratios. Honest: SynthID watermark + AI disclosure; never real identifiable people or copyrighted characters/logos; verify spelling/data. The API/connection and WoopSocial upload flow live in tools/integrations/nano-banana.md.

Overview

Publisher	social-media-skills
Repository	`skills`
Skill name	`nano-banana`
Stars	215
Forks	44
Bundled files	5
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Nano Banana AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/social-media-skills/skills/tree/main/skills/nano-banana
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/nano-banana .claude/skills/nano-banana

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nano Banana in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nano Banana on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nano Banana is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Nano Banana (image prompt craft)

Write prompts that get studio-quality images out of Nano Banana — Google's Gemini image model (Nano Banana Pro = Gemini 3 Pro Image; the Flash variant is faster/cheaper). This is the prompt-craft layer of a three-layer setup:

Connection/API (model IDs, auth, the generate → upload to WoopSocial Media → attach flow) → tools/integrations/nano-banana.md.
Prompt craft (this skill) → how to ask for the right image well.
In-skill application → e.g. carousel-writer's image-prompt-pack.

Fast-moving area — re-verify model names/capabilities quarterly.

Reach for Nano Banana when… (match the job)

Its real strengths: legible in-image text (best in class), multi-image/character consistency, conversational editing, and Search-grounded infographics. Reach elsewhere for typography/layout-led design (→ ideogram) or surreal/fine-art aesthetics (Midjourney). (Imagen, the former photoreal sibling, is deprecated — Gemini API shutdown Aug 17, 2026 — so Google-side photoreal work now lands here.) Don't default it to every job. (Details: references/when-and-how-to-prompt.md.)

Step 0 — Read the brand + the job

Load brand-profile.md (colours, visual style, do/don't). Identify the job (quote graphic / carousel / thumbnail / infographic / product shot / background / ad / edit) and the platform aspect ratio.

Step 1 — Write the prompt (natural language, not keyword spam)

Describe, don't pad. Include subject · composition/camera · action/context · lighting/atmosphere · style/medium · constraints + exact text. Drop "4k, masterpiece, trending on artstation" tokens — modern Gemini models reason over natural language. Bake in the brand palette/style. Set the aspect ratio. Iterate cheap at 1K, finalize at 2K/4K. See references/when-and-how-to-prompt.md.

Step 2 — Use the superpowers deliberately

Text: put the exact words in quotes + font + placement; settle the copy first (the text-first approach), keep it short, and verify the spelling in the output.
Consistency: use reference images and a locked style description; generate a set one at a time ("everything the same except X"); hold the aspect ratio; review for drift.
Editing: natural-language changes to a hero image for locale/seasonal/A-B variants.

See references/text-and-consistency.md.

Step 3 — Pick the recipe

Adapt a pattern for the job (quote graphic, carousel set, thumbnail, infographic, product/lifestyle, background, ad), with the right aspect ratio and brand grounding. See references/social-recipes.md.

Step 4 — Verify, disclose, ship

Verify rendered text and any infographic data before publishing (the model can misspell / misplace facts).
Disclose AI generation per platform/region (Meta "Made with AI", EU AI Act); every image carries a SynthID watermark (+ C2PA) — don't strip it or pass the image off as a non-AI photo.
Ship: generate per the integration guide → upload bytes to WoopSocial Media → attach to the post via scheduling-and-queue. WoopSocial doesn't generate images.

Quality bar — self-check

Did I match the tool to the job (and say when to use another model)?
Is the prompt natural-language and specific (subject/composition/lighting/style/text), brand- grounded, with the right aspect ratio?
For text: exact words in quotes + font + placement, copy-first, spelling verified?
For sets: references + locked style, one-at-a-time, reviewed for drift?
Did I handle SynthID + disclosure, verify text/data, and refuse real people / IP?
Did I point to tools/integrations/nano-banana.md for the API + WoopSocial flow (no claim that WoopSocial generates images)?

Edge cases & pushback

Photoreal headshot / surreal art → suggest the better-fit model; don't force Nano Banana.
"logo, 4k, masterpiece, trending…" → rewrite into a specific scene description; drop token spam.
Real person / copyrighted character / brand style → refuse; offer an original alternative.
"Post it as a normal photo" → SynthID + disclosure; don't disguise AI imagery.
Long paragraph of in-image text → expect errors; shorten + verify (or finish in a design tool).
"Generate it in WoopSocial" → WoopSocial doesn't generate; this skill prompts the model, then the image is uploaded to Media and attached.

tools/integrations/nano-banana.md — API/model IDs, auth, pricing, the upload-to-WoopSocial flow.
carousel-writer (image-prompt-pack), reels-script — consuming skills; ideogram — typography sibling.
brand-profile — the visual brand; caption-writer/hook-writer — the in-image copy.
scheduling-and-queue — attach the image to a post and publish.

References

references/when-and-how-to-prompt.md — when to reach for it vs other models, and the prompt anatomy.
references/text-and-consistency.md — the two superpowers: legible in-image text and multi-image consistency/editing.
references/social-recipes.md — adaptable prompt patterns per social job + aspect ratios.
references/examples.md — weak→strong prompts, a consistent carousel, an edit, and honest scope.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/evals.json4 KB
references/examples.md3 KB
references/social-recipes.md3 KB
references/text-and-consistency.md3 KB
references/when-and-how-to-prompt.md4 KB

Frequently asked questions

What does the Nano Banana AI skill do?

Why use Nano Banana on TypingMind?

Because you install it once and use it with any model. Nano Banana is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nano Banana in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/nano-banana. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Nano Banana?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nano Banana?

As many as you like. As long as a model supports skills, you can use Nano Banana with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nano Banana AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Accessibility

affaan-m

CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Archify

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Nano Banana

Overview