Nano Banana Pro Prompts Recommend Skill
Pull proven text-to-image prompts from a 10,000+ library matched to portraits, products, social posts, or marketing visuals.
Overview
Nano Banana Pro Prompts Recommend is an agent skill most often used in Grow (also Validate landing, Launch distribution) that recommends image-generation prompts from a 10,000+ curated library.
Install
npx skills add https://github.com/youmind-openlab/nano-banana-pro-prompts-recommend-skill --skill nano-banana-pro-prompts-recommend-skillWhat is this skill?
- Recommends from 10,000+ curated Nano Banana Pro community prompts with sample images
- Works across Nano Banana Pro, Gemini, GPT Image, Seedream, Midjourney, DALL-E, Flux, and Stable Diffusion
- Use-case routing for portraits, products, social media, posters, and editorial illustrations
- Model-agnostic positioning with optional ai-image-prompts sibling skill on ClawHub
- Translates and explains prompt techniques so builders learn structure, not just copy-paste
- 10,000+ community-curated Nano Banana Pro prompts
- Cross-model support including Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion
Adoption & trust: 3.4k installs on skills.sh; 1.6k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need on-brand AI images fast but do not know which prompt structure actually works for your use case or model.
Who is it for?
Indie creators and marketers who generate visuals across multiple models and want a searchable prompt library instead of one-off experimentation.
Skip if: Builders who only need local SD LoRA training pipelines or strict brand-governed asset pipelines with no generative AI.
When should I use this skill?
User wants AI image prompts, prompt recommendations for a use case, marketing illustrations, or to browse the Nano Banana Pro prompt library.
What do I get? / Deliverables
You receive matched, battle-tested prompts and technique notes ready to run in your chosen text-to-image tool.
- Tailored prompt text with technique explanation
- Use-case-matched recommendations from the curated library
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Grow content because the skill’s primary payoff is illustrations and campaign-ready imagery that compounds distribution. Content subphase covers article art, social creatives, and prompt templates that feed lifecycle marketing—not model training.
Where it fits
Pick hero and feature illustration prompts before you publish a waitlist landing page.
Generate social and poster prompt sets for a Product Hunt or launch week push.
Refresh blog and newsletter artwork with proven portrait or product prompt patterns.
Source consistent diagram and cover art prompts for in-app help or README visuals.
How it compares
Curated prompt librarian for image models—not an image renderer or LoRA trainer.
Common Questions / FAQ
Who is nano-banana-pro-prompts-recommend-skill for?
Solo builders and small teams creating marketing, social, and editorial visuals with Nano Banana Pro, Gemini, or other text-to-image tools.
When should I use nano-banana-pro-prompts-recommend-skill?
In Validate for landing and prototype visuals, in Launch for distribution creatives, and in Grow when you need fresh content prompts for articles, video, or campaigns.
Is nano-banana-pro-prompts-recommend-skill safe to install?
Check the Security Audits panel on this page; the skill recommends prompts and may reference external YouMind resources rather than executing image generation itself.
SKILL.md
READMESKILL.md - Nano Banana Pro Prompts Recommend Skill
> 📖 Prompts curated by [YouMind](https://youmind.com/nano-banana-pro-prompts) · 10,000+ community prompts · [Try generating images →](https://youmind.com/nano-banana-pro-prompts) > > 🔗 Looking for a model-agnostic version? Try [ai-image-prompts](https://clawhub.com/skill/ai-image-prompts) — same library, universal positioning. # Nano Banana Pro Prompts Recommendation You are an expert at recommending image generation prompts from the Nano Banana Pro prompt library (10,000+ prompts). These prompts are optimized for Nano Banana Pro (Google Gemini) but work with any text-to-image model including Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, and Stable Diffusion. ## ⚠️ CRITICAL: Sample Images Are MANDATORY **Every prompt recommendation MUST include its sample image.** This is not optional — images are the core value of this skill. Users need to SEE what each prompt produces before choosing. - Each prompt has `sourceMedia[]` — always send `sourceMedia[0]` as an image - If `sourceMedia` is empty, skip that prompt entirely - **Never present a prompt as text-only** — always attach the image ## Quick Start User provides image generation need → You recommend matching prompts **with sample images** → User selects a prompt → (If content provided) Remix to create customized prompt. ### Two Usage Modes 1. **Direct Generation**: User describes what image they want → Recommend prompts → Done 2. **Content Illustration**: User provides content (article/video script/podcast notes) → Recommend prompts → User selects → Collect personalization info → Generate customized prompt based on their content ## Setup After installing this skill, the prompt library is automatically downloaded from GitHub via `postinstall`. No credentials needed — all data is publicly available. If references are missing, run manually: ```bash node scripts/setup.js ``` **Keep references up to date** (GitHub syncs community prompts twice daily): ```bash # Force pull latest references (recommended weekly) pnpm run sync # or equivalently node scripts/setup.js --force ``` Before Step 2, check whether references are stale (>24h since last update): ```bash node scripts/setup.js --check ``` This fetches the latest `references/*.json` files from: https://github.com/YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill/tree/main/references ## Available Reference Files The `references/` directory contains categorized prompt data (auto-generated daily by GitHub Actions). **Categories are dynamic** — read `references/manifest.json` to get the current list: ```json // references/manifest.json (example) { "updatedAt": "2026-02-28T10:00:00Z", "totalPrompts": 10224, "categories": [ { "slug": "social-media-post", "title": "Social Media Post", "file": "social-media-post.json", "count": 6382 }, { "slug": "product-marketing", "title": "Product Marketing", "file": "product-marketing.json", "count": 3709 } // .