nano-banana
Skill17 starsChanged 4 months agoMITView on GitHub
Generate and edit high-quality AI images using Google's Gemini image models (Nano Banana series) via MCP. Use when user wants to create images, edit photos, generate graphics, or needs visual content with text rendering. Supports gemini-3.1-flash-image-preview (Nano Banana 2) and gemini-2.5-flash-image-preview (Nano Banana).
- Reads credentials
40 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- okou-ai/okou-skillstheir own version, first seen Nov 11, 2026
- runapi-ai/nano-bananatheir own version, first seen Nov 8, 2026
- frontdesk-alhouse/alto-ostheir own version, first seen Nov 8, 2026
- hwangx/claude-skill-nano-bananatheir own version, first seen Nov 6, 2026
- agentrix-ai/skillstheir own version, first seen Oct 20, 2026
- Samueladewole/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use agency-docs-updater, brand-agency and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
KISHOR403Skillagency-docs-updater
End-to-end pipeline for publishing Claude Code lab meetings. Automatically finds/creates Fathom transcript, downloads video, uploads to YouTube, generates fact-checked Russian summary, creates MDX documentation, and pushes to agency-docs for Vercel deployment. Single invocation replaces 5+ manual steps.
Also in 3 projects that use this
KISHOR403Skillbrand-agency
Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.
Also in 3 projects that use this
jechearteSkillelevenlabs-tts
Generate realistic audio from text using ElevenLabs Text-to-Speech API. Use when the user needs to convert text to speech, create voiceovers, generate narration, or produce audio content. Triggers include "generate audio", "text to speech", "TTS", "voiceover", "narration", "ElevenLabs", "audio from text", "read this text aloud
Also in 5 projects that use this
- +9 more from KISHOR403
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- nilecui/SkillsBase★ 2790% same
Wrote their own version · 39
- OpenMinis/MinisSkills★ 612same name
- EvoScientist/EvoSkills★ 486same name
- glebis/claude-skills★ 414same name
- kkoppenhaver/cc-nano-banana★ 368same name
- mikeOnBreeze/cc-crossbeam★ 297same name
- ruizrica/agent-pi★ 274same name
- LichAmnesia/lich-skills★ 233same name
- refly-ai/refly-skills★ 204same name
- okou-ai/okou-skills★ 81same name
- vm0-ai/vm0-skills★ 81same name
29 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- agent-engineeringSkill
- app-marketing-copySkill
- ascii-pixel-artSkill
- autopredictSkill
- autoresearchSkill
- babysit-prSkill
- bird-fastSkill
- blockchain-auditorSkill
- brainstormingSkill
- ceo-reviewSkill
- ck-reviewSkill
- cloudflare-managerSkill
- codex-advisorSkill
- content-trend-researcherSkill
- continuous-learningSkill
- coreml-optimizerSkill
- cto-reviewSkill
- direct-mail-strategistSkill
- evangelion-designSkill
- executing-plansSkill
- freshdesk-apiSkill
- gemini-image-generatorSkill
- gemini-visualSkill
- github-actions-templatesSkill
- googleSkill
- gsplat-optimizerSkill
- hyperagentSkill
- idea-mdSkill
- imagegenSkill
- ios-app-testerSkill
- llm-advisorSkill
- llm-evaluationSkill
- macos-appsSkill
- markdown-fetchSkill
- mcp-builderSkill
- mcp-testerSkill
- opensea-apiSkill
- paperclipSkill
- playdate-devSkill
- poke-assistantSkill
- poplar-direct-mailSkill
- practical-typographySkill
- prompt-factorySkill
- qmdSkill
- scientific-critical-thinkingSkill
- security-best-practicesSkill
- security-threat-modelSkill
- seo-optimizerSkill
- shadertoySkill
- skill-finderSkill
- skimmableSkill
- subway-infoSkill
- systematic-debuggingSkill
- tui-designerSkill
- ui-designSkill
- video-editorSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 36 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 197
Use history:0 reference in subsequent prompts
- Distinctive: line 244
Never committed to version control
- Very specific: line 246
Use .env files for key management in projects
- Distinctive: line 272
Process Mapper: - Create diagram visuals
- Distinctive: line 273
Research to Essay: - Add illustrations to content
“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nano Banana - AI Image Generation via MCP
Generate stunning 4K images, edit photos, and create graphics with perfect text rendering using Google's Gemini image models via MCP. The default model is gemini-3.1-flash-image-preview (Nano Banana 2), launched February 2026.
When to Use
Invoke when user:
- Asks to "generate an image" or "create a picture"
- Wants to "edit this photo" or "modify this image"
- Needs graphics with text (logos, infographics, diagrams)
- Requests "consistent characters" across multiple images
- Says "visualize this" or "make me a [visual thing]"
Prerequisites
1. Gemini API Key
Get a free API key from Google AI Studio:
- Sign in with Google account
- Click "Get API Key" → "Create API Key"
- Copy and save securely
2. MCP Server Setup
Recommended: NanoBanana-MCP (uses Gemini 3.1 Flash Image for highest quality)
# Quick install via Claude Code CLI
claude mcp add nano-banana --env GEMINI_API_KEY=your-key-here -- npx -y nanobanana-mcpOr add to ~/.claude/settings.json manually:
{
"mcpServers": {
"nano-banana": {
"command": "npx",
"args": ["-y", "nanobanana-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}Alternative: Nano-Banana-MCP by ConechoAI (Gemini 2.0 Flash - faster, lower cost)
{
"mcpServers": {
"nano-banana": {
"command": "npx",
"args": ["nano-banana-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}Available Tools
Once MCP is configured, these tools become available:
Core Tools
| Tool | Purpose | Key Parameters |
gemini_generate_image | Create new images from text prompts | prompt, model, aspectRatio, imageSize |
gemini_edit_image | Modify existing images with instructions | imagePath, instructions, model |
continue_editing | Refine the last generated image | instructions |
get_image_history | List all generated images in session | - |
Model Options
| Model ID | Description |
gemini-3.1-flash-image-preview | Default. Highest quality, 4K support, best text rendering (Nano Banana 2, launched Feb 2026) |
gemini-2.5-flash-image-preview | Fast generation, 1K resolution, good quality (Nano Banana) |
gemini-3-pro-image-preview | Previous-gen Pro model, still high quality (Nano Banana Pro) |
gemini-2.0-flash-exp | Older experimental model; prefer gemini-2.5-flash-image-preview for new work |
Image Size (Gemini 3.1 / 3 only)
| Size | Use Case |
4K | Final assets, print, marketing materials |
2K | Balanced quality and speed |
1K | Fast iteration, prototyping |
Advanced Features
| Feature | Capability |
| 4K Output | Up to 5632×3072 pixels |
| Text Rendering | Accurate text in images (signs, labels, UI) |
| Multi-Image Composition | Combine up to 14 reference images |
| Character Consistency | Maintain same character across 5+ images |
| Google Search Grounding | Real-world accurate imagery |
Prompting Best Practices
Structure Your Prompts
[Subject] + [Style] + [Details] + [Technical Specs]Example:
"A cozy coffee shop interior, watercolor illustration style, warm lighting, wooden furniture, steaming cup on table, 4K resolution, soft morning light through windows"
For Best Results
- Be Specific - Include colors, materials, lighting, mood
- Specify Style - "photorealistic", "oil painting", "3D render", "anime"
- Add Context - Time of day, weather, setting
- Request Resolution - "4K", "high resolution", "detailed"
Precision Mode (JSON Prompting)
For high-stakes work requiring exact reproducibility, use structured JSON schemas.
When to Activate
Trigger phrases:
- "I need exact control over..."
- "Create a product shot for [brand]..."
- "Generate a UI mockup..."
- "Make an infographic showing..."
- "I want to iterate on just the lighting..."
- "A/B test different versions..."
Three Schema Types
| Type | Use Case | Key Controls |
marketing_image | Product shots, hero images | subject, props, lighting, camera, brand locks |
ui_builder | App screens, dashboards | tokens, screens, containers, components |
diagram_spec | Flowcharts, infographics | nodes, edges, data constraints |
The Translator Workflow
- Describe - User explains what they want in plain English
- Clarify - Claude asks targeted questions for missing fields
- Generate - Claude outputs structured JSON schema
- Review - User checks key fields match intent
- Render - JSON converts to precise prompt for Nano Banana 2
- Iterate - Modify specific fields, re-render (scoped changes)
Example: Product Shot
User: "I need a hero shot for Aurora Lime seltzer"
Claude asks: "For the Aurora Lime hero shot:
- Can size? (12oz standard?)
- Props? (lime slices, ice, condensation?)
- Background style? (solid color, gradient, bokeh?)
- Lighting mood? (bright/refreshing or moody/premium?)"
Result: Structured JSON with exact specifications that can be iterated field-by-field.
Scoped Edits (The Key Unlock)
JSON enables changing ONE thing without regenerating everything:
| Change | What Stays Fixed |
| Swap lighting direction | Subject, props, background |
| Try different camera angle | Lighting, props, environment |
| Change background color | Subject geometry, lighting setup |
| Add/remove props | Everything else |
Reference Docs
references/json-prompting.md- Full JSON prompting guidereferences/translator-prompt.md- Translator system promptreferences/schemas/- Template schemas for each typereferences/examples-json.md- Filled-out examples
Text in Images
Nano Banana 2 excels at text rendering:
"A vintage movie poster for 'COSMIC ADVENTURE' with bold retro typography, starfield background, astronaut silhouette, 1970s sci-fi aesthetic"
Character Consistency
For consistent characters across images:
- Generate initial character with detailed description
- Use
history:0reference in subsequent prompts - Describe scene changes while referencing original
First: "A young woman with red curly hair, freckles, green eyes, wearing a blue jacket"
Then: "The same woman from history:0, now sitting at a café, reading a book"Workflow Examples
Basic Image Generation
User: "Create an image of a futuristic city at sunset"
Claude uses: gemini_generate_image
Prompt: "Futuristic cityscape at golden hour sunset, towering glass skyscrapers with holographic advertisements, flying vehicles, warm orange and purple sky, photorealistic, 4K resolution, cinematic lighting"Photo Editing
User: "Edit this photo to make it look like winter"
Claude uses: gemini_edit_image
Input: [user's image path]
Instructions: "Transform to winter scene: add snow on ground and surfaces, frost on windows, visible breath, overcast sky, cool blue color grading"Iterative Refinement
User: "Make the lighting warmer"
Claude uses: continue_editing
Instructions: "Adjust lighting to warmer tones, add golden hour glow, enhance orange/yellow highlights, softer shadows"Output Management
Images save to: ~/Documents/nanobanana_generated/
Naming format: generated-[timestamp]-[id].png
Security Notes
- API keys stored locally in environment variables
- Never committed to version control
- Images processed locally, not stored on external servers
- Use
.envfiles for key management in projects
Model Comparison
| Model | Speed | Quality | Max Res | Cost | Best For |
gemini-3.1-flash-image-preview | Fast | Highest | 4K | ~$0.045/img (1K) | Final assets, print, marketing |
gemini-2.5-flash-image-preview | Fastest | Good | 1K | ~$0.039/img | Prototyping, iteration, drafts |
gemini-3-pro-image-preview | Slower | High | 4K | ~$0.134/img | Previous-gen Pro fallback |
gemini-2.0-flash-exp | Fast | Good | 1K | Low | Legacy; use 2.5-flash-image-preview instead |
Pricing as of March 2026. Free tier (~500 req/day) available via Google AI Studio for all models.
Troubleshooting
| Issue | Solution |
| "API key invalid" | Verify key at AI Studio |
| "Rate limited" | Wait 60s, or upgrade API tier |
| "MCP not connected" | Restart Claude Code, check config syntax |
| "Image not saving" | Check write permissions on output directory |
Integration
Works well with:
- Artifacts Builder - Generate images for HTML artifacts
- Process Mapper - Create diagram visuals
- Research to Essay - Add illustrations to content
References
references/prompting-guide.md- Detailed prompting techniquesreferences/examples.md- Sample prompts by category
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

