Image prompting

Skill DojoCodingLabs/nanobanana-mcp/skills/image-prompting

Best practices for AI image generation prompts with Gemini models. Activated when the user works with nanobanana image generation or editing tools. Provides guidance on prompt structure, style keywords, and iterative refinement.From its SKILL.md

Install

npx -y skills add DojoCodingLabs/nanobanana-mcp --skill image-prompting

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, as published. Nobody here has run it

Image Prompting Best Practices

When helping users generate or edit images with nanobanana, apply these guidelines.

Prompt Structure for Generation

A strong image prompt follows this pattern: [Subject] + [Style] + [Composition] + [Lighting/Mood] + [Details]

Example: "A cozy coffee shop interior, watercolor illustration style, wide angle view, warm golden lighting, with plants on shelves and a cat sleeping on a chair"

Model Selection Guide

nanobanana supports three Gemini models via the NANOBANANA_MODEL env var:

Model	Best For
`gemini-2.5-flash-image` (default)	Fast generation, prototyping, high-volume work
`gemini-3-pro-image-preview`	Complex prompts, text rendering in images, high quality
`gemini-3.1-flash-image-preview`	Latest features, advanced capabilities

Recommend model changes when appropriate:

User needs text in the image -> suggest Pro
User is iterating rapidly -> stick with Flash (default)
User wants highest quality for final output -> suggest Pro

Editing Best Practices

When using edit_image or continue_editing:

Be specific about what to change: "Make the sky more orange" not "improve the colors"
Reference specific areas: "Add a tree in the bottom-left corner"
For style transfer, use reference images via the referenceImages parameter
Each edit creates a new file -- the original is always preserved

Constraints

Prompts over 10,000 characters will be rejected
Image files must be under 20MB
Supported input formats: JPEG, PNG, WebP, GIF
Output is always PNG
File paths must resolve within $HOME or $TMPDIR (security constraint)
Images are saved to ~/nanobanana-images/

Iterative Workflow

The most effective image workflow is:

Generate a base image with a detailed prompt
Use continue_editing for incremental refinements
Each iteration should address ONE specific change
If the result diverges too far, start fresh with generate_image