Muapi Nano Banana

If you're working with AI image generation and tired of keyword soup prompts that produce inconsistent results, this takes a more structured approach. Built around what the author calls "reasoning-driven" prompting (inspired by Gemini 3's architecture), it pushes you to think in terms of Subject + Action + Context + Composition + Lighting rather than throwing adjectives at a wall. The focus on explicit text rendering instructions is smart, since that's where most models still struggle. It's opinionated about how to write creative briefs, which means there's a learning curve, but if you're generating images programmatically or need repeatable quality, that structure pays off. Over 500 installs suggests people are finding the formula useful.

skills.sh installs: 2.2K
GitHub stars: 4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add samuraigpt/generative-media-skills --skill muapi-nano-banana --agent claude-code

Installs into .claude/skills of the current project.

Files

🍌 Nano-Banana Expert Skill (Gemini 3 Style)

A specialized skill for AI Agents to leverage "Reasoning-Driven" image generation. Based on the advanced prompting architecture of Google's Gemini 3 (Nano Banana Pro), this skill moves beyond keyword stuffing to structured, logic-based creative briefs.

Core Competencies

Reasoning-Driven Prompting: Using natural language logic to define physics, lighting, and spatial relationships.
Structured Creative Briefs: Implementing the "Perfect Prompt" formula: Subject + Action + Context + Composition + Lighting.
Text Rendering Precision: Explicitly defining typography and signifiers for legible text integration.
Contextual Grounding: Using "Search Grounding" logic (simulated) to anchor generations in real-world accuracy.