Muapi Nano Banana
Turn a short subject-and-scene brief into a reasoning-driven photorealistic image prompt and run the bundled Nano-Banana shell generator for marketing and product visuals.
Overview
muapi-nano-banana is an agent skill most often used in Build (also Launch, Grow) that assembles a reasoning-driven Nano-Banana image prompt and runs a bash generator from subject, scene, style, and resolution flags.
Install
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-nano-bananaWhat is this skill?
- Reasoning-brief prompt formula: subject + action + context + lighting + style + optional sign text
- CLI flags: --subject, --action, --context, --style, --lighting, --resolution 1k|2k|4k, --text, --view
- Optional typography clause when --text is set (bold readable sign copy)
- Cinematic default style with natural lighting; photorealistic execute step in the brief
- Bash entrypoint generate-nano-art.sh with usage guard when subject is missing
- 7 CLI dimensions (subject, action, context, style, lighting, resolution, text) plus optional --view
Adoption & trust: 681 installs on skills.sh; 3.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know what scene you want but keep getting inconsistent or vague image results from one-line chat prompts.
Who is it for?
Solo builders shipping landing pages, indie SaaS marketing, or content calendars who want structured CLI-driven image briefs.
Skip if: Teams that need vector brand kits, automated multi-size asset pipelines, or video generation without shell access.
When should I use this skill?
You need a reasoning-driven photorealistic image brief from structured flags rather than a freeform one-liner.
What do I get? / Deliverables
You get a repeatable expert prompt and script invocation so your agent can generate photorealistic visuals with explicit composition, lighting, and optional sign text.
- Structured reasoning-brief prompt string
- Executed bash generation invocation
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because solo builders most often invoke this while producing UI, landing, and promo imagery alongside the product. Frontend is the default bucket for visual assets that ship in interfaces, ads, and store creatives rather than backend logic.
Where it fits
Generate a hero illustration of your app concept with cinematic lighting before polishing the landing layout.
Produce consistent promo stills for Product Hunt or social posts using the same subject-action-context template.
Batch blog or newsletter header art with optional --text signage for campaign copy.
How it compares
Use as a prompt-and-shell generator skill, not as an MCP media server or a Figma replacement.
Common Questions / FAQ
Who is muapi-nano-banana for?
Indie and solo builders using Claude Code, Cursor, or Codex who want photorealistic images from a fixed subject-action-context formula without writing prompts from scratch each time.
When should I use muapi-nano-banana?
During Build for UI and mock imagery, at Launch for distribution creatives and store art, and in Grow when you need fresh content visuals—any time you have a clear subject and scene but need consistent reasoning-brief output.
Is muapi-nano-banana safe to install?
Review the Security Audits panel on this Prism page and inspect the bash script in your repo before running it; the skill executes shell and may call external image APIs you wire in.
SKILL.md
READMESKILL.md - Muapi Nano Banana
#!/bin/bash # Expert Skill: Nano-Banana (Gemini 3 Style) # Implements the "Perfect Prompt" reasoning-driven formula. SUBJECT="" ACTION="" CONTEXT="" STYLE="cinematic" LIGHTING="natural" RESOLUTION="1k" TEXT="" VIEW_FLAG="" while [[ $# -gt 0 ]]; do case $1 in --subject) SUBJECT="$2"; shift 2 ;; --action) ACTION="$2"; shift 2 ;; --context) CONTEXT="$2"; shift 2 ;; --style) STYLE="$2"; shift 2 ;; --lighting) LIGHTING="$2"; shift 2 ;; --resolution) RESOLUTION="$2"; shift 2 ;; --text) TEXT="$2"; shift 2 ;; --view) VIEW_FLAG="--view"; shift ;; *) shift ;; esac done if [ -z "$SUBJECT" ]; then echo "Usage: bash generate-nano-art.sh --subject 'robot' [--action 'pouring coffee'] [--context 'cafe'] [--style 'photorealistic'] [--resolution 1k|2k|4k] [--text 'CAFE'] [--view]" exit 1 fi # Text Logic TEXT_PROMPT="" if [ -n "$TEXT" ]; then TEXT_PROMPT="featuring a sign that clearly reads \"$TEXT\" in bold typography" fi # Nano-Banana Reasoning-Driven Prompt # Formula: Subject + Action + Context + Lighting + Style + Text EXPERT_PROMPT="[REASONING_BRIEF] SUBJECT: A highly detailed $SUBJECT. ACTION: The subject is $ACTION. ENVIRONMENT: Situated in $CONTEXT. LIGHTING: Illuminated by $LIGHTING lighting. STYLE: Use a $STYLE aesthetic. High fidelity, physically accurate reflections and textures. EXTRA: $TEXT_PROMPT. [EXECUTE] Generate a photorealistic image based on this logic. Ensure precise composition and lighting interactions." # Call Core Primitive SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" CORE_SCRIPT="$SCRIPT_DIR/../../../../core/media/generate-image.sh" bash "$CORE_SCRIPT" --prompt "$EXPERT_PROMPT" --model "nano-banana-pro" --resolution "$RESOLUTION" $VIEW_FLAG --json --- name: muapi-nano-banana version: 0.1.0 description: Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting --- # 🍌 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 1. **Reasoning-Driven Prompting**: Using natural language logic to define physics, lighting, and spatial relationships. 2. **Structured Creative Briefs**: Implementing the "Perfect Prompt" formula: `Subject + Action + Context + Composition + Lighting`. 3. **Text Rendering Precision**: Explicitly defining typography and signifiers for legible text integration. 4. **Contextual Grounding**: Using "Search Grounding" logic (simulated) to anchor generations in real-world accuracy. --- ## 🏗️ Technical Specification ### 1. The "Perfect Prompt" Formula | Component | Description | Example | | :--- | :--- | :--- | | **Subject** | Detailed entity description | "A stoic robot barista with exposed copper wiring" | | **Action** | Dynamic interaction | "Pouring a latte art leaf with mechanical precision" | | **Context** | Environment & Atmosphere | "Inside a neon-lit cyberpunk cafe at midnight" | | **Composition** | Camera & Lens choice | "Close-up, 85mm lens, f/1.8 aperture" | | **Lighting** | Mood & Direction | "Volumetric blue rim light, warm cafe glow" | | **Style** | Aesthetic anchor | "Cinematic, photorealistic, 4K production value" | ### 2. Advanced Features - **Negative Constraint Logic**: Instead of "no blurry," use "Ensure sharp focus on the subject's eyes." - **Identity Consistency**: (Simulated) "Maintain consistent facial structure across variations." - **Text Integration**: Use double quotes for specific text: `The sign reads "OPEN 24/7"`. --- ## 🧠 Prompt Optimization Protocol (Agent Instruction) **Before calling the script, the Agent MUST rewrite the user's prompt into a logic-driven Reasoning Brief:** 1. **NO KEY