muapi-nano-banana

muapi-nano-banana is a skill for OpenCode from SamurAIGPT/Generative-Media-Skills. It costs 37 tokens per session (900 once invoked), scanned A, original, MIT.

A method for guiding an image generator with a structured brief covering the subject, action, setting, composition, lighting, and visible text.

In plain words
What is it for?
Use it to prepare prompts for realistic scenes, controlled layouts, lighting, spatial relationships, and readable signs or typography.
Why use it?
It replaces scattered prompt keywords with a clear description of how the image should look and how its parts relate.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/generate-nano-art.sh \.

not rated 4.3krepo +40 3d ago A scan Socket: passSnyk: passSkillSpector: pass 37 tokens original MIT

Good fit Use it to prepare prompts for realistic scenes, controlled layouts, lighting, spatial relationships, and readable signs or typography.

Compare 6 skills from other repositories ↓
About the project

Generative-Media-Skills is a toolkit that lets AI agents generate, edit, and display images, videos, and audio through the muapi command-line interface. It is for users of Claude Code, Cursor, Gemini CLI, and OpenCode who need multimodal media-generation workflows. The catalogue entries are the skills that expose these media capabilities to coding agents.

SamurAIGPT/Generative-Media-Skills · 4,263 stars · on GitHub · muapi.ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-Skills
agentmods
npx agentmods add skills/samuraigpt/generative-media-skills/muapi-nano-banana

Made for: OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for muapi-nano-banana

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/muapi-nano-banana/github.svg)](https://agentmods.dev/skills/samuraigpt/generative-media-skills/muapi-nano-banana)
Your own site
<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/muapi-nano-banana"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/muapi-nano-banana/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for muapi-nano-banana

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/muapi-nano-banana"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/muapi-nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 13 Mar 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00900
Opus 5 $0.00018 $0.00450
Sonnet 5 $0.00007 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 13d ago against content hash e26187b5a7c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

muapi-nano-banana scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.opencode/skills/muapi-nano-banana/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🍌 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 KEYWORD SOUP: Remove "8k, masterpiece, ultra-detailed." Use full, descriptive sentences.
  2. PHYSICAL CONSISTENCY: Describe how elements interact (e.g., "The light from the crystal shards casts caustic patterns across the obsidian floor").
  3. TEXT PRECISION: If the user wants text, define it precisely: featuring a sign that says "STORE NAME" in a weathered serif font.
  4. OPTICAL DIRECTIVES: Specify lens behavior: Shallow Depth of Field (f/1.8), Macro Lens, Anamorphic Flare.

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 81 lines · 37 tokens per session scan A e26187b5a7c6

Subscribe to this mod's changes

muapi-nano-banana is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (4,263 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 900 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mlops-automation

Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.

MLOps-Courses/mlops-coding-skills · 58 tokens

mlops-validation

Add the validation layers that gate a merge — ty typing, Ruff linting, pytest coverage, structured logging, and the trivy, pip-audit, and gitleaks scans. Use when hardening code quality or wiring the mise run check task.

MLOps-Courses/mlops-coding-skills · 55 tokens

mlops-prototyping

Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.

MLOps-Courses/mlops-coding-skills · 50 tokens

mlops-collaboration

Prepare a project for public collaboration — license, code of conduct, docs, branch rulesets, templates, and git-cliff releases. Use when open-sourcing a repository, onboarding contributors, or cutting a tagged release.

MLOps-Courses/mlops-coding-skills · 50 tokens

mlops-observability

Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.

MLOps-Courses/mlops-coding-skills · 51 tokens

mlops-industrialization

Convert notebook prototypes into a distributable Python package with a src layout, a domain/io/application split, and validated OmegaConf plus Pydantic configuration. Use when moving code out of notebooks or designing entrypoints.

MLOps-Courses/mlops-coding-skills · 48 tokens