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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SamurAIGPT/Generative-Media-Skills --skill nano-bananagit clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-SkillsWrote 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.
[](https://agentmods.dev/skills/samuraigpt/generative-media-skills/nano-banana)<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/nano-banana"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/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.
<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/nano-banana"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once 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 |
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 9d 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.
This is a copy
100% identical to muapi-nano-banana — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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
- 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.
🏗️ 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:
- NO KEYWORD SOUP: Remove "8k, masterpiece, ultra-detailed." Use full, descriptive sentences.
- PHYSICAL CONSISTENCY: Describe how elements interact (e.g., "The light from the crystal shards casts caustic patterns across the obsidian floor").
- TEXT PRECISION: If the user wants text, define it precisely:
featuring a sign that says "STORE NAME" in a weathered serif font. - OPTICAL DIRECTIVES: Specify lens behavior: Shallow Depth of Field (f/1.8), Macro Lens, Anamorphic Flare.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 81 lines · 37 tokens per session scan A e26187b5a7c6
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. It is 100% identical to muapi-nano-banana, differing in 0 lines, and is treated as a copy.
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-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-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-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-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-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.