🎭 Generative Media Skills for AI Agents

The Ultimate Multimodal Toolset for Claude Code, Cursor, Gemini CLI, and OpenCode. A high-performance, schema-driven architecture for AI agents to generate, edit, and display professional-grade images, videos, and audio — powered by the muapi-cli.

🚀 Get Started | 🎬 Recipe Pack | 🎨 Expert Library | ⚙️ Core Primitives | 🤖 MCP Server | 📖 Reference

Related Projects

• minimax-music-3-api — Python SDK for MiniMax Music 3.0 text-to-music generation on Muapi.
• awesome-minimax-music-3-prompts — Curated song prompts and lyrics-formatting guide for MiniMax Music 3.0.
• MiniMax-H3-API — Python SDK for MiniMax H3 video-generation workflows on Muapi.
• awesome-minimax-h3-prompts — Prompt gallery and runnable examples for the MiniMax H3 skills.
• Wan-3.0-API — Python SDK and MCP server for Wan 3.0-compatible video-generation workflows.
• Open-Generative-AI — Free self-hosted AI media studio — GUI alternative to these skills for the same model set
• Awesome-GPT-Image-2-API-Prompts — Curated GPT-Image-2 prompts to use with these skills
• Awesome-Gemini-Omni-API-Prompts — Curated Gemini Omni prompts for video generation
• AI-Voice-Agent — Self-hosted AI voice agent for real-time voice conversations, sales calls, and customer support
• awesome-ai-image-models — compare AI image models by API, price & quality
• flux-3-video-api — Python wrapper focused on FLUX 3 Text-to-Video and Image-to-Video
• ai-creator-academy — free curriculum teaching creators to monetize generative AI, built on these same skills
• Flux-3-Dev-API — Python wrapper for Black Forest Labs' FLUX 3 (Dev variant) — text-to-image, image-to-image, text-to-video, image-to-video
• Grok-Imagine-Image-2-API — Python SDK and MCP server for Grok Imagine Image 2.0 generation and editing through MuAPI
• midjourney-api — Python SDK for Midjourney V7, V8, and Niji image generation through MuAPI
• suno-api — Python SDK for Suno music, audio, and voice workflows through MuAPI
• awesome-flux-3-api-prompts — FLUX 3 API guide, prompts, and parameters
• seedance-2.5-mcp — MCP server for generating Seedance 2.5 Preview videos through MuAPI.
• seedance-2-mcp — MCP server for generating Seedance 2 videos through MuAPI.
• Text-to-Speech-API — narration and dialogue API examples for media workflows.
• Speech-to-Text-API — transcription and audio-understanding API examples.
• Voice-Cloning-API — consent-aware speaking and singing voice workflows.
• Image-Enhancement-API — image enhancement examples for creative pipelines.
• Video-Utilities-API — video upscaling and sound-generation utility examples.
• AI-3D-Model-API — 3D asset generation comparison and examples.

✨ Key Features

• 🤖 Agent-Native Design — CLI-powered scripts with structured JSON outputs, semantic exit codes, and --jq filtering for seamless agentic pipelines.
• 🧠 Expert Knowledge Layer — Domain-specific skills that bake in professional cinematography, atomic design, and branding logic.
• ⚡ CLI-Powered Core — All primitives delegate to muapi-cli — no curl, no JSON parsing, no boilerplate.
• 🖼️ Direct Media Display — Use the --view flag to automatically download and open generated media in your system viewer.
• 📁 Local File Support — Auto-upload images, videos, faces, and audio from your local machine to the CDN for processing.
• 🌈 100+ AI Models — One-click access to Midjourney v7, Flux Kontext, Seedance 2.0, Kling 3.0, Veo3, and more.
• 🔌 MCP Server — Run muapi mcp serve to expose all 19 tools directly to Claude Desktop, Cursor, or any MCP-compatible agent.

🏗️ Scalable Architecture

This repository uses a Core/Library split to ensure efficiency and high-signal discovery for LLMs:

⚙️ Core Primitives (/core)

Thin wrappers around muapi-cli for raw API access.

• core/media/ — File upload
• core/edit/ — Image editing (prompt-based)
• core/platform/ — Setup, auth & result polling

📚 Expert Library (/library)

High-value skills that translate creative intent into technical directives.

• Cinema Director (/library/motion/cinema-director/) — Technical film direction & cinematography.
• Nano-Banana (/library/visual/nano-banana/) — Reasoning-driven image generation (Gemini 3 Style).
• UI Designer (/library/visual/ui-design/) — High-fidelity mobile/web mockups (Atomic Design).
• Logo Creator (/library/visual/logo-creator/) — Minimalist vector branding (Geometric Primitives).
• Seedance 2 (Doubao Video) (/library/motion/seedance-2/) — Director-level cinematic video generation with text-to-video, image-to-video, and video extension with native audio-video sync.
• AI Clipping (/library/edit/ai-clipping/) — Long video → ranked vertical short clips in one managed API call. Server-side transcription, virality ranking, dedupe, and face-tracked auto-crop — no local Whisper or LLM.
• YouTube Shorts (/library/social/youtube-shorts/) — Platform-aware preset over AI Clipping (Shorts / TikTok / Reels / Feed defaults).

Plus 41 ready-to-run workflow recipes organized by output type — see 🎬 Recipe Pack below.

🎬 Recipe Pack

Forty-one LLM-orchestrated workflow recipes that combine multiple muapi-cli calls into named end-to-end pipelines (e.g. photo of person → 3D action figure, product photo → cinematic 10s ad). Each skill is a SKILL.md the agent reads and follows; bring your own consuming agent (Claude Code, Cursor, MCP) — these are recipes, not bash wrappers.

Motion / Video (16)

Social (5)

Visual / Images & Design (21)

Each recipe declares its inputs and a Steps body. Pass the inputs and let your agent execute the steps via muapi CLI calls (or raw API for endpoints that don't yet have a CLI alias — see the per-skill Notes for the Executing Agent footer).

🚀 Quick Start

1. Install the muapi CLI

The core scripts require muapi-cli. Install it once:

# via npm (recommended — no Python required)
npm install -g muapi-cli

# via pip
pip install muapi-cli

# or run without installing
npx muapi-cli --help

2. Configure Your API Key

# Interactive setup
muapi auth configure

# Or pass directly
muapi auth configure --api-key "YOUR_MUAPI_KEY"

# Get your key at https://muapi.ai/dashboard?utm_source=github&utm_medium=readme&utm_campaign=generative-media-skills

3. Install the Skills

# Install all skills to your AI agent
npx skills add SamurAIGPT/Generative-Media-Skills --all

# Or install a specific skill
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-media-generation

# Install to specific agents
npx skills add SamurAIGPT/Generative-Media-Skills --all -a claude-code -a cursor

4. Generate Your First Image

muapi image generate "a cyberpunk city at night" --model flux-dev

# Download the result automatically
muapi image generate "a sunset over mountains" --model hidream-fast --download ./outputs

# Extract just the URL (agent-friendly)
muapi image generate "product on white bg" --model flux-schnell --output-json --jq '.outputs[0]'

5. Run an Expert Skill

# Use Nano-Banana reasoning to generate a 2K masterpiece
bash library/visual/nano-banana/scripts/generate-nano-art.sh \
  --file ./my-source-image.jpg \
  --subject "a glass hummingbird" \
  --style "macro photography" \
  --resolution "2k" \
  --view

6. Direct a Cinematic Scene

cd library/motion/cinema-director

# Create a 10-second epic reveal
bash scripts/generate-film.sh \
  --subject "a cybernetic dragon over Tokyo" \
  --intent "epic" \
  --model "kling-v3.0-pro" \
  --duration 10 \
  --view

# Animate a reference image into video
bash library/motion/seedance-2/scripts/generate-seedance.sh \
  --mode i2v \
  --file ./concept.jpg \
  --subject "camera slowly pulls back to reveal the full landscape" \
  --intent "reveal" \
  --view

# Extend an existing video
bash library/motion/seedance-2/scripts/generate-seedance.sh \
  --mode extend \
  --request-id "YOUR_REQUEST_ID" \
  --subject "camera continues pulling back to reveal the vast city" \
  --duration 10

OpenCode

# Clone the repo and set the MUAPI_API_KEY env var
git clone https://github.com/SamurAIGPT/Generative-Media-Skills
export MUAPI_API_KEY=your_key_here

# Skills auto-load from .opencode/skills/ when you run opencode in this directory
opencode

🤖 MCP Server

Run muapi as a Model Context Protocol server so Claude Desktop, Cursor, or any MCP-compatible agent can call generation tools directly — no shell scripts needed.

muapi mcp serve

Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "muapi": {
      "command": "muapi",
      "args": ["mcp", "serve"],
      "env": { "MUAPI_API_KEY": "your-key-here" }
    }
  }
}

This exposes 19 structured tools with full JSON Schema input/output definitions:

⚡ Agentic Pipeline Examples

# Submit async, capture request_id, poll when ready
REQUEST_ID=$(muapi video generate "a dog running on a beach" \
  --model kling-master --no-wait --output-json --jq '.request_id' | tr -d '"')

# ... do other work ...

muapi predict wait "$REQUEST_ID" --download ./outputs

# Pipe a prompt from another command
generate_prompt | muapi image generate - --model flux-dev

# Chain: upload → edit → download
URL=$(muapi upload file ./photo.jpg --output-json --jq '.url' | tr -d '"')
muapi image edit "make it look like a painting" --image "$URL" \
  --model flux-kontext-pro --download ./outputs

📖 Schema Reference

This repository includes a streamlined schema_data.json that core scripts use at runtime to:

• Validate Model IDs: Ensures the requested model exists.
• Resolve Endpoints: Automatically maps model names to API endpoints.
• Check Parameters: Validates supported aspect_ratio, resolution, and duration values.

Discover all available models via the CLI:

muapi models list
muapi models list --category video --output-json

🔧 Compatibility

Optimized for the next generation of AI development environments:

• Claude Code — Direct terminal execution via tools + MCP server mode.
• Gemini CLI / Cursor / Windsurf — Seamless integration as local scripts.
• MCP — Full Model Context Protocol server with typed input/output schemas.
• CI/CD — --output-json, --jq, semantic exit codes for scripting.

📄 License

MIT © 2026