Generative Media Skills
A set of skills for agents to generate and edit images, video and audio through the muapi.ai service and muapi-cli
- 7,053 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Runs shell scripts that call an external paid API
- Uses a secret muapi.ai key
- Generation spends paid account credits
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/generative-media-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs shell scripts that call an external paid API
- Uses a secret muapi.ai key
- Generation spends paid account credits
This is third-party code. Review the repository files before installing.
What it does
The set gives an agent shell-script skills for generating and editing images, video and audio. It splits into core primitives, namely generation, editing, file upload and result polling, and an expert library of task skills: ad creatives, product videos, thumbnails, logos, cinema-style clips, music and more. All scripts call muapi-cli, which reaches muapi.ai and returns structured JSON with exit codes and a --jq filter for agentic pipelines. Separately, an MCP server starts with muapi mcp serve, exposing 19 typed tools for Claude Desktop, Cursor and other MCP clients. A paid muapi.ai key is required. It works with Claude Code, Cursor, Gemini CLI and OpenCode.
Who it is for. For designers, marketers and content creators who need media generation directly from the agent.
Good fit when
- You need to generate or edit an image, video or music from the agent
- You need to build an ad clip, thumbnail or UGC video from a ready skill
- You need to embed media generation into a pipeline that parses JSON
Not a fit when
- You have no paid muapi.ai key
- You need local generation without calling an external service
Example request
Make a 10-second product ad video from this photo and show the resultLimitations
A paid muapi.ai key is required in the MUAPI_API_KEY variable, and generation spends account credits. The scripts need muapi-cli, installed via npm or pip. Availability of muapi.ai from Russia without a VPN is not confirmed, so check it separately. The key lives in the CLI config or an environment variable.
How to disable. Delete the skill folders from the agent's directory or remove the plugin. Optionally remove the CLI with npm uninstall -g muapi-cli.
FAQ
Do I need a paid account?
Yes, a muapi.ai key is required, and generation spends account credits.
Can I use it over MCP?
Yes. The muapi mcp serve command starts an MCP server with typed tools for Claude Desktop, Cursor and other MCP clients.
Discussion
No questions or reviews yet.
Related
SkillsA skill and CLI for image and video generation through Gemini, OpenAI and Kie AI, with provider choice and AI-content marking
A CLI for fal.ai: an agent searches, runs and downloads results from 1200+ image, video and audio models with shell commands.
The media-pipeline plugin generates images through Gemini or OpenAI gpt-image-2: a skill, CLI and MCP server install in one step.
An MCP server for generating images and video from the agent: several models, a large prompt library and parallel tasks
The official SpicyAPI skill: an agent runs image, video and audio generation tasks through the MCP server, CLI or SDK
Clipmivo Video
clipmivo-video
A skill for ClipmivoAI: the agent quotes a video task in credits, starts generation, follows it and downloads the result.
README in short
The README describes a set of skills for image, video and audio generation in agents, built around muapi-cli and the muapi.ai service. The skills split into core primitives and a library of expert scenarios for ads, product videos, thumbnails and other tasks, and every script returns structured JSON for pipelines. The quick start covers installing the CLI, configuring the key, and installing skills with npx skills add. A separate section shows how to run the MCP server with 19 tools and the config for Claude Desktop. MIT licensed.
README badge
Original SKILL.md
--- name: muapi-media-generation version: 0.1.0 description: Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5 --- # MuAPI Media Generation **Schema-driven generation primitives for images, videos, and audio.** Generate professional-grade media directly from the terminal using 100+ state-of-the-art AI models. All scripts are powered by schema_data.json for dynamic model and endpoint resolution. ## Available Scripts | Script | Description | Default Model | | :--- | :--- | :--- | | generate-image.sh | Text-to-image generation | flux-dev | | generate-video.sh | Text-to-video generation | minimax-pro | | image-to-video.sh | Animate a static image into video | kling-pro | | create-music.sh | Music creation, remix, extend, text/video-to-audio | Suno V5 | | upload.sh | Upload local files to CDN for use with other skills | ## Quick Start ```bash bash generate-image.sh --prompt "a sunset over mountains" --model flux-dev --view bash generate-video.sh --prompt "ocean waves at golden hour" --model minimax-pro --view bash create-music.sh --style "lo-fi hip hop" --prompt "chill beats for studying" ```