Generative Media Skills — 41+ agent recipes for images, video, and audio
A high-performance, schema-driven collection of 41 AI agent recipes for generating, editing, and displaying professional-grade images, videos, and audio. Powered by muapi-cli with 100+ models including Midjourney, Flux, Seedance, Kling, and Veo.
Prompt template
You are a generative media director. Given the user's creative intent, select the right recipe from the library and execute it via muapi-cli calls. First identify the output type (image, video, audio, or multi-step pipeline), then choose the matching recipe, declare its inputs, and execute step by step. For video: specify duration, aspect ratio, motion style, and camera movement. For images: specify style, composition, color palette, and subject. Always return the generated media file path plus the final prompt used.
How to use
- 1Identify the desired output type and creative intent from the user request
- 2Select the matching recipe from the library (motion, social, visual, or core primitive)
- 3Declare the recipe inputs and parameters explicitly
- 4Execute via muapi-cli calls, polling for results
- 5Inspect the output for quality and completeness
- 6Return the media file, final prompt, and recipe summary
Pro tips
- Use the Cinema Director skill for technical film direction and cinematography
- Nano-Banana is best for reasoning-driven image generation (Gemini 3 style)
- Seedance 2 handles text-to-video, image-to-video, and video extension with native audio sync
- AI Clipping turns long videos into ranked vertical shorts with server-side transcription
- 41 recipes cover motion (16), social (5), and visual/design (21) workflows
- Install muapi-cli once: npm install -g muapi-cli, then muapi auth configure
Use cases
Examples
Input:
Input:
Input:
Input:
Input:
Not this
- Not a standalone app — requires an AI agent (Claude Code, Cursor, Codex) to execute
- Not free — muapi API key required with pay-as-you-go pricing
- Not a video editor — it generates new media, it does not edit existing timelines
- Not for text-only tasks — focused on image, video, and audio generation
Works best with
Ratings & Reviews
Loading reviews…
Related Skills
Midjourney Character Consistency with --cref
Keep the same character across many images using Midjourney's character reference parameter.
Punk Cover — generate article cover images from 32 curated visual styles
Turn articles, notes, tweets, and topic drafts into polished cover images for Xiaohongshu, WeChat public accounts, X/Twitter, and more. Selects exactly one reusable style from a shared library of 32 curated visual styles — including minimalist black-and-white, retro torn collage, pixel art metaphor, industrial OSB blueprint, business magazine front page, avant-garde geometry, layered paper-cut concept, and more — then fuses the style atom into a complete cover-specific prompt. Supports custom aspect ratios, multi-size suites, and prompt-only output mode.
Punk Avatar — generate profile pictures, pet portraits, and surreal paper-art from 8 styles
Generate avatar images from photos or text descriptions for people, pets, and objects. Choose from 8 curated styles including pixel avatar, grotesque soul sketch, messy crayon pet portrait, fashion sketch observation, polaroid keepsake card, minimal paper acrylic block illustration, and surreal pop-up paper landscape. Preserves recognizable subject traits while translating them into the selected style. Default 1:1 ratio with custom ratio support.