A multimodal toolset for AI agents to generate, edit, and display images, videos, and audio via CLI.
Generative Media Skills is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add SamurAIGPT/Generative-Media-SkillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This repository provides ready-to-use skills for AI agents like Claude Code and Cursor. It lets agents generate images, videos, and audio using simple commands. The skills are powered by muapi.ai and include many AI models like Midjourney and Kling.
Generative Media Skills is a comprehensive, schema-driven toolkit designed for AI agents (Claude Code, Cursor, Gemini CLI) to create professional-grade multimedia content. It features a core/library architecture: core primitives handle file uploads, image editing, and platform setup, while the expert library provides domain-specific skills like cinema direction, UI design, and logo creation. The toolkit supports over 100 AI models including Midjourney v7, Flux Kontext, Seedance 2.0, Kling 3.0, and Veo3. It includes 41 ready-to-run workflow recipes for end-to-end pipelines, an MCP server exposing 19 tools, and direct media display via the --view flag. All operations are CLI-based, delegating to muapi-cli for structured JSON outputs and semantic exit codes, making it ideal for agentic pipelines.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 5 days ago.
3433 GitHub stars indicate community interest.
1 open issues signal maintenance load.
MIT license detected.
Generate high-quality images from text prompts for marketing materials
Create cinematic videos with text-to-video and image-to-video capabilities
Edit images using natural language instructions
Produce AI-generated music and audio clips
Automate social media content creation (e.g., YouTube Shorts, TikTok)
API keys and credentials must be kept secure; avoid hardcoding in scripts.
Generated content may have licensing restrictions; verify model terms.
Local file uploads to CDN may expose sensitive data; use caution.
3,433
Stars
391
Forks
1
Issues
MIT
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Production-grade engineering skills for AI coding agents.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
3 security/trust notes recorded.
Setup difficulty is 2/5.