The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The Python scripts (generate_audio_edge.py, generate_audio_minimax.py, and generate_audio_qwen.py) use subprocess.run to call ffprobe and ffmpeg. These calls are used to extract audio duration and convert audio formats, which are standard operations for a video/audio generation skill.
[CREDENTIALS_UNSAFE] (SAFE): The generate_audio_minimax.py script retrieves sensitive API keys from environment variables (MINIMAX_API_KEY) rather than hardcoding them in the source code, adhering to security best practices.
[DYNAMIC_EXECUTION] (LOW): The scripts programmatically generate and overwrite the src/audioConfig.ts file. This is used to synchronize the generated audio metadata with the React-based Remotion framework. While this is a form of code generation, it is restricted to a configuration file and is a core intended functionality of the skill.

remotion-video