The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run with list-based arguments to interact with system tools like ffmpeg, whisper, edge-tts, and piper. This implementation prevents shell injection and is a standard way to handle audio processing tasks.
[EXTERNAL_DOWNLOADS]: The skill recommends installing well-known, reputable packages such as openai-whisper, faster-whisper, and ffmpeg. It also utilizes the edge-tts tool which connects to cloud services for speech synthesis.
[SAFE]: The skill performs its intended audio processing functions using local file access and standard command-line tools without any suspicious behavior, obfuscation, or data exfiltration patterns.

audio-gen