The Agent Skills Directory

[SAFE]: The skill uses the allowed-tools configuration to restrict the agent's Bash tool usage to only commands starting with belt, which is a security best practice for limiting scope.
[EXTERNAL_DOWNLOADS]: The skill references installation instructions and assets from inference.sh and their official GitHub repository. These are legitimate resources owned by the skill's vendor.
[COMMAND_EXECUTION]: The skill instructs the agent to execute belt commands to interact with voice generation models. These commands are constrained by the allowed-tools field and are used according to the skill's primary purpose.

ai-voice-cloning