The Agent Skills Directory

[SAFE]: The skill implements security best practices by using the allowed-tools frontmatter field to restrict the agent's execution environment to only the belt CLI.
[SAFE]: All external resource references, including the transcription API at inference.sh and the documentation hosted on GitHub, originate from the official domains and repositories of the skill's author.
[SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscated code were identified. The shell commands provided in the examples are limited to the intended functionality of audio processing.

elevenlabs-stt