The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the belt-sh/cli package via npx and the inferencesh Python package via pip. These are the official tools for the inference.sh service described in the skill.
[COMMAND_EXECUTION]: The skill uses the belt CLI tool (restricted via allowed-tools to the belt command only) to perform text-to-speech operations, manage sessions, and interact with the ElevenLabs API.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for audio generation, which represents a surface for indirect prompt injection where instructions could be hidden in processed data.
Ingestion points: The text parameter in the input JSON objects in SKILL.md.
Boundary markers: The documentation uses standard JSON structures and shell-quoted strings to encapsulate user input.
Capability inventory: The skill is limited to shell execution of the belt command and network operations to the inference.sh API.
Sanitization: The skill assumes the underlying API handles sanitization of text inputs for the speech synthesis process.

elevenlabs-tts