The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external installation script for the belt CLI hosted on the author's official GitHub repository (inference-sh). This is a standard setup procedure for the vendor's toolset and originates from a resource associated with the author profile.
[COMMAND_EXECUTION]: The skill makes extensive use of the belt CLI via Bash to run various AI applications for image generation, text-to-speech, and social media posting. The frontmatter allowed-tools: Bash(belt *) provides a security boundary by restricting Bash execution to only the belt command.
[DATA_EXFILTRATION]: The skill includes instructions to post content to external platforms like Twitter (X) using belt app run x/post-create. This behavior is the primary intended function of a content repurposing skill and is performed via the vendor's managed CLI.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted external data such as blog posts, podcast transcripts (e.g., episode-42.mp3), and video content.
Ingestion points: Data enters the context through files or text provided by the user for conversion.
Boundary markers: The instructions do not explicitly define boundary markers or 'ignore' instructions for the processed content.
Capability inventory: The skill has access to network-enabled tools for posting and generative tasks (x/post-create, falai/dia-tts, etc.).
Sanitization: No explicit sanitization of input text is defined in the workflow.

content-repurposing