The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the belt CLI tool to execute AI models and interact with social media platforms (e.g., posting to Twitter/X via x/post-create). This tool is declared in the allowed-tools metadata.- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt CLI package using npx and references documentation hosted on a public GitHub repository (inference-sh/skills). It also encourages adding additional skills from the same vendor via npx skills add.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external data.
Ingestion points: External text sources such as blog posts, newsletters, and podcast transcripts (specified in conversion recipes).
Boundary markers: Absent; there are no clear delimiters or instructions to ignore embedded commands within the source content.
Capability inventory: The skill has the ability to post content to social media (x/post-create), generate images (falai/flux-dev-lora), and create audio/video assets.
Sanitization: No sanitization or validation of the input content is described, allowing potentially malicious instructions in a blog post to influence the generated social media output or media generation parameters.

content-repurposing