The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the belt command-line utility for LLM interaction. Execution is restricted to this specific tool through the allowed-tools frontmatter configuration.
[EXTERNAL_DOWNLOADS]: The documentation references installation guides and associated skills hosted within the inference-sh GitHub organization. These are legitimate resources required for the skill's primary functionality and are handled through the standard npx skills package manager.
[DATA_EXPOSURE]: While the skill involves a belt login step for authentication, it does not contain hardcoded credentials or instructions that exfiltrate sensitive local environment data.

llm-models