The Agent Skills Directory

[SAFE]: The skill is entirely composed of natural language instructions and templates for creative writing. It contains no executable scripts, system commands, or network operations.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected. The instructions are focused solely on video content strategy.
[DATA_EXFILTRATION]: There are no network requests, credential references, or accesses to sensitive file paths. The skill operates purely on the provided text context.
[EXTERNAL_DOWNLOADS]: No external dependencies, package installations, or remote script fetches are present in the files.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands or subprocesses. It lacks the dynamic context injection syntax or any other mechanism for runtime execution.

ra-hook