The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and static reference documentation. It does not contain executable scripts, shell commands, or binary files.
[PROMPT_INJECTION]: No malicious patterns or instructions to bypass safety guidelines or override system prompts were identified.
[DATA_EXFILTRATION]: There are no network operations or calls to external APIs. The skill only references standard agent context files like MEMORY.md and USER.md for product context, which is standard practice for personalized agent behavior.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, such as piping network content to a shell or installing external packages, are present.
[COMMAND_EXECUTION]: The skill does not utilize any shell command execution or dynamic context injection (!command syntax).

copywriting