The Agent Skills Directory

[SAFE]: The skill consists solely of natural language instructions for text transformation and styling. It defines a 'house register' for high-density prose and provides linguistic rules for its application.
[NO_CODE]: No code, scripts, or external dependencies are included or referenced. The skill operates entirely within the context of text manipulation by the LLM.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths, credentials, or network operations (such as curl, wget, or fetch) were found. The skill does not interact with the file system or external network.
[PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters, override core agent instructions, or extract system prompts. The 'IMPORTANT' keyword is not used in a malicious context.

pro