The Agent Skills Directory

[SAFE]: The skill functions as a high-level manager for copy generation, delegating writing tasks to other skills without executing high-risk commands or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate copy, which is a common surface for indirect prompt injection. This risk is effectively addressed by the mandatory 'De-Slop Pass' in Step 5 and the 'Critique' phase in Step 6, which score the output against strict quality and 'AI-tell' rubrics.
[SAFE]: The skill reads from a project-internal reference file to apply anti-slop guidelines; this file access is restricted to the skill's own environment and does not involve sensitive system directories or credentials.

copy-workflow