The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown files providing instructional guidelines and writing frameworks. No executable code or binaries are present.
[COMMAND_EXECUTION]: There are no shell commands or dynamic execution patterns. The skill does not utilize the dynamic context injection syntax.
[DATA_EXFILTRATION]: The skill instructions advise the agent to read local project context files (e.g., .agents/product-marketing.md) to gather product information. This is a standard practice for personalizing output and does not involve accessing sensitive system credentials or exfiltrating data.

marketing-copywriting