The Agent Skills Directory

[SAFE]: The skill operates entirely within the agent's internal reasoning and text generation capabilities. It contains no executable scripts, shell commands, or external dependencies. All referenced materials are local markdown files within the skill's own repository structure.
[SAFE]: The frontmatter and instructions focus on guiding the AI's persona and output formatting without attempting to bypass safety filters or override core instructions. Phrases like 'Important' are used in a benign, instructional context.
[SAFE]: The skill refers to internal context files like .agents/product-marketing.md to improve response relevance, which is a standard practice for agentic workflows and does not involve sensitive system paths or credential access.
[SAFE]: No network operations, remote code downloads, or persistence mechanisms are present. The content is purely instructional and follows established marketing best practices.

copywriting