The Agent Skills Directory

[SAFE]: The skill consists entirely of informational markdown files and an evaluation JSON. It does not contain any scripts, binary executables, or command-line instructions.
[SAFE]: The skill instructs the agent to read local context files like .agents/product-marketing.md to personalize its advice. This is a standard and safe practice for AI agents to gain project-specific context.
[SAFE]: No prompt injections, data exfiltration patterns, obfuscation, or remote code dependencies were detected across the analyzed files.

marketing-ideas