The Agent Skills Directory

[SAFE]: The skill's primary function is to read from and write to specific local files (.agents/product-marketing.md) to maintain a "source of truth" for product marketing context. This is standard behavior for an agent skill.
[SAFE]: The 'automatic draft' feature reads project files like README.md and package.json to extract context. These are local file reads intended to assist the user, and no data is sent to external, unauthorized servers.
[SAFE]: No obfuscated URLs, hardcoded credentials, or remote code execution patterns were detected in the instructions or configuration files.
[SAFE]: The skill uses natural instructional language to guide the AI and does not attempt to override safety filters or bypass system prompts.

product-marketing