The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and a JSON evaluation file. No scripts or binary files are included.
[SAFE]: While the skill instructs the agent to read local context files such as .agents/product-marketing.md to gather business context, this is a standard configuration pattern. The skill lacks any tools or commands for data exfiltration or external communication, making this ingestion point safe.
[NO_CODE]: No programming logic or shell commands are present within the skill's instructions or metadata.

signup