The Agent Skills Directory

[SAFE]: The skill is entirely composed of instructional content and references to local markdown files for copywriting patterns; it contains no executable code, shell commands, or network operations.\n- [SAFE]: The skill instructs the agent to read brand-brief.md for voice and glossary details. This is a legitimate use of local data for contextual personalization and does not pose a security risk as the skill lacks any exfiltration or execution capabilities.\n- [SAFE]: The skill includes safety-relevant guidelines for users, such as flagging potentially illegal bulk cold outreach and requiring standard legal elements like unsubscribe links and Impressums for German senders.\n- [SAFE]: All referenced skills (e.g., landing-page, ads-copy, humanizer-en) and local files belong to the same development context and demonstrate no signs of typosquatting or malicious intent.

email-copy