The Agent Skills Directory

[NO_CODE]: The skill is composed entirely of markdown instructions and evaluation test cases. It contains no executable scripts (Python, Node.js, Shell), binaries, or automated system commands.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing external data by instructing the agent to read context from local files like .agents/marketing-strategy.md. However, because the skill does not include any capabilities for network exfiltration, file system modification, or command execution, this surface area presents no significant security risk.
[SAFE]: The instructions demonstrate good safety practices by explicitly directing the agent to maintain authenticity and follow compliance guidelines, specifically regarding the prevention of fabricated customer testimonials.

storytelling