The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and markdown reference files. No executable scripts, shell commands, or external dependencies are included.
[SAFE]: The skill safely attempts to read a local configuration file (.claude/product-marketing-context.md) to align with brand guidelines. This is a standard, low-risk operation for providing context to the agent.
[SAFE]: No obfuscation, data exfiltration patterns, or privilege escalation attempts were detected. The skill's behavior is consistent with its stated purpose of copy editing and review.

copy-editing