The Agent Skills Directory

[SAFE]: The skill operates entirely through natural language instructions and local markdown reference files. It does not perform network operations, execute external code, or access sensitive system files. The instructions encourage reading local project context (e.g., .agents/product-marketing-context.md) to align with brand voice, which is a standard and safe operational practice for AI agents. The evals.json file demonstrates intended behavior focused solely on linguistic analysis and text rewriting without any malicious intent.

copy-editing