The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected. The skill is entirely instructional and focused on marketing optimization.\n- [SAFE]: The skill identifies a surface for potential indirect influence by reading local configuration files, which is a standard pattern for workspace-aware agents.\n
Ingestion points: Reads project context from .agents/product-marketing-context.md or .claude/product-marketing-context.md (SKILL.md).\n
Boundary markers: Not explicitly defined in instructions.\n
Capability inventory: The agent is restricted to generating text-based recommendations and marketing copy.\n
Sanitization: Not applicable as the agent only processes the data as informational context for copywriting.

popup-cro