The Agent Skills Directory

[SAFE]: The skill instructions direct the agent to read marketing context from specific project files (.agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md). This is a legitimate way to gather context for providing marketing advice and does not involve exfiltration of sensitive data.
[SAFE]: No external network operations, script executions, or package installations are performed by this skill. It relies entirely on static markdown content and local project metadata.
[SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were detected in the skill files or metadata.

marketing-ideas