The Agent Skills Directory

[SAFE] (SAFE): The skill contains no executable scripts (Python, Node.js, or Shell). It is entirely composed of Markdown files containing instructions for the AI agent on how to behave as a conversion copywriter.
[DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, fetch) or sensitive file path access (SSH keys, AWS credentials) were found. The skill reads from a local .claude/product-marketing-context.md file, which is a standard pattern for context-aware agents.
[REMOTE_CODE_EXECUTION] (SAFE): No remote code execution patterns or package installations (pip, npm) were identified. The skill relies purely on the LLM's natural language generation capabilities.
[PROMPT_INJECTION] (SAFE): No malicious override instructions or jailbreak attempts were detected. Instructions like 'IMPORTANT' are used in a benign, instructional context to guide writing style and check for marketing context.

copywriting