The Agent Skills Directory

[SAFE]: The skill defines a structured methodology for reviewing and improving marketing copy through seven focused passes. It provides logical, plain-text instructions for enhancing clarity, voice, and conversion without introducing any malicious logic.
[NO_CODE]: The skill package is composed entirely of markdown documentation. It does not contain any executable scripts, binaries, or platform-specific automation commands that could be misused for malicious purposes.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit user-supplied marketing copy. While it lacks explicit delimiters to prevent an agent from following instructions embedded within the processed text, the skill has no dangerous tools or network capabilities, minimizing the potential impact. \n
Ingestion points: User-provided text processed as described in SKILL.md. \n
Boundary markers: Absent. \n
Capability inventory: Basic file reading of local context (.claude/product-marketing-context.md) and references (references/plain-english-alternatives.md) as specified in SKILL.md. \n
Sanitization: Absent.

copy-editing