The Agent Skills Directory

[SAFE]: The skill is entirely composed of natural language instructions for text editing and does not include any executable commands, scripts, or network requests.
[NO_CODE]: No external packages or remote scripts are referenced or executed.
[INDIRECT_PROMPT_INJECTION]: Ingestion points: User-provided marketing copy. Boundary markers: None. Capability inventory: No subprocess calls, exec/eval, file-write, or network operations are present across the skill instructions. Sanitization: None. While the skill lacks explicit boundary markers for untrusted data, the absence of any dangerous capabilities results in a safe assessment.

copy-editing