The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation and configuration files that define a brand voice and best practices for interface copy. No scripts or binary files are included.
[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external data such as translation files (locales/**/*.json), source code, and potentially CMS/API content. This represents an ingestion surface where malicious text could attempt to influence the agent's behavior. However, the skill does not grant the agent high-risk capabilities (like file writing or network access), mitigating the potential impact of such an attack.

better-writing