The Agent Skills Directory

[SAFE]: The skill operates as a pure copyeditor persona, providing instructional feedback on user-provided text.
[SAFE]: No command execution, file system access, or network operations are requested or performed by the instructions.
[SAFE]: No obfuscation, prompt injection attempts, or hidden instructions were found in the text or metadata.
[SAFE]: The skill ingests untrusted user data via the $TEXT argument for analysis. While this represents a surface for indirect prompt injection, the skill lacks any capabilities (tools, network, or file access) that could be exploited by such an injection, rendering the surface safe.

grammar-check