The Agent Skills Directory

[SAFE]: The skill provides detailed instructions for performing mechanical copy-editing tasks (spelling, grammar, punctuation) according to established editorial standards like the Chicago Manual of Style.
[NO_CODE]: The skill consists exclusively of markdown instructions and metadata. No executable scripts (Python, Node.js, Shell) or binary files are included in the skill definition.
[PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety filters, extract system prompts, or override agent behavior beyond the scope of the defined copy-editing task.
[COMMAND_EXECUTION]: No shell commands, system-level operations, or dynamic context injection patterns (e.g., shell command placeholders) are present in the instructions.
[DATA_EXFILTRATION]: The skill does not perform any network operations to external or non-whitelisted domains. Its data access is restricted to reading and flagging the manuscript content provided by the user within the local editor environment.

copy-editor