The Agent Skills Directory

[SAFE]: The skill's functionality is limited to enforcing a specific punctuation style (avoiding em dashes) and providing a utility for verification. No security concerns were detected.
[COMMAND_EXECUTION]: The skill includes a local script, scripts/check_em_dashes.py, intended for use by the agent to verify its own output. The script uses regular expressions to scan text for dash characters and does not perform network operations, access sensitive files, or execute arbitrary code.
[PROMPT_INJECTION]: The instructions provide guidance on how to recast sentences to avoid em dashes. These are benign stylistic constraints and do not attempt to bypass safety filters or manipulate core agent behavior.

no-em-dashes