The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and documentation; it does not contain or execute any scripts, binaries, or automated tools.\n- [SAFE]: No patterns associated with data exfiltration or credential theft were detected. The skill does not perform network requests or access sensitive system files.\n- [SAFE]: The instructions focus on structured data processing (coding cards from a corpus) which, while processing untrusted user data, does not involve dangerous capabilities like subprocess execution or file system writes that could be targeted by indirect prompt injection.\n- [SAFE]: All referenced resources, including the evaluation rubric and shape catalog, are local files within the skill package and do not link to untrusted external domains.

mcphee-structure-derivation