The Agent Skills Directory

[SAFE]: No prompt injection or safety bypass patterns were identified. The instructions focus on improving creative diversity through specific reasoning scaffolds.
[SAFE]: No data exposure or exfiltration risks are present. The skill does not reference sensitive file paths or credentials.
[SAFE]: No obfuscation, hidden commands, or malicious encoding techniques were found. Citations provided are legitimate references to academic research.
[SAFE]: The skill uses internal platform tools for logic (e.g., method selection and scoring) but does not download or execute untrusted remote code.
[NO_CODE]: The skill contains no executable scripts or system commands; it is composed of instructional markdown and logical workflows.

ideate