The Agent Skills Directory

[SAFE]: No security issues detected. The instructions are purely instructional and focused on requirement clarification.
[NO_CODE]: The skill contains no scripts, shell commands, or external dependencies. It relies entirely on natural language processing.
[PROMPT_INJECTION]: The instructions do not contain patterns for bypassing safety guidelines, overriding system constraints, or extracting the agent's system prompt.
[DATA_EXFILTRATION]: No evidence of network operations, sensitive file access, or credential harvesting was found in the skill content.

deep-interview