The Agent Skills Directory

[SAFE]: The skill provides technical guidance and code snippets for RAG evaluation metrics such as Recall and Faithfulness. All content is educational and consistent with the described purpose.
[SAFE]: No patterns of prompt injection, data exfiltration, or malicious command execution were detected. The code examples are benign and focus on measurement logic.
[SAFE]: The prompt templates provided for LLM-as-judge evaluation are well-structured and do not contain instructions to override safety constraints or agent behavior.

rag-evaluation