The Agent Skills Directory

[SAFE]: The skill serves as a technical guide for LLM evaluation and pipeline auditing. It utilizes the opik library for tracing and evaluation, which is an established tool from the skill's author (comet-ml). No evidence of credential theft, obfuscation, or malicious command execution was found. The instructions follow security best practices for LLM judge design, such as enforcing structured JSON output and binary classification. All listed Python and Node.js dependencies are standard, well-known packages for data science and AI evaluation.

opik-evaluate