advanced-evaluation

SKILL.md

This skill covers production-grade techniques for evaluating LLM outputs using LLMs as judges. It synthesizes research from academic papers, industry practices, and practical implementation experience into actionable patterns for building reliable evaluation systems.

Key insight: LLM-as-a-Judge is not a single technique but a family of approaches, each suited to different evaluation contexts. Choosing the right approach and mitigating known biases is the core competency this skill develops.

Evaluation approaches fall into two primary categories with distinct reliability profiles:

Esta habilidad debe usarse cuando el usuario solicita "implementar LLM como juez", "comparar los resultados del modelo", "crear rúbricas de evaluación", "mitigar el sesgo de evaluación" o menciona calificación directa, comparación por pares, sesgo de posición, canales de evaluación o evaluación de calidad automatizada. Fuente: muratcankoylan/agent-skills-for-context-engineering.

Ver original