evaluating-skills-with-models

SKILL.md

Evaluate skills across multiple Claude models using sub-agents with quality-based scoring.

Binary pass/fail ("did it do X?") fails to differentiate models - all models can "do the steps." The difference is how well they do them. This skill uses weighted scoring to reveal capability differences.

Default to difficult scenarios: When multiple scenarios exist, prioritize Hard or Medium difficulty scenarios for evaluation. Easy scenarios often don't show meaningful differences between models and aren't realistic for production use.

Evalúe las habilidades ejecutándolas en modelos de soneto, opus y haiku utilizando subagentes. Úselo para probar si una habilidad funciona correctamente, comparar el rendimiento del modelo o encontrar el modelo compatible más barato. Devuelve puntuaciones numéricas (0-100) para diferenciar las capacidades del modelo. Fuente: taisukeoe/agentic-ai-skills-creator.

Ver original