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.

Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities. Source: taisukeoe/agentic-ai-skills-creator.

View raw