eval-harness

SKILL.md

Evaluation-driven development (EDD) is a methodology where evaluations are defined before or alongside implementation, ensuring that success criteria are explicit, measurable, and testable from the start.

Purpose: Verify that a new capability works correctly. Capability evals test whether the system can do something it couldn't do before, or does something better than before.

Purpose: Verify that existing functionality still works after changes. Regression evals protect against unintended breakage.

Cadre d'évaluation complet pour les tests systématiques, la mesure et l'assurance qualité des implémentations assistées par l'IA. Prend en charge les évaluations de capacités, les tests de régression, plusieurs types d'évaluateurs et les métriques standardisées. Source : mhylle/claude-skills-collection.

Voir l'original