Skill Eval

Behaviorally evaluate a skill: define 3-5 representative tasks, run each N>=3 times with and without the skill loaded in fresh agents, compare pass rates, and report a comparison table plus concrete improvement items that feed back into the skill's SKILL.md. Use when a skill changes, at quarterly evaluation, or when accepting a new skill. NOT for: static description compliance — use skill-description-audit.

NinjaSln-labs Updated 4 repo stars

File contents

NinjaSln-labs/agent-skills commit 449f3aa0be

Frequently asked questions

npx get-skill add ninjasln-labs/skill-eval