agent-skills-eval: An open-source test framework for measuring AI agent skill effectiveness

Agent Skills — the open standard from Anthropic for giving agents domain knowledge — make it easy to ship a SKILL.md and assume your agent is now better at the task. The hard part is proving it.

agent-skills-eval is the missing piece. It runs your skill against the same prompts twice — once with_skill loaded into context, once without_skill (baseline) — has a judge model grade both outputs, and gives you a side-by-side report.

If the skill doesn't make a measurable difference, you'll see it. If it does, you have receipts.