AI 导读
Claude Code 新增 claude plugin eval 命令，用于评估插件或 skill 带来的实际增益。用户可以创建测试用例，对插件或 skill 的运行结果打分，再在不启用插件的情况下重跑同一用例，对比两者差异。官方终端示例显示 7 个用例平均差值 +0.29，耗时 1483s、花费 9.59 美元。
正文
New in Claude Code: claude plugin eval
See what value your plugin is adding, or if it needs more work.
You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences. https://t.co/qfPU6WHueV
来源：@ClaudeDevs · x.com