我们收到反馈称，很难知道您的技能是否仍然适用于新模型发布。插件评估工具（plugin evals）旨在帮助运行“claude plugin eva...”。
we heard feedback that it's hard to know if your skills are still working with new model releases plugin evals are here to help run `claude plugin eva...
ThariqAI2026-09-11
我们收到反馈称，难以判断您的技能是否与新模型发布保持同步。插件评估功能正是为此而来。在您的插件文件夹中运行 `claude plugin eval init`。ClaudeDevs：Claude代码新功能：claude plugin eval。查看您的插件增加了多少价值，或者是否需要更多改进。您可以创建测试用例，将您的插件或技能与这些测试用例进行匹配，评分这些运行，然后在不使用插件的情况下再次运行每个用例，以查看差异。
原文
we heard feedback that it's hard to know if your skills are still working with new model releasesplugin evals are here to helprun `claude plugin eval init` in your plugin folderClaudeDevs: New in Claude Code: claude plugin evalSee 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.