ClaudeDevs· @ClaudeDevs · X·· 2026-09-12AI 评分53
AI 导读
Claude Code 推出 claude plugin eval 功能,用于评估插件或技能带来的实际价值。用户可以创建测试用例、运行插件并为其表现评分,再关闭插件重复运行同一用例,对比两者的差异,判断插件是否需要继续改进。
正文 · 原文
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.
来源:ClaudeDevs · x.com