X：Claude Devs (@ClaudeDevs)· @ClaudeDevs·· 6 天前AI 评分
Claude 支持构建评测并对其做 hillclimb
Claude can now help you build evaluations and hillclimb on them. In this article, we share guidance on eval design & skills that Claude Code can use to improve your applications. https://claude.dev/blog/automating-eval-design-and-hillclimbing/
Claude 现在可以帮助用户构建评测（eval）并对其做 hillclimb。官方文章分享了评测设计的原则，以及 Claude Code 中 claude-api 技能的 build-eval 和 hillclimb 命令如何把这些原则落地，用于改进应用。原文链接：https://claude.dev/blog/automating-eval-design-and-hillclimbing/
来源：X：Claude Devs (@ClaudeDevs) · x.lingyaoai.com