技巧多源确认
Claude 团队工程师分享自己的提示词写法：像跟同事说话一样
精选理由
Claude Code 那位工程师的提示词心得：不用记复杂模板，说清目标、投入程度和验证方式就够，Sonnet 3.5 那套可以放下了。
Anthropic 的 Boris Cherny（Claude Code 背后工程师）发帖称自己用 Claude 的方式就是把它当同事对话，没有秘密套路。他提到在 Sonnet 3.5 时代提示词细节影响很大，如今不再需要过度脚手架化的提示结构。现在只需向模型传达三件事：要做什么、希望它花多少精力、如何验证它做对了。
原文 · Boris Cherny
I am surprised that people are surprised this is how I prompt Claude.
Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.
Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:
1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing
