对Cursor首席设计师12条黄金法则的深度解读

[

Chimin

](https://piedpay.medium.com/?source=post_page---byline--f5d45b518d8c---------------------------------------)

Cursor’s chief designer Ryo Lu posted on X yesterday, personally teaching how to use Cursor effectively. Mastering these rules will make Cursor operate as smoothly as taking off!

Cursor 的首席设计师 Ryo Lu 昨天在 X 上发布，亲自教授如何有效使用 Cursor。掌握这些规则将使 Cursor 的操作如同起飞般顺畅！

Proper Cursor usage = fast, clean code. Improper usage = AI spaghetti code that takes a week to fix. Original post: https://x.com/ryolu_/status/1914384195138511142

正确使用 Cursor = 快速、干净的代码。错误使用 = AI 意大利面条代码，修复需要一周时间。原始帖子： https://x.com/ryolu_/status/1914384195138511142

Set 5–10 clear project rules upfront so Cursor knows your structure and constraints. Try /generate rules for existing codebases.
提前设定 5-10 条明确的项目规则，以便 Cursor 了解你的结构和约束。尝试 /generate 规则以适用于现有代码库。
Be specific in prompts. Spell out tech stack, behavior, and constraints like a mini spec.
在提示中要具体。详细说明技术栈、行为和约束，就像一个迷你规格。
Work file by file; generate, test, and review in small, focused chunks.
逐个文件工作；以小而集中的块生成、测试和审查。
Write tests first, lock them, and generate code until all tests pass.
首先编写测试，锁定它们，然后生成代码直到所有测试通过。
Always review AI output and hard-fix anything that breaks, then tell Cursor to use them as examples.
始终审查 AI 输出，并对任何破损的部分进行硬修复，然后告诉 Cursor 将它们用作示例。
Use @ file, @ folders, @ git to scope Cursor’s attention to the right parts of your codebase.
使用 @ 文件, @ 文件夹, @ git 将 Cursor 的注意力集中在代码库的正确部分。
Keep design docs and checklists in .cursor/ so the agent has full context on next steps.
将设计文档和检查清单保存在 .cursor/ 中，以便代理能够全面了解下一步。
If code is wrong, just write it yourself. Cursor learns faster from edits than explanations.
如果代码错误，就自己写。Cursor 从编辑中学习的速度比从解释中快。
Use chat history to iterate on old prompts without starting over.
利用聊天记录在旧提示上进行迭代，而无需重新开始。
Choose models intentionally. Gemini for precision, Claude for breadth.
有意选择模型。Gemini 用于精确，Claude 用于广度。