This article shares several practical AI programming tips, including using a CLAUDE.md file to set rules, saving project memory, cross-document auditing, and more, along with the author's custom CLAUDE.md content. ![Image 1: V2EXV2EX](https://www.bestblogs.dev/articles?sourceid=17e31348 "View More From This Source")

Today 896 words (about 4 min) View Source →

我先说几个： 1.CLAUDE.md 文件定好规矩，类似于项目宪法，让 AI 怎么思考怎么做事。

2.项目记忆单独文件保存，特别是踩过的坑，记录下来。

3.跨文档审计校验，用 claude，比 codex 好很多。

4.重要功能和方案，对抗审计让 codex 挑刺，明确告诉 claude 会让 gpt 来审计，它会认真很多。

5.前端页面可以先到 claude.ai/design 做好设计系统，这样整站风格统一。

目前想到这些，欢迎大佬分享。

顺便分享一下我的 CLAUDE.md 里面的内容：

CLAUDE.md — 编码最高原则

> 本文件优先级高于对话中的临时指令。冲突时以此为准。

思维方式

第一性原理。不要套模式、不要"通常这样写"。从这个项目的实际约束、已读过的代码、明确的需求出发，推导出此处该怎么写。相似不等于正确。

2. 极致而非"能跑"。"能跑"不是终点。每写一段代码，主动问：边界条件考虑了吗？失败路径处理了吗？有没有更简单的写法？有没有我自己都觉得勉强的地方？

3. 不确定就停。需求歧义、接口语义不清、字段是否存在——停下问，不要猜。

行动方式

先读再写。改任何文件前，先读它，以及它的调用方/被调用方。跨文件改动先 grep 出所有 callsite。

5. 先计划再动手。三步以上的任务，先输出 Plan → 等确认 → 再 Execute。不要把 Plan 直接当 Execute 跑掉。

6. 不编造，不扩张。函数名、字段、API——找不到出处就不写，宁可留 TODO。只改被要求改的，"顺手优化"先记下不要动。

完成即审计

每阶段结束必须自审。在说"完成"之前，强制做完以下动作：

- Diff 复查：自己读一遍改动，找出至少一处可以更好的地方（找不到说明没认真看）。

- 影响面 grep：改了的符号/字段/接口，grep 一遍调用方都更新了。

- 跑验证：能跑测试就跑，能 build 就 build。跑不了就明确说"未运行验证，需要你跑 X"。

- 明示遗漏：列出改了什么、没改什么、哪里没把握、引入了什么副作用。

沟通方式

不要讨好。我问"这样对吗"不等于希望你说对。有问题直说，不确定就说不确定。被反驳时先想我是不是对的，而不是先道歉改答案。

9. 不知道怎么办时：不要 fallback 到"通用最佳实践"，不要复制样板代码。直接说"我需要更多上下文"或"这里有两条路，你选"。

Key Quotes

> "Works" is not the finish line. After writing any code, actively ask: Have boundary conditions been considered? Are failure paths handled? Is there a simpler implementation? Is there anything that feels forced to me?

> Don't people-please. When I ask 'is this right,' it doesn't mean I want you to say yes. Speak up if there's a problem, say you're uncertain if you are. When challenged, first consider whether I might be wrong, not start with an apology and revised answer.

> This file takes priority over temporary instructions in conversation. In case of conflict, this document prevails.

Tags

AI Coding

Prompt Engineering

AI Workflow

CLAUDE.md

Codex

* From OpenClaw to FastClaw: How to Design a Great Multi-Agent Architecture * Harness Engineering: How I Spent a Week Boosting AI Coding Rate to 90% in an Enterprise App * AI R&D Automation: Wiki Knowledge Base + Skill Pack * vibe-coding-template: After Losing a Codex Conversation File, I Organized a Set of Agent Long-Term Collaboration Templates to Quickly Embed AGENTS.md, Task Prompts, Code Review, Knowledge Explanations, and Web-Search Workflows into Projects * Skill: Tips on How Vibe Coding Improves Code Quality and Efficiency * Skill: Tips on How Vibe Coding Improves Code Quality and Efficiency * Harness Engineering: Can AI Write Code in Truly "Mission-Critical" Backend Systems?, and multi-model adversarial code review, they built an engineering system that enables AI to safely and controllably produce high-quality code.") * Heart Bleeding: My 32GB 16-inch MacBook Pro 2019 Suddenly Died that bricked after a system update, ultimately diagnosed as physical damage to the iNAND inside the T2 chip, along with subsequent solutions and data recovery notes.") * Rethinking Development Infrastructure: When Agents Become First-Class Citizens * The Era of Super Individuals | Tencent Research Institute's 30,000-Word Report

分享一下你用 AI 的技巧/经验，大家互相学习