My Development Preferences【免费下载链接】claude-howtoA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-howtoAbout MeExperience Level: 8 years full-stack developmentPreferred Languages: TypeScript, PythonCommunication Style: Direct, with examplesLearning Style: Visual diagrams with codeCode PreferencesError HandlingI prefer explicit error handling with try-catch blocks and meaningful error messages. Avoid generic errors. Always log errors for debugging.CommentsUse comments for WHY, not WHAT. Code should be self-documenting. Comments should explain business logic or non-obvious decisions.TestingI prefer TDD (test-driven development). Write tests first, then implementation. Focus on behavior, not implementation details.ArchitectureI prefer modular, loosely-coupled design. Use dependency injection for testability. Separate concerns (Controllers, Services, Repositories).Debugging PreferencesUse console.log with prefix:[DEBUG]Include context: function name, relevant variablesUse stack traces when availableAlways include timestamps in logsCommunicationExplain complex concepts with diagramsShow concrete examples before explaining theoryInclude before/after code snippetsSummarize key points at the endProject OrganizationI organize my projects as:project/ ├── src/ │ ├── api/ │ ├── services/ │ ├── models/ │ └── utils/ ├── tests/ ├── docs/ └── docker/ToolingIDE: VS Code with vim keybindingsTerminal: Zsh with Oh-My-ZshFormat: Prettier (100 char line length)Linter: ESLint with airbnb configTest Framework: Jest with React Testing Library需要特别说明上面的字段全部取自 claude-howto 模板是**示例画像**而非你的真实画像。落地时请把经验年数、语言、工具逐项替换成你自己的情况——个人记忆文件的价值在于「真实」照抄他人画像反而会让 Claude 产生错误假设。 ## 三步完成部署从模板到生效 依据 claude-howto 记忆指南中的[「個人メモリのセットアップ」](https://link.gitcode.com/i/d8b9310751d19e173d79f88faf2fb7cb)一节个人记忆文件的部署比项目记忆更简单因为它**不依赖任何具体项目目录** **第 1 步创建 ~/.claude 目录与用户级 CLAUDE.md** bash mkdir -p ~/.claude touch ~/.claude/CLAUDE.md第 2 步把上面整理好的模板写入文件cat ~/.claude/CLAUDE.md EOF # My Development Preferences # ...粘贴上面完整模板内容... EOF也可以直接用你常用的编辑器编辑code ~/.claude/CLAUDE.md第 3 步验证加载ls -la ~/.claude/CLAUDE.md确认文件存在后开启一个新的 Claude Code 会话——用户级 CLAUDE.md 与项目级文件一样是在会话启动时被自动加载进上下文的正在进行的旧会话不会因为文件刚创建而热加载。新会话里可以让 Claude 复述你的代码风格偏好即可验证记忆是否生效。关于首次创建的常见坑英文记忆指南中「Example 3: Personal Memory」记录了一个真实的踩坑场景开发者向 Claude 提出「执行 Python 脚本前先检查虚拟环境并激活」这类规则时如果机器上任何位置都没有 CLAUDE.md 文件Claude 只能回应规则本身、却无法把它落盘——也就是说空有对话确认不等于记忆已持久化。只有当你明确指定把规则写入某个记忆文件例如用户记忆~/.claude/CLAUDE.mdClaude 才会真正执行写入并返回成功确认。下面两张截图完整展示了这一过程先口头提出规则尚未保存随后明确要求「保存到 Personal memory」Claude 写入~/.claude/CLAUDE.md并回执成功。日常维护如何把新偏好持续写进个人记忆个人记忆不是一次配置终身不变的静态文件它应当随你的习惯演进。有两种被 claude-howto 记忆指南明确推荐的更新方式。方式一会话中直接交代推荐单条规则在任意会话中直接以自然语言请 Claude 记住偏好即可例如User: Remember before executing any Python script, always check if there is an existing virtual environment; if there is, activate it first.当文件已经存在时Claude 会确认该规则要进入哪一级记忆项目./CLAUDE.md还是个人~/.claude/CLAUDE.md选定个人记忆后即可完成写入。若文件尚未创建则需要先按上一节步骤补建否则会出现「只确认、不落盘」的情况。方式二用/memory打开编辑器整体修订推荐批量维护/memory【免费下载链接】claude-howtoA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-howto创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考 My Development Preferences
My Development Preferences【免费下载链接】claude-howtoA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-howtoAbout MeExperience Level: 8 years full-stack developmentPreferred Languages: TypeScript, PythonCommunication Style: Direct, with examplesLearning Style: Visual diagrams with codeCode PreferencesError HandlingI prefer explicit error handling with try-catch blocks and meaningful error messages. Avoid generic errors. Always log errors for debugging.CommentsUse comments for WHY, not WHAT. Code should be self-documenting. Comments should explain business logic or non-obvious decisions.TestingI prefer TDD (test-driven development). Write tests first, then implementation. Focus on behavior, not implementation details.ArchitectureI prefer modular, loosely-coupled design. Use dependency injection for testability. Separate concerns (Controllers, Services, Repositories).Debugging PreferencesUse console.log with prefix:[DEBUG]Include context: function name, relevant variablesUse stack traces when availableAlways include timestamps in logsCommunicationExplain complex concepts with diagramsShow concrete examples before explaining theoryInclude before/after code snippetsSummarize key points at the endProject OrganizationI organize my projects as:project/ ├── src/ │ ├── api/ │ ├── services/ │ ├── models/ │ └── utils/ ├── tests/ ├── docs/ └── docker/ToolingIDE: VS Code with vim keybindingsTerminal: Zsh with Oh-My-ZshFormat: Prettier (100 char line length)Linter: ESLint with airbnb configTest Framework: Jest with React Testing Library需要特别说明上面的字段全部取自 claude-howto 模板是**示例画像**而非你的真实画像。落地时请把经验年数、语言、工具逐项替换成你自己的情况——个人记忆文件的价值在于「真实」照抄他人画像反而会让 Claude 产生错误假设。 ## 三步完成部署从模板到生效 依据 claude-howto 记忆指南中的[「個人メモリのセットアップ」](https://link.gitcode.com/i/d8b9310751d19e173d79f88faf2fb7cb)一节个人记忆文件的部署比项目记忆更简单因为它**不依赖任何具体项目目录** **第 1 步创建 ~/.claude 目录与用户级 CLAUDE.md** bash mkdir -p ~/.claude touch ~/.claude/CLAUDE.md第 2 步把上面整理好的模板写入文件cat ~/.claude/CLAUDE.md EOF # My Development Preferences # ...粘贴上面完整模板内容... EOF也可以直接用你常用的编辑器编辑code ~/.claude/CLAUDE.md第 3 步验证加载ls -la ~/.claude/CLAUDE.md确认文件存在后开启一个新的 Claude Code 会话——用户级 CLAUDE.md 与项目级文件一样是在会话启动时被自动加载进上下文的正在进行的旧会话不会因为文件刚创建而热加载。新会话里可以让 Claude 复述你的代码风格偏好即可验证记忆是否生效。关于首次创建的常见坑英文记忆指南中「Example 3: Personal Memory」记录了一个真实的踩坑场景开发者向 Claude 提出「执行 Python 脚本前先检查虚拟环境并激活」这类规则时如果机器上任何位置都没有 CLAUDE.md 文件Claude 只能回应规则本身、却无法把它落盘——也就是说空有对话确认不等于记忆已持久化。只有当你明确指定把规则写入某个记忆文件例如用户记忆~/.claude/CLAUDE.mdClaude 才会真正执行写入并返回成功确认。下面两张截图完整展示了这一过程先口头提出规则尚未保存随后明确要求「保存到 Personal memory」Claude 写入~/.claude/CLAUDE.md并回执成功。日常维护如何把新偏好持续写进个人记忆个人记忆不是一次配置终身不变的静态文件它应当随你的习惯演进。有两种被 claude-howto 记忆指南明确推荐的更新方式。方式一会话中直接交代推荐单条规则在任意会话中直接以自然语言请 Claude 记住偏好即可例如User: Remember before executing any Python script, always check if there is an existing virtual environment; if there is, activate it first.当文件已经存在时Claude 会确认该规则要进入哪一级记忆项目./CLAUDE.md还是个人~/.claude/CLAUDE.md选定个人记忆后即可完成写入。若文件尚未创建则需要先按上一节步骤补建否则会出现「只确认、不落盘」的情况。方式二用/memory打开编辑器整体修订推荐批量维护/memory【免费下载链接】claude-howtoA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.项目地址: https://gitcode.com/GitHub_Trending/cl/claude-howto创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考