mirror of
https://github.com/sweetwisdom/everything-claude-code-zh.git
synced 2026-03-21 22:10:09 +00:00
docs: 完成所有文档的中文翻译并应用到项目
This commit is contained in:
xuxiang
@@ -1,54 +1,54 @@
|
||||
# The Shorthand Guide to Everything Claude Code
|
||||
# Claude Code 全方位速查手册
|
||||
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
**Been an avid Claude Code user since the experimental rollout in Feb, and won the Anthropic x Forum Ventures hackathon with [zenith.chat](https://zenith.chat) alongside [@DRodriguezFX](https://x.com/DRodriguezFX) - completely using Claude Code.**
|
||||
**自 2 月份实验性推出以来，我一直是 Claude Code 的忠实用户。我与 [@DRodriguezFX](https://x.com/DRodriguezFX) 合作，完全使用 Claude Code 开发了 [zenith.chat](https://zenith.chat)，并赢得了 Anthropic x Forum Ventures 黑客松。**
|
||||
|
||||
Here's my complete setup after 10 months of daily use: skills, hooks, subagents, MCPs, plugins, and what actually works.
|
||||
以下是我在 10 个月的日常使用后总结出的完整配置：技能（Skills）、生命周期钩子（Hooks）、子智能体（Subagents）、模型上下文协议（MCPs）、插件（Plugins）以及真正行之有效的实践方案。
|
||||
|
||||
---
|
||||
|
||||
## Skills and Commands
|
||||
## 技能（Skills）与命令（Commands）
|
||||
|
||||
Skills operate like rules, constricted to certain scopes and workflows. They're shorthand to prompts when you need to execute a particular workflow.
|
||||
技能（Skills）类似于规则，但被限定在特定的作用域和工作流中。当你需要执行特定工作流时，它们是提示词（Prompts）的快捷方式。
|
||||
|
||||
After a long session of coding with Opus 4.5, you want to clean out dead code and loose .md files? Run `/refactor-clean`. Need testing? `/tdd`, `/e2e`, `/test-coverage`. Skills can also include codemaps - a way for Claude to quickly navigate your codebase without burning context on exploration.
|
||||
在使用 Opus 4.5 进行长时间编码后，想要清理废弃代码和散落的 .md 文件？运行 `/refactor-clean`。需要测试？使用 `/tdd`、`/e2e`、`/test-coverage`。技能还可以包含代码映射（Codemaps）——这是一种让 Claude 快速导航代码库的方法，而不会在探索过程中浪费上下文（Context）。
|
||||
|
||||
|
||||
*Chaining commands together*
|
||||
|
||||
*链式调用多个命令*
|
||||
|
||||
Commands are skills executed via slash commands. They overlap but are stored differently:
|
||||
命令（Commands）是通过斜杠命令（Slash Commands）执行的技能。它们在功能上有重叠，但存储方式不同：
|
||||
|
||||
- **Skills**: `~/.claude/skills/` - broader workflow definitions
|
||||
- **Commands**: `~/.claude/commands/` - quick executable prompts
|
||||
- **技能 (Skills)**: `~/.claude/skills/` - 更广泛的工作流定义
|
||||
- **命令 (Commands)**: `~/.claude/commands/` - 快速可执行的提示词
|
||||
|
||||
```bash
|
||||
# Example skill structure
|
||||
# 示例技能结构
|
||||
~/.claude/skills/
|
||||
pmx-guidelines.md # Project-specific patterns
|
||||
coding-standards.md # Language best practices
|
||||
tdd-workflow/ # Multi-file skill with README.md
|
||||
security-review/ # Checklist-based skill
|
||||
pmx-guidelines.md # 项目特定模式
|
||||
coding-standards.md # 语言最佳实践
|
||||
tdd-workflow/ # 包含 README.md 的多文件技能
|
||||
security-review/ # 基于清单的技能
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Hooks
|
||||
## 生命周期钩子（Hooks）
|
||||
|
||||
Hooks are trigger-based automations that fire on specific events. Unlike skills, they're constricted to tool calls and lifecycle events.
|
||||
生命周期钩子（Hooks）是基于触发器的自动化功能，在特定事件发生时触发。与技能不同，它们被限制在工具调用（Tool Calls）和生命周期事件中。
|
||||
|
||||
**Hook Types:**
|
||||
**钩子类型：**
|
||||
|
||||
1. **PreToolUse** - Before a tool executes (validation, reminders)
|
||||
2. **PostToolUse** - After a tool finishes (formatting, feedback loops)
|
||||
3. **UserPromptSubmit** - When you send a message
|
||||
4. **Stop** - When Claude finishes responding
|
||||
5. **PreCompact** - Before context compaction
|
||||
6. **Notification** - Permission requests
|
||||
1. **PreToolUse** - 工具执行前（验证、提醒）
|
||||
2. **PostToolUse** - 工具执行后（格式化、反馈循环）
|
||||
3. **UserPromptSubmit** - 发送消息时
|
||||
4. **Stop** - Claude 完成响应时
|
||||
5. **PreCompact** - 上下文压缩前
|
||||
6. **Notification** - 权限请求
|
||||
|
||||
**Example: tmux reminder before long-running commands**
|
||||
**示例：在执行耗时命令前发送 tmux 提醒**
|
||||
|
||||
```json
|
||||
{
|
||||
@@ -66,249 +66,249 @@ Hooks are trigger-based automations that fire on specific events. Unlike skills,
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
*Example of what feedback you get in Claude Code, while running a PostToolUse hook*
|
||||
|
||||
*运行 PostToolUse 钩子时在 Claude Code 中获得的反馈示例*
|
||||
|
||||
**Pro tip:** Use the `hookify` plugin to create hooks conversationally instead of writing JSON manually. Run `/hookify` and describe what you want.
|
||||
**专家提示：** 使用 `hookify` 插件可以通过对话方式创建钩子，而无需手动编写 JSON。运行 `/hookify` 并描述你的需求即可。
|
||||
|
||||
---
|
||||
|
||||
## Subagents
|
||||
## 子智能体（Subagents）
|
||||
|
||||
Subagents are processes your orchestrator (main Claude) can delegate tasks to with limited scopes. They can run in background or foreground, freeing up context for the main agent.
|
||||
子智能体（Subagents）是你的编排器（主 Claude 实例）可以委派任务的进程，具有受限的作用域。它们可以在后台或前台运行，从而为主智能体释放上下文空间。
|
||||
|
||||
Subagents work nicely with skills - a subagent capable of executing a subset of your skills can be delegated tasks and use those skills autonomously. They can also be sandboxed with specific tool permissions.
|
||||
子智能体与技能配合得非常好——能够执行部分技能集的子智能体可以被委派任务并自主使用这些技能。它们还可以通过特定的工具权限进行沙箱化处理。
|
||||
|
||||
```bash
|
||||
# Example subagent structure
|
||||
# 示例子智能体结构
|
||||
~/.claude/agents/
|
||||
planner.md # Feature implementation planning
|
||||
architect.md # System design decisions
|
||||
tdd-guide.md # Test-driven development
|
||||
code-reviewer.md # Quality/security review
|
||||
security-reviewer.md # Vulnerability analysis
|
||||
planner.md # 功能实现规划
|
||||
architect.md # 系统设计决策
|
||||
tdd-guide.md # 测试驱动开发
|
||||
code-reviewer.md # 质量/安全审查
|
||||
security-reviewer.md # 漏洞分析
|
||||
build-error-resolver.md
|
||||
e2e-runner.md
|
||||
refactor-cleaner.md
|
||||
```
|
||||
|
||||
Configure allowed tools, MCPs, and permissions per subagent for proper scoping.
|
||||
为每个子智能体配置允许的工具、MCP 和权限，以实现适当的作用域限定。
|
||||
|
||||
---
|
||||
|
||||
## Rules and Memory
|
||||
## 规则（Rules）与记忆（Memory）
|
||||
|
||||
Your `.rules` folder holds `.md` files with best practices Claude should ALWAYS follow. Two approaches:
|
||||
你的 `.rules` 文件夹存放着 Claude 应该始终遵循的最佳实践 `.md` 文件。有两种方法：
|
||||
|
||||
1. **Single CLAUDE.md** - Everything in one file (user or project level)
|
||||
2. **Rules folder** - Modular `.md` files grouped by concern
|
||||
1. **单个 CLAUDE.md** - 所有内容放在一个文件中（用户级或项目级）
|
||||
2. **Rules 文件夹** - 按关注点分组的模块化 `.md` 文件
|
||||
|
||||
```bash
|
||||
~/.claude/rules/
|
||||
security.md # No hardcoded secrets, validate inputs
|
||||
coding-style.md # Immutability, file organization
|
||||
testing.md # TDD workflow, 80% coverage
|
||||
git-workflow.md # Commit format, PR process
|
||||
agents.md # When to delegate to subagents
|
||||
performance.md # Model selection, context management
|
||||
security.md # 禁止硬编码密钥，验证输入
|
||||
coding-style.md # 不可变性，文件组织
|
||||
testing.md # TDD 工作流，80% 覆盖率
|
||||
git-workflow.md # 提交格式，PR 流程
|
||||
agents.md # 何时委派给子智能体
|
||||
performance.md # 模型选择，上下文管理
|
||||
```
|
||||
|
||||
**Example rules:**
|
||||
**示例规则：**
|
||||
|
||||
- No emojis in codebase
|
||||
- Refrain from purple hues in frontend
|
||||
- Always test code before deployment
|
||||
- Prioritize modular code over mega-files
|
||||
- Never commit console.logs
|
||||
- 代码库中严禁使用表情符号 (Emojis)
|
||||
- 前端避免使用紫色调
|
||||
- 部署前始终测试代码
|
||||
- 优先采用模块化代码而非超大文件
|
||||
- 严禁提交 `console.log`
|
||||
|
||||
---
|
||||
|
||||
## MCPs (Model Context Protocol)
|
||||
## 模型上下文协议（MCPs）
|
||||
|
||||
MCPs connect Claude to external services directly. Not a replacement for APIs - it's a prompt-driven wrapper around them, allowing more flexibility in navigating information.
|
||||
模型上下文协议（MCPs）将 Claude 直接连接到外部服务。它不是 API 的替代品，而是围绕 API 的提示词驱动封装，允许在导航信息时具有更高的灵活性。
|
||||
|
||||
**Example:** Supabase MCP lets Claude pull specific data, run SQL directly upstream without copy-paste. Same for databases, deployment platforms, etc.
|
||||
**示例：** Supabase MCP 让 Claude 能够拉取特定数据，直接在上游运行 SQL，无需复制粘贴。数据库、部署平台等同理。
|
||||
|
||||
|
||||
*Example of the Supabase MCP listing the tables within the public schema*
|
||||
|
||||
*Supabase MCP 列出 public 模式下数据表的示例*
|
||||
|
||||
**Chrome in Claude:** is a built-in plugin MCP that lets Claude autonomously control your browser - clicking around to see how things work.
|
||||
**Claude 内部的 Chrome：** 是一个内置的 MCP 插件，允许 Claude 自主控制浏览器——通过点击来查看功能运行情况。
|
||||
|
||||
**CRITICAL: Context Window Management**
|
||||
**关键点：上下文窗口（Context Window）管理**
|
||||
|
||||
Be picky with MCPs. I keep all MCPs in user config but **disable everything unused**. Navigate to `/plugins` and scroll down or run `/mcp`.
|
||||
对 MCP 要精挑细选。我将所有 MCP 保留在用户配置中，但**禁用所有不使用的 MCP**。导航至 `/plugins` 并向下滚动或运行 `/mcp`。
|
||||
|
||||
|
||||
*Using /plugins to navigate to MCPs to see which ones are currently installed and their status*
|
||||
|
||||
*使用 /plugins 导航至 MCP，查看当前已安装的 MCP 及其状态*
|
||||
|
||||
Your 200k context window before compacting might only be 70k with too many tools enabled. Performance degrades significantly.
|
||||
由于启用了过多工具，你在压缩前的 200k 上下文窗口可能实际上只剩 70k。性能会显著下降。
|
||||
|
||||
**Rule of thumb:** Have 20-30 MCPs in config, but keep under 10 enabled / under 80 tools active.
|
||||
**经验法则：** 配置中保留 20-30 个 MCP，但保持启用的少于 10 个 / 活跃工具少于 80 个。
|
||||
|
||||
```bash
|
||||
# Check enabled MCPs
|
||||
# 检查已启用的 MCP
|
||||
/mcp
|
||||
|
||||
# Disable unused ones in ~/.claude.json under projects.disabledMcpServers
|
||||
# 在 ~/.claude.json 的 projects.disabledMcpServers 中禁用不使用的 MCP
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Plugins
|
||||
## 插件（Plugins）
|
||||
|
||||
Plugins package tools for easy installation instead of tedious manual setup. A plugin can be a skill + MCP combined, or hooks/tools bundled together.
|
||||
插件（Plugins）封装了工具以便于安装，避免繁琐的手动设置。一个插件可以是技能（Skill）与 MCP 的组合，也可以是绑定在一起的钩子（Hooks）/工具（Tools）。
|
||||
|
||||
**Installing plugins:**
|
||||
**安装插件：**
|
||||
|
||||
```bash
|
||||
# Add a marketplace
|
||||
# 添加市场
|
||||
claude plugin marketplace add https://github.com/mixedbread-ai/mgrep
|
||||
|
||||
# Open Claude, run /plugins, find new marketplace, install from there
|
||||
# 打开 Claude，运行 /plugins，找到新市场，并从中安装
|
||||
```
|
||||
|
||||
|
||||
*Displaying the newly installed Mixedbread-Grep marketplace*
|
||||
|
||||
*显示新安装的 Mixedbread-Grep 市场*
|
||||
|
||||
**LSP Plugins** are particularly useful if you run Claude Code outside editors frequently. Language Server Protocol gives Claude real-time type checking, go-to-definition, and intelligent completions without needing an IDE open.
|
||||
如果你经常在编辑器之外运行 Claude Code，**LSP 插件**特别有用。语言服务器协议（Language Server Protocol）为 Claude 提供了实时类型检查、转到定义和智能补全功能，无需打开 IDE。
|
||||
|
||||
```bash
|
||||
# Enabled plugins example
|
||||
typescript-lsp@claude-plugins-official # TypeScript intelligence
|
||||
pyright-lsp@claude-plugins-official # Python type checking
|
||||
hookify@claude-plugins-official # Create hooks conversationally
|
||||
mgrep@Mixedbread-Grep # Better search than ripgrep
|
||||
# 已启用插件示例
|
||||
typescript-lsp@claude-plugins-official # TypeScript 智能提示
|
||||
pyright-lsp@claude-plugins-official # Python 类型检查
|
||||
hookify@claude-plugins-official # 对话式创建钩子
|
||||
mgrep@Mixedbread-Grep # 比 ripgrep 更好的搜索
|
||||
```
|
||||
|
||||
Same warning as MCPs - watch your context window.
|
||||
与 MCP 同样的警告——注意你的上下文窗口。
|
||||
|
||||
---
|
||||
|
||||
## Tips and Tricks
|
||||
## 技巧与建议
|
||||
|
||||
### Keyboard Shortcuts
|
||||
### 键盘快捷键
|
||||
|
||||
- `Ctrl+U` - Delete entire line (faster than backspace spam)
|
||||
- `!` - Quick bash command prefix
|
||||
- `@` - Search for files
|
||||
- `/` - Initiate slash commands
|
||||
- `Shift+Enter` - Multi-line input
|
||||
- `Tab` - Toggle thinking display
|
||||
- `Esc Esc` - Interrupt Claude / restore code
|
||||
- `Ctrl+U` - 删除整行（比狂按退格键快）
|
||||
- `!` - 快速 Bash 命令前缀
|
||||
- `@` - 搜索文件
|
||||
- `/` - 启动斜杠命令
|
||||
- `Shift+Enter` - 多行输入
|
||||
- `Tab` - 切换思考过程显示
|
||||
- `Esc Esc` - 中断 Claude / 恢复代码
|
||||
|
||||
### Parallel Workflows
|
||||
### 并行工作流
|
||||
|
||||
- **Fork** (`/fork`) - Fork conversations to do non-overlapping tasks in parallel instead of spamming queued messages
|
||||
- **Git Worktrees** - For overlapping parallel Claudes without conflicts. Each worktree is an independent checkout
|
||||
- **派生** (`/fork`) - 派生对话以并行执行不重叠的任务，而不是让排队的请求堆积
|
||||
- **Git 工作树 (Worktrees)** - 用于并行运行多个 Claude 实例而不会产生冲突。每个工作树都是一个独立的检出目录
|
||||
|
||||
```bash
|
||||
git worktree add ../feature-branch feature-branch
|
||||
# Now run separate Claude instances in each worktree
|
||||
# 现在在每个工作树中运行独立的 Claude 实例
|
||||
```
|
||||
|
||||
### tmux for Long-Running Commands
|
||||
### 使用 tmux 处理耗时命令
|
||||
|
||||
Stream and watch logs/bash processes Claude runs:
|
||||
串流并观察 Claude 运行的日志/Bash 进程：
|
||||
|
||||
https://github.com/user-attachments/assets/shortform/07-tmux-video.mp4
|
||||
|
||||
```bash
|
||||
tmux new -s dev
|
||||
# Claude runs commands here, you can detach and reattach
|
||||
# Claude 在这里运行命令，你可以随时分离 (detach) 和重新连接 (reattach)
|
||||
tmux attach -t dev
|
||||
```
|
||||
|
||||
### mgrep > grep
|
||||
|
||||
`mgrep` is a significant improvement from ripgrep/grep. Install via plugin marketplace, then use the `/mgrep` skill. Works with both local search and web search.
|
||||
`mgrep` 是对 ripgrep/grep 的重大改进。通过插件市场安装，然后使用 `/mgrep` 技能。同时支持本地搜索和网络搜索。
|
||||
|
||||
```bash
|
||||
mgrep "function handleSubmit" # Local search
|
||||
mgrep --web "Next.js 15 app router changes" # Web search
|
||||
mgrep "function handleSubmit" # 本地搜索
|
||||
mgrep --web "Next.js 15 app router changes" # 网络搜索
|
||||
```
|
||||
|
||||
### Other Useful Commands
|
||||
### 其他有用命令
|
||||
|
||||
- `/rewind` - Go back to a previous state
|
||||
- `/statusline` - Customize with branch, context %, todos
|
||||
- `/checkpoints` - File-level undo points
|
||||
- `/compact` - Manually trigger context compaction
|
||||
- `/rewind` - 回退到之前的状态
|
||||
- `/statusline` - 自定义显示分支、上下文占比、待办事项 (Todos)
|
||||
- `/checkpoints` - 文件级撤销点
|
||||
- `/compact` - 手动触发上下文压缩
|
||||
|
||||
### GitHub Actions CI/CD
|
||||
|
||||
Set up code review on your PRs with GitHub Actions. Claude can review PRs automatically when configured.
|
||||
使用 GitHub Actions 在 PR 上设置代码审查。配置完成后，Claude 可以自动审查 PR。
|
||||
|
||||
|
||||
*Claude approving a bug fix PR*
|
||||
|
||||
*Claude 批准了一个漏洞修复 PR*
|
||||
|
||||
### Sandboxing
|
||||
### 沙箱化（Sandboxing）
|
||||
|
||||
Use sandbox mode for risky operations - Claude runs in restricted environment without affecting your actual system.
|
||||
对风险操作使用沙箱模式——Claude 在受限环境中运行，不会影响你的实际系统。
|
||||
|
||||
---
|
||||
|
||||
## On Editors
|
||||
## 关于编辑器
|
||||
|
||||
Your editor choice significantly impacts Claude Code workflow. While Claude Code works from any terminal, pairing it with a capable editor unlocks real-time file tracking, quick navigation, and integrated command execution.
|
||||
编辑器的选择会显著影响 Claude Code 的工作流。虽然 Claude Code 可以从任何终端运行，但配合功能强大的编辑器可以解锁实时文件跟踪、快速导航和集成命令执行。
|
||||
|
||||
### Zed (My Preference)
|
||||
### Zed（我的首选）
|
||||
|
||||
I use [Zed](https://zed.dev) - written in Rust, so it's genuinely fast. Opens instantly, handles massive codebases without breaking a sweat, and barely touches system resources.
|
||||
我使用 [Zed](https://zed.dev) —— 用 Rust 编写，速度极快。瞬间打开，处理庞大的代码库也游刃有余，且几乎不占用系统资源。
|
||||
|
||||
**Why Zed + Claude Code is a great combo:**
|
||||
**为什么 Zed + Claude Code 是绝佳组合：**
|
||||
|
||||
- **Speed** - Rust-based performance means no lag when Claude is rapidly editing files. Your editor keeps up
|
||||
- **Agent Panel Integration** - Zed's Claude integration lets you track file changes in real-time as Claude edits. Jump between files Claude references without leaving the editor
|
||||
- **CMD+Shift+R Command Palette** - Quick access to all your custom slash commands, debuggers, build scripts in a searchable UI
|
||||
- **Minimal Resource Usage** - Won't compete with Claude for RAM/CPU during heavy operations. Important when running Opus
|
||||
- **Vim Mode** - Full vim keybindings if that's your thing
|
||||
- **速度** - 基于 Rust 的性能意味着当 Claude 快速编辑文件时不会有延迟。你的编辑器能跟上节奏
|
||||
- **智能体面板集成** - Zed 的 Claude 集成让你在 Claude 编辑时实时跟踪文件更改。无需离开编辑器即可在 Claude 引用的文件间跳转
|
||||
- **CMD+Shift+R 命令面板** - 在可搜索的 UI 中快速访问所有自定义斜杠命令、调试器和构建脚本
|
||||
- **极低的资源占用** - 在执行繁重操作时不会与 Claude 争夺 RAM/CPU。运行 Opus 时这一点很重要
|
||||
- **Vim 模式** - 如果你习惯 Vim，它有完整的 Vim 键绑定支持
|
||||
|
||||
|
||||
*Zed Editor with custom commands dropdown using CMD+Shift+R. Following mode shown as the bullseye in the bottom right.*
|
||||
|
||||
*使用 CMD+Shift+R 弹出自定义命令下拉列表的 Zed 编辑器。右下角的牛眼图标显示了跟随模式 (Following mode)。*
|
||||
|
||||
**Editor-Agnostic Tips:**
|
||||
**编辑器通用技巧：**
|
||||
|
||||
1. **Split your screen** - Terminal with Claude Code on one side, editor on the other
|
||||
2. **Ctrl + G** - quickly open the file Claude is currently working on in Zed
|
||||
3. **Auto-save** - Enable autosave so Claude's file reads are always current
|
||||
4. **Git integration** - Use editor's git features to review Claude's changes before committing
|
||||
5. **File watchers** - Most editors auto-reload changed files, verify this is enabled
|
||||
1. **分屏显示** - 一侧是运行 Claude Code 的终端，另一侧是编辑器
|
||||
2. **Ctrl + G** - 在 Zed 中快速打开 Claude 当前正在处理的文件
|
||||
3. **自动保存** - 开启自动保存，确保 Claude 读取的文件始终是最新的
|
||||
4. **Git 集成** - 使用编辑器的 Git 功能在提交前审查 Claude 的更改
|
||||
5. **文件监听器** - 大多数编辑器会自动重载更改后的文件，请确认该功能已启用
|
||||
|
||||
### VSCode / Cursor
|
||||
|
||||
This is also a viable choice and works well with Claude Code. You can use it in either terminal format, with automatic sync with your editor using `\ide` enabling LSP functionality (somewhat redundant with plugins now). Or you can opt for the extension which is more integrated with the Editor and has a matching UI.
|
||||
这也是一个可行的选择，并且与 Claude Code 配合良好。你可以通过终端形式使用它，利用 `\ide` 自动与编辑器同步并启用 LSP 功能（现在在某种程度上与插件功能重叠）。或者你可以选择扩展程序，它与编辑器集成度更高，并拥有匹配的 UI。
|
||||
|
||||
|
||||
*The VS Code extension provides a native graphical interface for Claude Code, integrated directly into your IDE.*
|
||||
|
||||
*VS Code 扩展为 Claude Code 提供了原生图形界面，直接集成到你的 IDE 中。*
|
||||
|
||||
---
|
||||
|
||||
## My Setup
|
||||
## 我的配置
|
||||
|
||||
### Plugins
|
||||
### 插件 (Plugins)
|
||||
|
||||
**Installed:** (I usually only have 4-5 of these enabled at a time)
|
||||
**已安装：**（我通常一次只启用 4-5 个）
|
||||
|
||||
```markdown
|
||||
ralph-wiggum@claude-code-plugins # Loop automation
|
||||
frontend-design@claude-code-plugins # UI/UX patterns
|
||||
commit-commands@claude-code-plugins # Git workflow
|
||||
security-guidance@claude-code-plugins # Security checks
|
||||
pr-review-toolkit@claude-code-plugins # PR automation
|
||||
typescript-lsp@claude-plugins-official # TS intelligence
|
||||
hookify@claude-plugins-official # Hook creation
|
||||
ralph-wiggum@claude-code-plugins # 循环自动化
|
||||
frontend-design@claude-code-plugins # UI/UX 模式
|
||||
commit-commands@claude-code-plugins # Git 工作流
|
||||
security-guidance@claude-code-plugins # 安全检查
|
||||
pr-review-toolkit@claude-code-plugins # PR 自动化
|
||||
typescript-lsp@claude-plugins-official # TS 智能提示
|
||||
hookify@claude-plugins-official # 钩子创建
|
||||
code-simplifier@claude-plugins-official
|
||||
feature-dev@claude-code-plugins
|
||||
explanatory-output-style@claude-code-plugins
|
||||
explanatory-output-style@claude-plugins-official
|
||||
code-review@claude-code-plugins
|
||||
context7@claude-plugins-official # Live documentation
|
||||
pyright-lsp@claude-plugins-official # Python types
|
||||
mgrep@Mixedbread-Grep # Better search
|
||||
context7@claude-plugins-official # 实时文档
|
||||
pyright-lsp@claude-plugins-official # Python 类型
|
||||
mgrep@Mixedbread-Grep # 更好的搜索
|
||||
```
|
||||
|
||||
### MCP Servers
|
||||
### MCP 服务器
|
||||
|
||||
**Configured (User Level):**
|
||||
**已配置（用户级）：**
|
||||
|
||||
```json
|
||||
{
|
||||
@@ -336,9 +336,9 @@ mgrep@Mixedbread-Grep # Better search
|
||||
}
|
||||
```
|
||||
|
||||
This is the key - I have 14 MCPs configured but only ~5-6 enabled per project. Keeps context window healthy.
|
||||
关键在于：我配置了 14 个 MCP，但每个项目只启用 ~5-6 个。这能保持上下文窗口的健康。
|
||||
|
||||
### Key Hooks
|
||||
### 关键钩子 (Key Hooks)
|
||||
|
||||
```json
|
||||
{
|
||||
@@ -358,73 +358,73 @@ This is the key - I have 14 MCPs configured but only ~5-6 enabled per project. K
|
||||
}
|
||||
```
|
||||
|
||||
### Custom Status Line
|
||||
### 自定义状态栏 (Custom Status Line)
|
||||
|
||||
Shows user, directory, git branch with dirty indicator, context remaining %, model, time, and todo count:
|
||||
显示用户、目录、带脏标记的 Git 分支、剩余上下文 %、模型、时间和待办事项计数：
|
||||
|
||||
|
||||
*Example statusline in my Mac root directory*
|
||||
|
||||
*我的 Mac 根目录下的状态栏示例*
|
||||
|
||||
```
|
||||
affoon:~ ctx:65% Opus 4.5 19:52
|
||||
▌▌ plan mode on (shift+tab to cycle)
|
||||
▌▌ 规划模式已开启 (按 shift+tab 切换)
|
||||
```
|
||||
|
||||
### Rules Structure
|
||||
### 规则结构 (Rules Structure)
|
||||
|
||||
```
|
||||
~/.claude/rules/
|
||||
security.md # Mandatory security checks
|
||||
coding-style.md # Immutability, file size limits
|
||||
testing.md # TDD, 80% coverage
|
||||
git-workflow.md # Conventional commits
|
||||
agents.md # Subagent delegation rules
|
||||
patterns.md # API response formats
|
||||
performance.md # Model selection (Haiku vs Sonnet vs Opus)
|
||||
hooks.md # Hook documentation
|
||||
security.md # 强制性安全检查
|
||||
coding-style.md # 不可变性，文件大小限制
|
||||
testing.md # TDD，80% 覆盖率
|
||||
git-workflow.md # 约定式提交 (Conventional commits)
|
||||
agents.md # 子智能体委派规则
|
||||
patterns.md # API 响应格式
|
||||
performance.md # 模型选择 (Haiku vs Sonnet vs Opus)
|
||||
hooks.md # 钩子文档说明
|
||||
```
|
||||
|
||||
### Subagents
|
||||
### 子智能体 (Subagents)
|
||||
|
||||
```
|
||||
~/.claude/agents/
|
||||
planner.md # Break down features
|
||||
architect.md # System design
|
||||
tdd-guide.md # Write tests first
|
||||
code-reviewer.md # Quality review
|
||||
security-reviewer.md # Vulnerability scan
|
||||
planner.md # 分解功能需求
|
||||
architect.md # 系统设计
|
||||
tdd-guide.md # 测试先行
|
||||
code-reviewer.md # 质量审查
|
||||
security-reviewer.md # 漏洞扫描
|
||||
build-error-resolver.md
|
||||
e2e-runner.md # Playwright tests
|
||||
refactor-cleaner.md # Dead code removal
|
||||
doc-updater.md # Keep docs synced
|
||||
e2e-runner.md # Playwright 测试
|
||||
refactor-cleaner.md # 废弃代码清理
|
||||
doc-updater.md # 保持文档同步
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Key Takeaways
|
||||
## 核心要点
|
||||
|
||||
1. **Don't overcomplicate** - treat configuration like fine-tuning, not architecture
|
||||
2. **Context window is precious** - disable unused MCPs and plugins
|
||||
3. **Parallel execution** - fork conversations, use git worktrees
|
||||
4. **Automate the repetitive** - hooks for formatting, linting, reminders
|
||||
5. **Scope your subagents** - limited tools = focused execution
|
||||
1. **不要过度复杂化** - 将配置视为微调，而非架构设计
|
||||
2. **上下文窗口极其珍贵** - 禁用不使用的 MCP 和插件
|
||||
3. **并行执行** - 派生对话，利用 Git 工作树
|
||||
4. **自动化重复性任务** - 为格式化、代码检查、提醒设置钩子
|
||||
5. **明确子智能体的作用域** - 受限的工具 = 专注的执行
|
||||
|
||||
---
|
||||
|
||||
## References
|
||||
## 参考资料
|
||||
|
||||
- [Plugins Reference](https://code.claude.com/docs/en/plugins-reference)
|
||||
- [Hooks Documentation](https://code.claude.com/docs/en/hooks)
|
||||
- [Checkpointing](https://code.claude.com/docs/en/checkpointing)
|
||||
- [Interactive Mode](https://code.claude.com/docs/en/interactive-mode)
|
||||
- [Memory System](https://code.claude.com/docs/en/memory)
|
||||
- [Subagents](https://code.claude.com/docs/en/sub-agents)
|
||||
- [MCP Overview](https://code.claude.com/docs/en/mcp-overview)
|
||||
- [插件参考 (Plugins Reference)](https://code.claude.com/docs/en/plugins-reference)
|
||||
- [钩子文档 (Hooks Documentation)](https://code.claude.com/docs/en/hooks)
|
||||
- [检查点功能 (Checkpointing)](https://code.claude.com/docs/en/checkpointing)
|
||||
- [交互模式 (Interactive Mode)](https://code.claude.com/docs/en/interactive-mode)
|
||||
- [记忆系统 (Memory System)](https://code.claude.com/docs/en/memory)
|
||||
- [子智能体 (Subagents)](https://code.claude.com/docs/en/sub-agents)
|
||||
- [MCP 概览 (MCP Overview)](https://code.claude.com/docs/en/mcp-overview)
|
||||
|
||||
---
|
||||
|
||||
**Note:** This is a subset of detail. See the [Longform Guide](./the-longform-guide.md) for advanced patterns.
|
||||
**注：** 以上仅为部分细节。进阶模式请参阅 [长篇指南 (Longform Guide)](./the-longform-guide.md)。
|
||||
|
||||
---
|
||||
|
||||
*Won the Anthropic x Forum Ventures hackathon in NYC building [zenith.chat](https://zenith.chat) with [@DRodriguezFX](https://x.com/DRodriguezFX)*
|
||||
*与 [@DRodriguezFX](https://x.com/DRodriguezFX) 在纽约共同开发 [zenith.chat](https://zenith.chat)，并赢得 Anthropic x Forum Ventures 黑客松。*
|
||||
|
||||
Reference in New Issue
Block a user