catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-10 02:24:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: translate workflow guide to English and synchronize Chinese version

Browse Source 
English README (README.md):
- Translate complete workflow guide from Chinese to English
- Maintain workflow structure and examples
- Update all technical terms to English

Chinese README (README_CN.md):
- Add comprehensive workflow guide
- Include brainstorming, planning, execution, and testing phases
- Add context package and task JSON structure examples
- Include LINUX DO community discussion link

Both versions now have consistent workflow documentation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-09-30 16:17:41 +08:00
parent 1acd33ee19
commit 07eff2d115
2 changed files with 281 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

178
README.md
View File

@@ -332,74 +332,74 @@ graph LR
--- ---
## 📖 完整工作流详解 (Complete Workflow Guide) ## 📖 Complete Workflow Guide
> **💡 社区讨论**: [LINUX DO 论坛讨论帖](https://linux.do/t/topic/995175/24) > **💡 Community Discussion**: [LINUX DO Forum Thread](https://linux.do/t/topic/995175/24)
> **📦 项目仓库**: [GitHub - Claude-Code-Workflow](https://github.com/catlog22/Claude-Code-Workflow) > **📦 Repository**: [GitHub - Claude-Code-Workflow](https://github.com/catlog22/Claude-Code-Workflow)
### 🎯 核心工作流程 (Core Workflow) ### 🎯 Core Workflow Process
**完整开发流程**: 头脑风暴 → 用户打磨修改 → 行动规划 → 执行 → 测试 **Complete Development Flow**: Brainstorm → User Refinement → Action Planning → Execution → Testing
```mermaid ```mermaid
graph LR graph LR
A[💭 头脑风暴] --> B[✏️ 用户修改] A[💭 Brainstorm] --> B[✏️ Refinement]
B --> C[📋 行动规划] B --> C[📋 Planning]
C --> D[⚡ 执行] C --> D[⚡ Execution]
D --> E[🧪 测试] D --> E[🧪 Testing]
``` ```
### 🧠 头脑风暴阶段 (Brainstorming Phase) ### 🧠 Brainstorming Phase
#### 涉及指令: #### Available Commands:
- `/workflow:brainstorm:auto-parallel` - 自动概念规划（并行版） - `/workflow:brainstorm:auto-parallel` - Automated concept planning (parallel execution)
- `/workflow:brainstorm:auto-squeeze` - 自动概念规划（串行版，用于测试） - `/workflow:brainstorm:auto-squeeze` - Automated concept planning (sequential execution for testing)
- 单个角色指令（用于重新规划） - Individual role commands (for replanning)
#### 工作流程: #### Workflow Steps:
1. **初始规划**: 通过 `/workflow:brainstorm:auto-squeeze [topic]` 进行自动规划 1. **Initial Planning**: Execute `/workflow:brainstorm:auto-squeeze [topic]` for automated planning
2. **修改优化**: 如果对规划不满意，使用单个角色指令如 `/workflow:brainstorm:ui-designer` 进行修改 2. **Refinement**: If unsatisfied with the plan, use individual role commands like `/workflow:brainstorm:ui-designer` to refine
3. **综合文档**: 通过 `/workflow:brainstorm:synthesis` 生成综合规划文档 3. **Synthesis**: Execute `/workflow:brainstorm:synthesis` to generate comprehensive planning documentation
**可用角色指令**: **Available Role Commands**:
- `🏗️ system-architect` - 系统架构分析 - `🏗️ system-architect` - System architecture analysis
- `🎨 ui-designer` - UI/UX 设计规划 - `🎨 ui-designer` - UI/UX design planning
- `🗄️ data-architect` - 数据架构设计 - `🗄️ data-architect` - Data architecture design
- `🔒 security-expert` - 安全架构分析 - `🔒 security-expert` - Security architecture analysis
- `📊 product-manager` - 产品需求分析 - `📊 product-manager` - Product requirements analysis
- `🔬 innovation-lead` - 技术创新建议 - `🔬 innovation-lead` - Technical innovation recommendations
- `📋 feature-planner` - 功能规划 - `📋 feature-planner` - Feature planning
- `📈 business-analyst` - 业务流程分析 - `📈 business-analyst` - Business process analysis
- `👥 user-researcher` - 用户行为分析 - `👥 user-researcher` - User behavior analysis
### 📋 行动规划阶段 (Action Planning Phase) ### 📋 Action Planning Phase
前述工作过程被称为**概念规划**，完成后进入**行动规划**阶段： The previous stage is called **Concept Planning**. After completion, enter the **Action Planning** phase:
```bash ```bash
/workflow:plan "d:\test_project\.workflow\.active-WFS-promptmaster-platform" /workflow:plan "d:\test_project\.workflow\.active-WFS-promptmaster-platform"
# 一般会传入前一项任务的标识符，也可以增加任务描述 # Typically pass the session identifier from the previous task, can also add task description
``` ```
#### Plan 命令协调器架构: #### Plan Command Coordinator Architecture:
`/workflow:plan` 被设计为协调器，自动协调其他斜杠命令执行，包括四个阶段： `/workflow:plan` is designed as a coordinator that automatically orchestrates other slash commands in four phases:
1. **🚀 Session 启动**: `/workflow:session:start` - 启动一个 workflow session 1. **🚀 Session Initialization**: `/workflow:session:start` - Start a workflow session
2. **🔍 上下文收集**: `/workflow:tools:context-gather` 2. **🔍 Context Gathering**: `/workflow:tools:context-gather`
- 查找相关代码文件（如果是功能更新） - Locate relevant code files (for feature updates)
- 使用 MCP 查找示例代码 - Use MCP to find example code
- 产出 `context-package.json` 供 agent 引用 - Generate `context-package.json` for agent reference
3. **🧪 概念增强**: `/workflow:tools:concept-enhanced` 3. **🧪 Concept Enhancement**: `/workflow:tools:concept-enhanced`
- 使用 CLI 工具对现有计划进行分析 - Analyze existing plans using CLI tools
- 提出改进建议及重点关注事项 - Provide improvement suggestions and key focus areas
- 产出 `ANALYSIS_RESULTS.md` 供 agent 引用 - Generate `ANALYSIS_RESULTS.md` for agent reference
4. **📝 任务生成**: `/workflow:tools:task-generate` 或 `/workflow:tools:task-generate-agent` 4. **📝 Task Generation**: `/workflow:tools:task-generate` or `/workflow:tools:task-generate-agent`
- 制定详细规划 - Develop detailed plans
- 产出任务 JSON 文件、`IMPL_PLAN.md`、`TODO_LIST.md` - Generate task JSON files, `IMPL_PLAN.md`, `TODO_LIST.md`
#### 🗂️ Context Package 示例结构: #### 🗂️ Context Package Structure Example:
```json ```json
{ {
@@ -422,13 +422,13 @@ graph LR
} }
], ],
"implementation_guidance": { "implementation_guidance": {
"start_with": ["项目结构初始化", "数据库架构", "认证系统"], "start_with": ["Project structure initialization", "Database architecture", "Authentication system"],
"key_deliverables": ["后端API", "前端界面", "测试套件"] "key_deliverables": ["Backend API", "Frontend interface", "Test suite"]
} }
} }
``` ```
#### 📋 Task JSON 示例结构: #### 📋 Task JSON Structure Example:
```json ```json
{ {
@@ -442,15 +442,15 @@ graph LR
"priority": "P0" "priority": "P0"
}, },
"context": { "context": {
"requirements": ["设置后端项目结构", "配置 Docker Compose"], "requirements": ["Setup backend project structure", "Configure Docker Compose"],
"focus_paths": ["backend/", "frontend/", "docker-compose.yml"], "focus_paths": ["backend/", "frontend/", "docker-compose.yml"],
"acceptance": ["后端服务运行在 8000 端口", "前端运行在 3000 端口"] "acceptance": ["Backend service running on port 8000", "Frontend running on port 3000"]
}, },
"flow_control": { "flow_control": {
"pre_analysis": [ "pre_analysis": [
{ {
"step": "load_synthesis_specification", "step": "load_synthesis_specification",
"action": "加载综合规范文档", "action": "Load comprehensive specification document",
"commands": ["Read(.workflow/xxx/synthesis-specification.md)"] "commands": ["Read(.workflow/xxx/synthesis-specification.md)"]
} }
] ]
@@ -458,67 +458,67 @@ graph LR
} }
``` ```
系统自动产生上下文，执行下一个斜杠命令，直到流程执行完毕。 The system automatically generates context and executes the next slash command until the workflow completes.
### ⚡ 任务执行阶段 (Execution Phase) ### ⚡ Execution Phase
通过 `/workflow:execute` 进入任务执行阶段： Enter the execution phase via `/workflow:execute`:
#### 🤖 Agent 自动分配: #### 🤖 Automatic Agent Assignment:
- **code-developer**: 代码开发任务 - **code-developer**: Code development tasks
- **code-review-test-agent**: 代码审查和测试任务 - **code-review-test-agent**: Code review and testing tasks
#### 📚 技术栈指南自动加载: #### 📚 Tech Stack Guidelines Auto-Loading:
Agent 根据上下文自动加载对应的技术栈指南（位置：`~\.claude\workflows\cli-templates\tech-stacks`） Agents automatically load corresponding tech stack guidelines based on context (location: `~\.claude\workflows\cli-templates\tech-stacks`)
**可用技术栈模板**: **Available Tech Stack Templates**:
- `typescript-dev.md` - TypeScript 开发规范 - `typescript-dev.md` - TypeScript development standards
- `python-dev.md` - Python 开发约定 - `python-dev.md` - Python development conventions
- `react-dev.md` - React 架构指南 - `react-dev.md` - React architecture guidelines
- `vue-dev.md` - Vue 开发最佳实践 - `vue-dev.md` - Vue development best practices
- `fastapi-dev.md` - FastAPI 后端规范 - `fastapi-dev.md` - FastAPI backend standards
> 💡 **欢迎贡献**: 如果您有更好的技术栈提示词，欢迎提交 PR！ > 💡 **Contributions Welcome**: If you have better tech stack prompts, PRs are welcome!
### 🐛 功能新增与 Bug 修复工作流 (Feature & Bug Fix Workflow) ### 🐛 Feature Development & Bug Fix Workflow
#### 快速交互式规划: #### Quick Interactive Planning:
使用 CLI 命令进行交互式询问，形成计划文档： Use CLI commands for interactive inquiry to form planning documents:
```bash ```bash
# Bug 分析和修复 # Bug analysis and fixing
/cli:mode:bug-index "描述 bug 现象" --tool gemini /cli:mode:bug-index "Describe bug symptoms" --tool gemini
# 深度代码分析 # Deep code analysis
/cli:mode:code-analysis "分析目标" --tool codex /cli:mode:code-analysis "Analysis target" --tool codex
# 架构规划 # Architecture planning
/cli:mode:plan "规划主题" --tool qwen /cli:mode:plan "Planning topic" --tool qwen
``` ```
**执行策略**: **Execution Strategy**:
- **简单任务**: 让 Claude 直接执行 - **Simple tasks**: Let Claude execute directly
- **复杂任务**: 按照完整工作流执行（头脑风暴 → 规划 → 执行） - **Complex tasks**: Follow complete workflow (Brainstorm → Planning → Execution)
### 🧪 测试工作流 (Testing Workflow) ### 🧪 Testing Workflow
在 `/workflow:execute` 完成后： After `/workflow:execute` completion:
```bash ```bash
# 生成测试工作流 # Generate test workflow
/workflow:test-gen WFS-session-id /workflow:test-gen WFS-session-id
# 执行测试任务 # Execute test tasks
/workflow:execute /workflow:execute
``` ```
测试工作流自动生成多层次测试： Test workflow automatically generates multi-level tests:
- **单元测试** (Unit Tests) - **Unit Tests**
- **集成测试** (Integration Tests) - **Integration Tests**
- **端到端测试** (E2E Tests) - **End-to-End Tests** (E2E)
- **性能测试** (Performance Tests) - **Performance Tests**
- **安全测试** (Security Tests) - **Security Tests**
--- ---

192
README_CN.md
View File

@@ -488,6 +488,198 @@ git commit -m "功能实现完成"
cd src/api && /update-memory-related cd src/api && /update-memory-related
``` ```
---
## 📖 完整工作流详解
> **💡 社区讨论**: [LINUX DO 论坛讨论帖](https://linux.do/t/topic/995175/24)
> **📦 项目仓库**: [GitHub - Claude-Code-Workflow](https://github.com/catlog22/Claude-Code-Workflow)
### 🎯 核心工作流程
**完整开发流程**: 头脑风暴 → 用户打磨修改 → 行动规划 → 执行 → 测试
```mermaid
graph LR
A[💭 头脑风暴] --> B[✏️ 用户修改]
B --> C[📋 行动规划]
C --> D[⚡ 执行]
D --> E[🧪 测试]
```
### 🧠 头脑风暴阶段
#### 涉及指令:
- `/workflow:brainstorm:auto-parallel` - 自动概念规划（并行版）
- `/workflow:brainstorm:auto-squeeze` - 自动概念规划（串行版，用于测试）
- 单个角色指令（用于重新规划）
#### 工作流程:
1. **初始规划**: 通过 `/workflow:brainstorm:auto-squeeze [topic]` 进行自动规划
2. **修改优化**: 如果对规划不满意，使用单个角色指令如 `/workflow:brainstorm:ui-designer` 进行修改
3. **综合文档**: 通过 `/workflow:brainstorm:synthesis` 生成综合规划文档
**可用角色指令**:
- `🏗️ system-architect` - 系统架构分析
- `🎨 ui-designer` - UI/UX 设计规划
- `🗄️ data-architect` - 数据架构设计
- `🔒 security-expert` - 安全架构分析
- `📊 product-manager` - 产品需求分析
- `🔬 innovation-lead` - 技术创新建议
- `📋 feature-planner` - 功能规划
- `📈 business-analyst` - 业务流程分析
- `👥 user-researcher` - 用户行为分析
### 📋 行动规划阶段
前述工作过程被称为**概念规划**，完成后进入**行动规划**阶段：
```bash
/workflow:plan "d:\test_project\.workflow\.active-WFS-promptmaster-platform"
# 一般会传入前一项任务的标识符，也可以增加任务描述
```
#### Plan 命令协调器架构:
`/workflow:plan` 被设计为协调器，自动协调其他斜杠命令执行，包括四个阶段：
1. **🚀 Session 启动**: `/workflow:session:start` - 启动一个 workflow session
2. **🔍 上下文收集**: `/workflow:tools:context-gather`
- 查找相关代码文件（如果是功能更新）
- 使用 MCP 查找示例代码
- 产出 `context-package.json` 供 agent 引用
3. **🧪 概念增强**: `/workflow:tools:concept-enhanced`
- 使用 CLI 工具对现有计划进行分析
- 提出改进建议及重点关注事项
- 产出 `ANALYSIS_RESULTS.md` 供 agent 引用
4. **📝 任务生成**: `/workflow:tools:task-generate` 或 `/workflow:tools:task-generate-agent`
- 制定详细规划
- 产出任务 JSON 文件、`IMPL_PLAN.md`、`TODO_LIST.md`
#### 🗂️ Context Package 示例结构:
```json
{
"metadata": {
"task_description": "Implement PromptMaster platform...",
"phase_type": "brainstorming",
"brainstorming_completed": true,
"session_id": "WFS-promptmaster-platform",
"tech_stack": {
"frontend": ["Vue 3", "TypeScript", "Element Plus"],
"backend": ["Python", "FastAPI", "SQLAlchemy"],
"database": ["PostgreSQL", "Redis"]
}
},
"assets": [
{
"type": "documentation",
"path": ".workflow/WFS-xxx/.brainstorming/synthesis-specification.md",
"priority": "critical"
}
],
"implementation_guidance": {
"start_with": ["项目结构初始化", "数据库架构", "认证系统"],
"key_deliverables": ["后端API", "前端界面", "测试套件"]
}
}
```
#### 📋 Task JSON 示例结构:
```json
{
"id": "IMPL-1",
"title": "Project Infrastructure & Environment Setup",
"status": "pending",
"meta": {
"type": "feature",
"agent": "@code-developer",
"complexity": "medium",
"priority": "P0"
},
"context": {
"requirements": ["设置后端项目结构", "配置 Docker Compose"],
"focus_paths": ["backend/", "frontend/", "docker-compose.yml"],
"acceptance": ["后端服务运行在 8000 端口", "前端运行在 3000 端口"]
},
"flow_control": {
"pre_analysis": [
{
"step": "load_synthesis_specification",
"action": "加载综合规范文档",
"commands": ["Read(.workflow/xxx/synthesis-specification.md)"]
}
]
}
}
```
系统自动产生上下文，执行下一个斜杠命令，直到流程执行完毕。
### ⚡ 任务执行阶段
通过 `/workflow:execute` 进入任务执行阶段：
#### 🤖 Agent 自动分配:
- **code-developer**: 代码开发任务
- **code-review-test-agent**: 代码审查和测试任务
#### 📚 技术栈指南自动加载:
Agent 根据上下文自动加载对应的技术栈指南（位置：`~\.claude\workflows\cli-templates\tech-stacks`）
**可用技术栈模板**:
- `typescript-dev.md` - TypeScript 开发规范
- `python-dev.md` - Python 开发约定
- `react-dev.md` - React 架构指南
- `vue-dev.md` - Vue 开发最佳实践
- `fastapi-dev.md` - FastAPI 后端规范
> 💡 **欢迎贡献**: 如果您有更好的技术栈提示词，欢迎提交 PR！
### 🐛 功能新增与 Bug 修复工作流
#### 快速交互式规划:
使用 CLI 命令进行交互式询问，形成计划文档：
```bash
# Bug 分析和修复
/cli:mode:bug-index "描述 bug 现象" --tool gemini
# 深度代码分析
/cli:mode:code-analysis "分析目标" --tool codex
# 架构规划
/cli:mode:plan "规划主题" --tool qwen
```
**执行策略**:
- **简单任务**: 让 Claude 直接执行
- **复杂任务**: 按照完整工作流执行（头脑风暴 → 规划 → 执行）
### 🧪 测试工作流
在 `/workflow:execute` 完成后：
```bash
# 生成测试工作流
/workflow:test-gen WFS-session-id
# 执行测试任务
/workflow:execute
```
测试工作流自动生成多层次测试：
- **单元测试** (Unit Tests)
- **集成测试** (Integration Tests)
- **端到端测试** (E2E Tests)
- **性能测试** (Performance Tests)
- **安全测试** (Security Tests)
---
## 目录结构 ## 目录结构
``` ```