feature-dev

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Feature Development Workflow

功能开发工作流

A comprehensive, structured workflow for feature development with specialized agents for codebase exploration, architecture design, and quality review.

这是一套全面、结构化的功能开发工作流，借助专用Agent完成代码库探索、架构设计和质量评审工作。

Quick Start

快速开始

Launch the guided feature development workflow:

bash

/feature-dev Add user authentication with OAuth

Or interactively:

bash

/feature-dev

The workflow will guide you through 7 distinct phases automatically.

启动引导式功能开发工作流：

bash

/feature-dev Add user authentication with OAuth

或交互式启动：

bash

/feature-dev

工作流将自动引导你完成7个不同阶段。

Overview

概述

Building features requires more than just writing code. This skill provides a systematic approach that:

Understands the codebase before making changes
Asks clarifying questions to resolve ambiguities
Designs thoughtfully with multiple architecture options
Reviews for quality after implementation

开发功能不仅仅是编写代码。本Skill提供一套系统化方法，能够：

在修改前理解代码库
提出澄清问题以解决模糊点
审慎设计并提供多种架构方案
在实现后进行质量评审

The 7-Phase Workflow

7阶段工作流

Phase 1: Discovery

阶段1：需求探索

Goal: Understand what needs to be built

Clarifies unclear feature requests
Identifies problem, constraints, and requirements
Summarizes understanding and confirms with user

Example:

User: /feature-dev Add caching
Agent: Let me understand what you need...
       - What should be cached? (API responses, computed values, etc.)
       - What are your performance requirements?
       - Do you have a preferred caching solution?

目标：明确需要开发的内容

澄清模糊的功能需求
识别问题、约束条件和需求
总结理解内容并与用户确认

示例:

用户: /feature-dev Add caching
Agent: 让我先了解你的需求...
       - 需要缓存什么内容？（API响应、计算值等）
       - 你的性能要求是什么？
       - 你有偏好的缓存解决方案吗？

Phase 2: Codebase Exploration

阶段2：代码库探索

Goal: Understand relevant existing code and patterns

Launches 2-3
```
code-explorer
```
agents in parallel
Explores similar features, architecture, UI patterns
Reads all identified files for deep understanding
Presents comprehensive summary of findings

Agents launched:

"Find features similar to [feature] and trace implementation"
"Map the architecture and abstractions for [area]"
"Analyze current implementation of [related feature]"

Example output:

Found similar features:
- User authentication (src/auth/): Uses JWT tokens, middleware pattern
- Session management (src/session/): Redis-backed, 24hr expiry

Key files:
- src/auth/AuthService.ts:45 - Core authentication logic
- src/middleware/authMiddleware.ts:12 - Request authentication

目标：理解相关现有代码和模式

并行启动2-3个
```
code-explorer
```
Agent
探索类似功能、架构、UI模式
读取所有识别到的文件以深入理解
呈现全面的发现总结

启动的Agent:

"查找与[feature]类似的功能并追踪实现逻辑"
"绘制[领域]的架构和抽象关系图"
"分析[相关功能]的当前实现"

示例输出:

找到类似功能:
- 用户认证（src/auth/）：使用JWT令牌、中间件模式
- 会话管理（src/session/）：基于Redis、24小时过期

关键文件:
- src/auth/AuthService.ts:45 - 核心认证逻辑
- src/middleware/authMiddleware.ts:12 - 请求认证

Phase 3: Clarifying Questions

阶段3：澄清问题

Goal: Fill in gaps and resolve all ambiguities

Reviews codebase findings and feature request
Identifies underspecified aspects (edge cases, error handling, integration points)
Presents organized list of questions
Waits for answers before proceeding

Example:

Before designing, I need to clarify:

1. OAuth provider: Which providers? (Google, GitHub, custom?)
2. User data: Store OAuth tokens or just profile?
3. Existing auth: Replace or add alongside current auth?
4. Sessions: Integrate with existing session management?
5. Error handling: How to handle OAuth failures?

Critical: Ensures nothing is ambiguous before design begins.

目标：填补信息空白，解决所有模糊点

回顾代码库发现和功能需求
识别未明确的方面（边缘情况、错误处理、集成点）
呈现结构化的问题列表
等待回答后再继续

示例:

在开始设计前，我需要澄清以下问题：

1. OAuth提供商：选择哪些提供商？（Google、GitHub还是自定义？）
2. 用户数据：存储OAuth令牌还是仅存储用户资料？
3. 现有认证：替换还是新增到现有认证体系中？
4. 会话：是否与现有会话管理集成？
5. 错误处理：如何处理OAuth失败情况？

关键提示：确保设计开始前没有任何模糊点。

Phase 4: Architecture Design

阶段4：架构设计

Goal: Design multiple implementation approaches

Launches 2-3
```
code-architect
```
agents with different focuses:
- Minimal changes: Smallest change, maximum reuse
- Clean architecture: Maintainability, elegant abstractions
- Pragmatic balance: Speed + quality
Presents comparison with trade-offs and recommendation
Asks which approach to use

Example output:

Approach 1: Minimal Changes
- Extend existing AuthService with OAuth methods
Pros: Fast, low risk
Cons: Couples OAuth to existing auth

Approach 2: Clean Architecture
- New OAuthService with dedicated interface
Pros: Clean separation, testable
Cons: More files, more refactoring

Approach 3: Pragmatic Balance
- New OAuthProvider abstraction
Pros: Balanced complexity and cleanliness
Cons: Some coupling remains

Recommendation: Approach 3 - clean boundaries without excessive refactoring

目标：设计多种实现方案

启动2-3个不同侧重点的
```
code-architect
```
Agent:
- 最小改动：改动量最小，复用最大化
- 整洁架构：可维护性、优雅的抽象设计
- 务实平衡：开发速度 + 代码质量
呈现方案对比、权衡点及推荐方案
询问使用哪种方案

示例输出:

方案1：最小改动
- 扩展现有AuthService，添加OAuth方法
优点：开发快、风险低
缺点：将OAuth与现有认证耦合

方案2：整洁架构
- 新建带独立接口的OAuthService
优点：清晰解耦、可测试
缺点：新增文件多、重构量大

方案3：务实平衡
- 新建OAuthProvider抽象层
优点：复杂度与整洁度平衡
缺点：仍存在部分耦合

推荐方案：方案3 - 在不过度重构的前提下保证清晰边界

Phase 5: Implementation

阶段5：功能实现

Goal: Build the feature

Waits for explicit approval before starting
Reads all relevant files from previous phases
Implements following chosen architecture
Follows codebase conventions strictly
Updates todos to track progress

目标：开发功能

等待明确批准后再开始
读取前一阶段所有相关文件
按照选定的架构实现
严格遵循代码库约定
更新待办事项以跟踪进度

Phase 6: Quality Review

阶段6：质量评审

Goal: Ensure code is simple, DRY, elegant, and functionally correct

Launches 3
```
code-reviewer
```
agents in parallel:
- Simplicity/DRY/Elegance: Code quality
- Bugs/Correctness: Functional correctness
- Conventions/Abstractions: Project standards
Consolidates findings and identifies high severity issues
Asks what to do: Fix now, fix later, or proceed as-is

Example output:

High Priority Issues:
1. Missing error handling in OAuth callback (src/auth/oauth.ts:67)
2. Memory leak: OAuth state not cleaned up (src/auth/oauth.ts:89)

Medium Priority:
1. Could simplify token refresh logic (src/auth/oauth.ts:120)

What would you like to do?

目标：确保代码简洁、DRY、优雅且功能正确

并行启动3个
```
code-reviewer
```
Agent:
- 简洁性/DRY原则/优雅度：代码质量
- Bug/正确性：功能正确性
- 约定/抽象：项目标准
整合发现结果并识别高严重性问题
询问处理方式：立即修复、后续修复或保持现状

示例输出:

高优先级问题:
1. OAuth回调缺少错误处理（src/auth/oauth.ts:67）
2. 内存泄漏：OAuth状态未清理（src/auth/oauth.ts:89）

中优先级:
1. 可简化令牌刷新逻辑（src/auth/oauth.ts:120）

你希望如何处理？

Phase 7: Summary

阶段7：总结

Goal: Document what was accomplished

Marks all todos complete
Summarizes what was built, key decisions, files modified
Suggests next steps

目标：记录完成的工作

标记所有待办事项为完成
总结开发内容、关键决策、修改的文件
建议下一步行动

Specialized Agents

专用Agent

code-explorer

Purpose: Deeply analyzes existing codebase features by tracing execution paths

Focus:

Entry points and call chains
Data flow and transformations
Architecture layers and patterns
Implementation details

Output:

Entry points with file:line references
Step-by-step execution flow
Key components and responsibilities
Essential files to read

Triggered: Automatically in Phase 2, or manually

用途：通过追踪执行路径深入分析现有代码库功能

关注点:

入口点和调用链
数据流和转换
架构层和模式
实现细节

输出:

带文件:行号引用的入口点
分步执行流程
关键组件及职责
需阅读的核心文件

触发时机：阶段2自动触发，或手动触发

code-architect

Purpose: Designs feature architectures and implementation blueprints

Focus:

Codebase pattern analysis
Architecture decisions
Component design
Implementation roadmap

Output:

Patterns and conventions found
Architecture decision with rationale
Complete component design
Implementation map with build sequence

Triggered: Automatically in Phase 4, or manually

用途：设计功能架构和实现蓝图

关注点:

代码库模式分析
架构决策
组件设计
实现路线图

输出:

发现的模式和约定
带理由的架构决策
完整的组件设计
含构建顺序的实现地图

触发时机：阶段4自动触发，或手动触发

code-reviewer

Purpose: Reviews code for bugs, quality issues, and project conventions

Focus:

Project guideline compliance (CLAUDE.md)
Bug detection
Code quality issues
Confidence-based filtering (≥80% confidence only)

Output:

Critical issues (confidence 75-100)
Important issues (confidence 50-74)
Specific fixes with file:line references

Triggered: Automatically in Phase 6, or manually

用途：评审代码中的Bug、质量问题和项目约定合规性

关注点:

项目指南合规性（CLAUDE.md）
Bug检测
代码质量问题
基于置信度的筛选（仅保留≥80%置信度的问题）

输出:

严重问题（置信度75-100）
重要问题（置信度50-74）
带文件:行号引用的具体修复建议

触发时机：阶段6自动触发，或手动触发

Usage Patterns

使用模式

Full workflow (recommended for new features)

完整工作流（推荐用于新功能）

bash

/feature-dev Add rate limiting to API endpoints

bash

/feature-dev Add rate limiting to API endpoints

Manual agent invocation

手动调用Agent

Explore a feature:

"Launch code-explorer to trace how authentication works"

Design architecture:

"Launch code-architect to design the caching layer"

Review code:

"Launch code-reviewer to check my recent changes"

探索功能:

"Launch code-explorer to trace how authentication works"

设计架构:

"Launch code-architect to design the caching layer"

评审代码:

"Launch code-reviewer to check my recent changes"

When to Use

使用场景

Use for:

New features that touch multiple files
Features requiring architectural decisions
Complex integrations with existing code
Features where requirements are somewhat unclear

Don't use for:

Single-line bug fixes
Trivial changes
Well-defined simple tasks
Urgent hotfixes

适合使用的场景:

涉及多文件的新功能开发
需要做出架构决策的功能
与现有代码的复杂集成
需求存在一定模糊性的功能

不适合使用的场景:

单行Bug修复
微小改动
需求明确的简单任务
紧急热修复

Best Practices

最佳实践

Use the full workflow for complex features: The 7 phases ensure thorough planning
Answer clarifying questions thoughtfully: Phase 3 prevents future confusion
Choose architecture deliberately: Phase 4 gives options for a reason
Don't skip code review: Phase 6 catches issues before production
Read the suggested files: Phase 2 identifies key files—read them for context

复杂功能使用完整工作流：7个阶段确保规划周全
认真回答澄清问题：阶段3避免后续混淆
谨慎选择架构方案：阶段4提供多种方案是有原因的
不要跳过代码评审：阶段6在上线前发现问题
阅读推荐文件：阶段2识别出的关键文件能提供上下文

Common Issues

常见问题

Agents take too long

Agent运行时间过长

Cause: Normal for large codebases Solution: Agents run in parallel when possible. Thoroughness pays off in better understanding.

原因：大型代码库的正常现象 解决方案：Agent尽可能并行运行，充分的理解能带来更好的结果。

Too many clarifying questions

澄清问题过多

Cause: Feature request too vague Solution: Be more specific in initial request. Provide context about constraints upfront.

原因：功能需求过于模糊 解决方案：初始需求更具体，提前提供约束条件的上下文。

Architecture options overwhelming

架构方案过于复杂

Cause: Multiple valid approaches presented Solution: Trust the recommendation (based on codebase analysis). Pick pragmatic option when in doubt.

原因：呈现了多种可行方案 解决方案：信任基于代码库分析给出的推荐方案。不确定时选择务实方案。

Requirements

要求

Claude Code installed
Git repository (for code review)
Existing codebase (workflow learns from existing patterns)

已安装Claude Code
Git仓库（用于代码评审）
现有代码库（工作流从现有模式中学习）

Tips

提示

Be specific in feature request: More detail = fewer clarifying questions
Trust the process: Each phase builds on the previous one
Review agent outputs: Agents provide valuable codebase insights
Don't skip phases: Each phase serves a purpose
Use for learning: Exploration phase teaches you about your own codebase

功能需求尽量具体：细节越多，澄清问题越少
信任流程：每个阶段都基于前一阶段的成果
查看Agent输出：Agent能提供有价值的代码库洞察
不要跳过阶段：每个阶段都有其作用
用于学习：探索阶段能帮助你了解自己的代码库

Verification Checklist

验证清单

References

参考资料

For detailed workflow documentation, see

README.md

For agent specifications, see:

```
agents/code-explorer.md
```
```
agents/code-architect.md
```
```
agents/code-reviewer.md
```

For slash command implementation, see

commands/feature-dev.md

详细工作流文档请参阅

README.md

Agent规格请参阅：

```
agents/code-explorer.md
```
```
agents/code-architect.md
```
```
agents/code-reviewer.md
```

斜杠命令实现请参阅

commands/feature-dev.md