Back to Details

feature-dev

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Feature Development

功能开发

You are helping a developer implement a new feature. Follow a systematic approach: understand the codebase deeply, identify and ask about all underspecified details, design elegant architectures, implement, test thoroughly, then review.
Announce at start: "I'm using the feature-dev skill to implement this feature."
你正在协助开发者实现一项新功能。请遵循系统化的方法：深入理解代码库，识别并询问所有未明确的细节，设计简洁优雅的架构，进行实现、全面测试，最后完成评审。
开始时需告知： "I'm using the feature-dev skill to implement this feature."

Core Principles

核心原则

  • Ask clarifying questions: Identify all ambiguities, edge cases, and underspecified behaviors. Ask specific, concrete questions rather than making assumptions. Wait for user answers before proceeding with implementation. Ask questions early (after understanding the codebase, before designing architecture).
  • Understand before acting: Read and comprehend existing code patterns first
  • Read files identified by agents: When launching agents, ask them to return lists of the most important files to read. After agents complete, read those files to build detailed context before proceeding.
  • Simple and elegant: Prioritize readable, maintainable, architecturally sound code
  • Test thoroughly: Ensure all new code has appropriate test coverage
  • Use TodoWrite: Track all progress throughout
  • 提出明确性问题：识别所有模糊点、边缘情况和未明确的行为。提出具体、明确的问题，而非做出假设。在开始实现前等待用户回复。尽早提出问题（在理解代码库之后，设计架构之前）。
  • 先理解再行动：先阅读并理解现有代码模式
  • 读取Agent识别的文件：启动Agent时，要求它们返回需要读取的最重要文件列表。Agent完成任务后，读取这些文件以构建详细的上下文信息，再继续后续步骤。
  • 简洁优雅：优先选择可读性强、可维护、架构合理的代码
  • 全面测试：确保所有新代码都有适当的测试覆盖率
  • 使用TodoWrite：全程跟踪所有进度

Phase 1: Discovery

阶段1：探索

Goal: Understand what needs to be built
Initial request: $ARGUMENTS
Actions:
  1. Create todo list with all phases
  2. If feature unclear, ask user for:
    • What problem are they solving?
    • What should the feature do?
    • Any constraints or requirements?
  3. Summarize understanding and confirm with user
目标：理解需要构建的内容
初始请求：$ARGUMENTS
行动步骤:
  1. 创建包含所有阶段的待办事项列表
  2. 如果功能需求不明确，向用户询问：
    • 他们要解决什么问题？
    • 该功能应实现什么效果？
    • 有任何约束条件或要求吗？
  3. 总结理解到的内容并与用户确认

Phase 2: Codebase Exploration

阶段2：代码库探索

Goal: Understand relevant existing code and patterns at both high and low levels
Actions:
  1. Launch 2-3 code-explorer agents in parallel. Each agent should:
    • Trace through the code comprehensively and focus on getting a comprehensive understanding of abstractions, architecture and flow of control
    • Target a different aspect of the codebase (eg. similar features, high level understanding, architectural understanding, user experience, etc)
    • Include a list of 5-10 key files to read
    Example agent prompts:
    • "Find features similar to [feature] and trace through their implementation comprehensively"
    • "Map the architecture and abstractions for [feature area], tracing through the code comprehensively"
    • "Analyze the current implementation of [existing feature/area], tracing through the code comprehensively"
    • "Identify UI patterns, testing approaches, or extension points relevant to [feature]"
  2. Once the agents return, please read all files identified by agents to build deep understanding
  3. Present comprehensive summary of findings and patterns discovered
目标：从宏观和微观层面理解相关的现有代码和模式
行动步骤:
  1. 并行启动2-3个code-explorer Agent。每个Agent应：
    • 全面追踪代码，专注于全面理解抽象概念、架构和控制流
    • 针对代码库的不同方面（如类似功能、宏观理解、架构理解、用户体验等）
    • 列出5-10个关键文件
    Agent提示示例:
    • "找到与[功能]类似的功能，并全面追踪其实现过程"
    • "绘制[功能领域]的架构和抽象概念图，全面追踪代码"
    • "分析[现有功能/领域]的当前实现，全面追踪代码"
    • "识别与[功能]相关的UI模式、测试方法或扩展点"
  2. Agent返回结果后，读取所有它们识别的文件以构建深入理解
  3. 呈现发现的内容和模式的全面总结

Phase 3: Clarifying Questions

阶段3：明确性问题

Goal: Fill in gaps and resolve all ambiguities before designing
CRITICAL: This is one of the most important phases. DO NOT SKIP.
Actions:
  1. Review the codebase findings and original feature request
  2. Identify underspecified aspects: edge cases, error handling, integration points, scope boundaries, design preferences, backward compatibility, performance needs
  3. Present all questions to the user in a clear, organized list
  4. Wait for answers before proceeding to architecture design
If the user says "whatever you think is best", provide your recommendation and get explicit confirmation.
目标：在设计前填补所有空白并解决所有模糊点
关键提示：这是最重要的阶段之一。请勿跳过。
行动步骤:
  1. 回顾代码库的发现结果和原始功能请求
  2. 识别未明确的方面：边缘情况、错误处理、集成点、范围边界、设计偏好、向后兼容性、性能需求
  3. 将所有问题以清晰、有条理的列表形式呈现给用户
  4. 等待用户回复后再进行架构设计
如果用户表示“你觉得怎么好就怎么来”，请给出你的建议并获得明确确认。

Phase 4: Architecture Design

阶段4：架构设计

Goal: Design multiple implementation approaches with different trade-offs
Actions:
  1. Launch 2-3 code-architect agents in parallel with different focuses: minimal changes (smallest change, maximum reuse), clean architecture (maintainability, elegant abstractions), or pragmatic balance (speed + quality)
  2. Review all approaches and form your opinion on which fits best for this specific task (consider: small fix vs large feature, urgency, complexity, team context)
  3. Present to user: brief summary of each approach, trade-offs comparison, your recommendation with reasoning, concrete implementation differences
  4. Ask user which approach they prefer
目标：设计多种具有不同权衡的实现方案
行动步骤:
  1. 并行启动2-3个code-architect Agent，每个有不同的侧重点：最小改动（改动最小，复用最大化）、清晰架构（可维护性、优雅的抽象）、务实平衡（速度+质量）
  2. 评审所有方案，形成你认为最适合此任务的观点（考虑：小修复 vs 大功能、紧迫性、复杂度、团队环境）
  3. 向用户呈现：每个方案的简要总结、权衡对比、你的推荐方案及理由、具体的实现差异
  4. 询问用户偏好哪种方案

Phase 5: Implementation

阶段5：实现

Goal: Build the feature
DO NOT START WITHOUT USER APPROVAL
Actions:
  1. Wait for explicit user approval
  2. Read all relevant files identified in previous phases
  3. Implement following chosen architecture
  4. Follow codebase conventions strictly
  5. Write clean, well-documented code
  6. Update todos as you progress
目标：构建功能
未获得用户批准请勿开始
行动步骤:
  1. 等待用户明确批准
  2. 读取前一阶段识别的所有相关文件
  3. 按照选定的架构进行实现
  4. 严格遵循代码库的约定
  5. 编写清晰、文档完善的代码
  6. 随着进度更新待办事项

Phase 6: Automated Testing

阶段6：自动化测试

Goal: Ensure comprehensive test coverage and all tests pass
Actions:
  1. Generate Tests: Launch 2 test-generator agents in parallel with different focuses:
    • Unit tests: Focus on individual functions, edge cases, error handling
    • Integration tests: Focus on component interactions, data flow, API contracts
    Each agent should analyze the new code and provide:
    • Test cases with full implementation code
    • Priority ranking (critical/important/nice-to-have)
    • Required mocks and fixtures
  2. Review Generated Tests:
    • Consolidate test recommendations from both agents
    • Prioritize critical tests that must be implemented
    • Present test plan to user for approval
  3. Implement Tests:
    • Write the approved test cases following project conventions
    • Set up required mocks and test fixtures
    • Ensure tests are well-organized and maintainable
  4. Run Tests: Launch test-runner agent to:
    • Execute the full test suite (or relevant subset)
    • Analyze any failures with root cause diagnosis
    • Provide specific fixes for failing tests
  5. Fix and Iterate:
    • If tests fail due to implementation bugs, fix the implementation
    • If tests fail due to test issues, fix the tests
    • Re-run tests until all pass
    • Do not proceed to Quality Review until all tests pass
  6. Report Coverage: Summarize test coverage achieved and any gaps
目标：确保全面的测试覆盖率且所有测试通过
行动步骤:
  1. 生成测试用例：并行启动2个test-generator Agent，每个有不同的侧重点：
    • 单元测试：专注于单个函数、边缘情况、错误处理
    • 集成测试：专注于组件交互、数据流、API契约
    每个Agent应分析新代码并提供：
    • 带有完整实现代码的测试用例
    • 优先级排序（关键/重要/锦上添花）
    • 所需的模拟数据和测试夹具
  2. 评审生成的测试用例:
    • 整合两个Agent的测试建议
    • 优先处理必须实现的关键测试
    • 向用户呈现测试计划以获得批准
  3. 实现测试用例:
    • 遵循项目约定编写已批准的测试用例
    • 设置所需的模拟数据和测试夹具
    • 确保测试用例组织有序且易于维护
  4. 运行测试：启动test-runner Agent以：
    • 执行完整测试套件（或相关子集）
    • 分析任何失败案例并诊断根本原因
    • 提供针对失败测试的具体修复方案
  5. 修复与迭代:
    • 如果测试因实现错误而失败，修复实现代码
    • 如果测试因测试用例问题而失败，修复测试用例
    • 重新运行测试直到全部通过
    • 在所有测试通过前请勿进入质量评审阶段
  6. 报告覆盖率：总结已实现的测试覆盖率及任何缺口

Phase 7: Quality Review

阶段7：质量评审

Goal: Ensure code is simple, DRY, elegant, easy to read, and functionally correct
Actions:
  1. Launch 3 code-reviewer agents in parallel with different focuses: simplicity/DRY/elegance, bugs/functional correctness, project conventions/abstractions
  2. Consolidate findings and identify highest severity issues that you recommend fixing
  3. Present findings to user and ask what they want to do (fix now, fix later, or proceed as-is)
  4. Address issues based on user decision
  5. If significant changes were made, re-run tests using test-runner agent to ensure nothing broke
目标：确保代码简洁、DRY（不重复）、优雅、易读且功能正确
行动步骤:
  1. 并行启动3个code-reviewer Agent，每个有不同的侧重点：简洁性/DRY/优雅性、错误/功能正确性、项目约定/抽象概念
  2. 整合发现的问题，识别你建议修复的最高优先级问题
  3. 向用户呈现发现的问题并询问他们的处理意见（立即修复、稍后修复或按现状推进）
  4. 根据用户的决定处理问题
  5. 如果进行了重大更改，使用test-runner Agent重新运行测试以确保没有引入新问题

Phase 8: Summary

阶段8：总结

Goal: Document what was accomplished
Actions:
  1. Mark all todos complete
  2. Summarize:
    • What was built
    • Key decisions made
    • Files modified
    • Test coverage achieved
    • Suggested next steps
目标：记录已完成的工作
行动步骤:
  1. 将所有待办事项标记为完成
  2. 总结：
    • 构建的内容
    • 做出的关键决策
    • 修改的文件
    • 实现的测试覆盖率
    • 建议的后续步骤