mcpField
R
refactor

refactor

github.com/parcadei开发3.9k623 次安装39 周前更新
代码仓库

关于 refactor

refactor 是通过分析、规划、实施、审查和测试验证来重构代码的工作流技能。它适用于代码整理和大型改动，并设有审查关卡及暂停或检查覆盖率的选项。

主要功能

  1. 01分析现有代码并找出改进点
  2. 02制定分步骤重构计划
  3. 03通过 Agent 序列实施改动
  4. 04审查改动并验证测试
  5. 05支持试运行和逐步审批

适用场景

  1. 01将验证逻辑提取为独立模块
  2. 02在保持行为不变的前提下调整代码结构
  3. 03通过审查关卡规划大型重构

安装

复制下面的命令，在终端中运行。

$npx skills add https://github.com/parcadei/continuous-claude-v3 --skill refactor

安装后在 Claude Code 中输入/refactor确认已加载。

详细介绍

/refactor - 重构工作流

通过评审关卡确保安全重构。

适用场景

  • “重构 X”
  • “清理这段代码”
  • “将其提取到一个模块中”
  • “改进 Y 的架构”
  • 大规模代码重构
  • 减少技术债务

工作流概览

┌──────────┐    ┌────────────┐    ┌──────────┐    ┌──────────┐    ┌───────────┐
│ phoenix  │───▶│   plan-    │───▶│  kraken  │───▶│plan-reviewer│───▶│ arbiter  │
│          │    │   agent    │    │          │    │          │    │           │
└──────────┘    └────────────┘    └──────────┘    └──────────┘    └───────────┘
  Analyze         Plan             Implement       Review          Verify
  current         changes          refactor        changes         tests pass

Agent 顺序

#Agent角色输出
1phoenix分析当前代码，找出可改进之处分析报告
2plan-agent制定安全的重构计划分步计划
3kraken实施重构代码变更
4plan-reviewer评审变更的正确性评审报告
5arbiter验证所有测试仍然通过测试报告

重构原则

  1. 先写测试：重构前确保测试覆盖率足够
  2. 小步进行：每项变更都应可独立验证
  3. 保持行为不变：重构过程中不进行功能变更
  4. 易于评审：变更应便于评审

执行流程

阶段 1：分析
Task(
  subagent_type="phoenix",
  prompt="""
  Analyze for refactoring: [TARGET_CODE]

  Identify:
  - Current pain points
  - Code smells
  - Improvement opportunities
  - Risk areas
  - Test coverage gaps
  """
)
阶段 2：规划
Task(
  subagent_type="plan-agent",
  prompt="""
  Plan refactoring: [TARGET_CODE]

  Analysis: [from phoenix]

  Create:
  - Step-by-step refactoring plan
  - Each step should be:
    - Small and focused
    - Independently testable
    - Reversible
  - Identify files affected
  - Risk mitigation strategy
  """
)
阶段 3：实施
Task(
  subagent_type="kraken",
  prompt="""
  Implement refactoring: [TARGET_CODE]

  Plan: [from plan-agent]

  Requirements:
  - Follow plan exactly
  - Run tests after each step
  - Stop if tests fail
  - NO behavior changes
  """
)
阶段 4：评审
Task(
  subagent_type="plan-reviewer",
  prompt="""
  Review refactoring: [TARGET_CODE]

  Changes: [git diff from kraken]

  Check:
  - Behavior preserved
  - No unintended changes
  - Code quality improved
  - Patterns consistent
  """
)
阶段 5：验证
Task(
  subagent_type="arbiter",
  prompt="""
  Validate refactoring: [TARGET_CODE]

  - Run full test suite
  - Verify no regressions
  - Check type errors
  - Run linting
  """
)

重构类型

提取模块
phoenix → plan-agent → kraken → plan-reviewer → arbiter
重命名/重组
phoenix → kraken → arbiter  (simpler, skip detailed planning)
架构变更
phoenix → plan-agent → [kraken → plan-reviewer] × N phases → arbiter

示例

User: /refactor Extract the validation logic into a separate module

Claude: Starting /refactor workflow...

Phase 1: Analyzing current structure...
[Spawns phoenix]
Found: Validation logic spread across 4 files
- form.ts (lines 45-120)
- api.ts (lines 200-280)
- user.ts (lines 15-45)
- order.ts (lines 88-130)

Phase 2: Planning extraction...
[Spawns plan-agent]
Plan:
1. Create src/validation/index.ts
2. Extract common validators
3. Update imports one file at a time
4. Run tests after each change

Phase 3: Implementing...
[Spawns kraken]
Completed all 4 steps, tests green after each

Phase 4: Reviewing changes...
[Spawns plan-reviewer]
✅ All behavior preserved
✅ DRY improved (removed 45 duplicate lines)
✅ New structure consistent

Phase 5: Final validation...
[Spawns arbiter]
✅ 312 tests passing, 0 regressions

Refactoring complete!

安全标志

  • --dry-run：仅制定计划，不实施
  • --step-by-step：每次变更后暂停，等待批准
  • --coverage-check：继续前要求覆盖率 >80%

评论

支持 Markdown