跳到正文
cccskills
免费在 GitHub 公开

refactor

Improve existing code structure while preserving its behavior, using Martin Fowler's refactoring approach. Assess tests, identify structural problems, agree on a phased plan, and make small, tested changes with reversible commits and before-and-after comparisons.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a phased approach with research, planning, and safe incremental implementation.

查看安装方法

适用场景

  • Splitting long functions into clearer responsibilities
  • Removing duplicate or unused code
  • Planning gradual improvements to legacy code
  • Checking tests before changing code structure

包含的文件(6)

  • SKILL.md11.7 KB
  • references/code-smells.md13.5 KB
  • references/refactoring-catalog.md23.7 KB
  • scripts/analyze-complexity.py19.7 KB
  • scripts/detect-smells.py28.1 KB
  • templates/refactoring-plan.md6.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Code Refactoring Skill

A systematic approach to refactoring code based on Martin Fowler's Refactoring: Improving the Design of Existing Code (2nd Edition). This skill emphasizes safe, incremental changes backed by tests.

"Refactoring is the process of changing a software system in such a way that it does not alter the external behavior of the code yet improves its internal structure." — Martin Fowler

Core Principles

  1. Behavior Preservation: External behavior must remain unchanged
  2. Small Steps: Make tiny, testable changes
  3. Test-Driven: Tests are the safety net
  4. Continuous: Refactoring is ongoing, not a one-time event
  5. Collaborative: User approval required at each phase

Workflow Overview

Phase 1: Research & Analysis
    ↓
Phase 2: Test Coverage Assessment
    ↓
Phase 3: Code Smell Identification
    ↓
Phase 4: Refactoring Plan Creation
    ↓
Phase 5: Incremental Implementation
    ↓
Phase 6: Review & Iteration

Phase 1: Research & Analysis

Objectives

  • Understand the codebase structure and purpose
  • Identify the scope of refactoring
  • Gather context about business requirements

Questions to Ask User

Before starting, clarify:

  1. Scope: Which files/modules/functions need refactoring?
  2. Goals: What problems are you trying to solve? (readability, performance, maintainability)
  3. Constraints: Are there any areas that should NOT be changed?
  4. Timeline pressure: Is this blocking other work?
  5. Test status: Do tests exist? Are they passing?

Actions

  • Read and understand the target code
  • Identify dependencies and integrations
  • Document current architecture
  • Note any existing technical debt markers (TODOs, FIXMEs)

Output

Present findings to user:

  • Code structure summary
  • Identified problem areas
  • Initial recommendations
  • Request approval to proceed

Phase 2: Test Coverage Assessment

Why Tests Matter

"Refactoring without tests is like driving without a seatbelt." — Martin Fowler

Tests are the key enabler of safe refactoring. Without them, you risk introducing bugs.

Assessment Steps

  1. Check for existing tests

    # Look for test files
    find . -name "*test*" -o -name "*spec*" | head -20
    
  2. Run existing tests

    # JavaScript/TypeScript
    npm test
    
    # Python
    pytest -v
    
    # Java
    mvn test
    
  3. Check coverage (if available)

    # JavaScript
    npm run test:coverage
    
    # Python
    pytest --cov=.
    

Decision Point: Ask User

If tests exist and pass:

  • Proceed to Phase 3

If tests are missing or incomplete: Present options:

  1. Write tests first (recommended)
  2. Add tests incrementally during refactoring
  3. Proceed without tests (risky - requires user acknowledgment)

If tests are failing:

  • STOP. Fix failing tests before refactoring
  • Ask user: Should we fix tests first?

Test Writing Guidelines (if needed)

For each function being refactored, ensure tests cover:

  • Happy path (normal operation)
  • Edge cases (empty inputs, null, boundaries)
  • Error scenarios (invalid inputs, exceptions)

Use the "red-green-refactor" cycle:

  1. Write failing test (red)
  2. Make it pass (green)
  3. Refactor

Phase 3: Code Smell Identification

What Are Code Smells?

Symptoms of deeper problems in code. They're not bugs, but indicators that the code could be improved.

Common Code Smells to Check

See references/code-smells.md for the complete catalog.

Quick Reference

SmellSignsImpact
Long MethodMethods > 30-50 linesHard to understand, test, maintain
Duplicated CodeSame logic in multiple placesBug fixes needed in multiple places
Large ClassClass with too many responsibilitiesViolates Single Responsibility
Feature EnvyMethod uses another class's data morePoor encapsulation
Primitive ObsessionOveruse of primitives instead of objectsMissing domain concepts
Long Parameter ListMethods with 4+ parametersHard to call correctly
Data ClumpsSame data items appearing togetherMissing abstraction
Switch StatementsComplex switch/if-else chainsHard to extend
Speculative GeneralityCode "just in case"Unnecessary complexity
Dead CodeUnused codeConfusion, maintenance burden

Analysis Steps

  1. Automated Analysis (if scripts available)

    python scripts/detect-smells.py <file>
    
  2. Manual Review

    • Walk through code systematically
    • Note each smell with location and severity
    • Categorize by impact (Critical/High/Medium/Low)
  3. Prioritization Focus on smells that:

    • Block current development
    • Cause bugs or confusion
    • Affect most-changed code paths

Output: Smell Report

Present to user:

  • List of identified smells with locations
  • Severity assessment for each
  • Recommended priority order
  • Request approval on priorities

Phase 4: Refactoring Plan Creation

Selecting Refactorings

For each smell, select an appropriate refactoring from the catalog.

See references/refactoring-catalog.md for the complete list.

Smell-to-Refactoring Mapping

Code SmellRecommended Refactoring(s)
Long MethodExtract Method, Replace Temp with Query
Duplicated CodeExtract Method, Pull Up Method, Form Template Method
Large ClassExtract Class, Extract Subclass
Feature EnvyMove Method, Move Field
Primitive ObsessionReplace Primitive with Object, Replace Type Code with Class
Long Parameter ListIntroduce Parameter Object, Preserve Whole Object
Data ClumpsExtract Class, Introduce Parameter Object
Switch StatementsReplace Conditional with Polymorphism
Speculative GeneralityCollapse Hierarchy, Inline Class, Remove Dead Code
Dead CodeRemove Dead Code

Plan Structure

Use the template at templates/refactoring-plan.md.

For each refactoring:

  1. Target: What code will change
  2. Smell: What problem it addresses
  3. Refactoring: Which technique to apply
  4. Steps: Detailed micro-steps
  5. Risks: What could go wrong
  6. Rollback: How to undo if needed

Phased Approach

CRITICAL: Introduce refactoring gradually in phases.

Phase A: Quick Wins (Low risk, high value)

  • Rename variables for clarity
  • Extract obvious duplicate code
  • Remove dead code

Phase B: Structural Improvements (Medium risk)

  • Extract methods from long functions
  • Introduce parameter objects
  • Move methods to appropriate classes

Phase C: Architectural Changes (Higher risk)

  • Replace conditionals with polymorphism
  • Extract classes
  • Introduce design patterns

Decision Point: Present Plan to User

Before implementation:

  • Show complete refactoring plan
  • Explain each phase and its risks
  • Get explicit approval for each phase
  • Ask: "Should I proceed with Phase A?"

Phase 5: Incremental Implementation

The Golden Rule

"Change → Test → Green? → Commit → Next step"

Implementation Rhythm

For each refactoring step:

  1. Pre-check

    • Tests are passing (green)
    • Code compiles
  2. Make ONE small change

    • Follow the mechanics from the catalog
    • Keep changes minimal
  3. Verify

    • Run tests immediately
    • Check for compilation errors
  4. If tests pass (green)

    • Commit with descriptive message
    • Move to next step
  5. If tests fail (red)

    • STOP immediately
    • Undo the change
    • Analyze what went wrong
    • Ask user if unclear

Commit Strategy

Each commit should be:

  • Atomic: One logical change
  • Reversible: Easy to revert
  • Descriptive: Clear commit message

Example commit messages:

refactor: Extract calculateTotal() from processOrder()
refactor: Rename 'x' to 'customerCount' for clarity
refactor: Remove unused validateOldFormat() method

Progress Reporting

After each sub-phase, report to user:

  • Changes made
  • Tests still passing?
  • Any issues encountered
  • Ask: "Continue with next batch?"

Phase 6: Review & Iteration

Post-Refactoring Checklist

  • All tests passing
  • No new warnings/errors
  • Code compiles successfully
  • Behavior unchanged (manual verification)
  • Documentation updated if needed
  • Commit history is clean

Metrics Comparison

Run complexity analysis before and after:

python scripts/analyze-complexity.py <file>

Present improvements:

  • Lines of code change
  • Cyclomatic complexity change
  • Maintainability index change

User Review

Present final results:

  • Summary of all changes
  • Before/after code comparison
  • Metrics improvements
  • Remaining technical debt
  • Ask: "Are you satisfied with these changes?"

Next Steps

Discuss with user:

  • Additional smells to address?
  • Schedule follow-up refactoring?
  • Apply similar changes elsewhere?

Important Guidelines

When to STOP and Ask

Always pause and consult user when:

  • Unsure about business logic
  • Change might affect external APIs
  • Test coverage is inadequate
  • Significant architectural decision needed
  • Risk level increases
  • You encounter unexpected complexity

Safety Rules

  1. Never refactor without tests (unless user explicitly acknowledges risk)
  2. Never make big changes - break into tiny steps
  3. Never skip the test run after each change
  4. Never continue if tests fail - fix or rollback first
  5. Never assume - when in doubt, ask

What NOT to Do

  • Don't combine refactoring with feature additions
  • Don't refactor during production emergencies
  • Don't refactor code you don't understand
  • Don't over-engineer - keep it simple
  • Don't refactor everything at once

Quick Start Example

Scenario: Long Method with Duplication

Before:

function processOrder(order) {
  // 150 lines of code with:
  // - Duplicated validation logic
  // - Inline calculations
  // - Mixed responsibilities
}

Refactoring Steps:

  1. Ensure tests exist for processOrder()
  2. Extract validation into validateOrder()
  3. Test - should pass
  4. Extract calculation into calculateOrderTotal()
  5. Test - should pass
  6. Extract notification into notifyCustomer()
  7. Test - should pass
  8. Review - processOrder() now orchestrates 3 clear functions

After:

function processOrder(order) {
  validateOrder(order);
  const total = calculateOrderTotal(order);
  notifyCustomer(order, total);
  return { order, total };
}

References

Scripts

  • scripts/analyze-complexity.py - Analyze code complexity metrics
  • scripts/detect-smells.py - Automated smell detection

Version History

  • v1.0.0 (2025-01-15): Initial release with Fowler methodology, phased approach, user consultation points

Last Updated: August 4, 2026 Claude Code Version: 2.1.220 Sources:

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Turn ideas and reference materials into a blog draft with source citations. Work through research, topic development, an approved outline, and revisions, while saving source summaries and numbered drafts to track how the article develops.

中文简介正在准备中。当前显示英语简介。

  • Turning an idea into a structured blog draft
  • Writing an article from research and reference materials
  • Revising an existing draft while keeping earlier versions
luongnv89/claude-howto4.2万2026年10月19日 更新

Turn ideas and reference materials into a blog draft through research, outline approval, and revision. The workflow includes source citations, adjustments for the intended audience and tone, and separate files for each draft version.

中文简介正在准备中。当前显示英语简介。

  • Turning research materials into a blog post
  • Planning an article for a specific audience
  • Drafting articles with source citations
luongnv89/claude-howto4.2万2026年10月19日 更新

Turn ideas and reference materials into a blog draft through research, discussion, and an approved outline. Produce cited articles tailored to the intended audience, then revise them while keeping each draft version.

中文简介正在准备中。当前显示英语简介。

  • Turning an idea into a blog draft
  • Writing an article from research materials
  • Agreeing on an outline before drafting
luongnv89/claude-howto4.2万2026年10月19日 更新

Turn ideas and reference materials into a blog draft through research, outline approval, and revision. The workflow includes source citations, adjustments for the intended audience and tone, and separate files for each draft version.

中文简介正在准备中。当前显示英语简介。

  • Turning research materials into a blog post
  • Planning an article for a specific audience
  • Drafting articles with source citations
luongnv89/claude-howto4.2万2026年10月19日 更新

Write marketing copy, customer messages, and public content in a consistent brand voice. Apply predefined guidance on tone, sentence length, preferred terms, and concrete examples to keep communication friendly, professional, clear, and concise.

中文简介正在准备中。当前显示英语简介。

  • Write marketing copy in a consistent tone
  • Align customer messages with brand guidance
  • Simplify technical explanations for readers
luongnv89/claude-howto4.2万2026年10月19日 更新

Keep marketing copy, customer messages, and public content consistent with a defined brand voice. The skill provides rules for a friendly, professional tone, concise sentences, concrete examples, preferred terminology, and clear calls to action.

中文简介正在准备中。当前显示英语简介。

  • Keeping marketing copy consistent in tone
  • Writing customer messages in the brand's voice
  • Aligning terminology across public content
luongnv89/claude-howto4.2万2026年10月19日 更新

查看 luongnv89 的全部技能

报告此技能的问题