Official agent skill

Refactor

by github in github/awesome-copilot

Surgical code refactoring to improve maintainability without changing behavior.

OfficialMITAuto-check passedDevelopment

Install Refactor

skills CLI
$ npx skills add github/awesome-copilot --skill refactor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install github/awesome-copilot refactor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/refactor .claude/skills/refactor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
refactor
GitHub stars
40k
Used in
6 other repos
Token cost
~4.2k tokens
SKILL.md length
386 words
Files
1
Skills in repo
417
Repo updated
First seen
Licence
MIT

At a glance

Surgical code refactoring to improve maintainability without changing behavior.

  • Works in 10 steps: Long Method/Function → Duplicated Code → Large Class/Module → …
  • Gradual improvements
  • SKILL.md covers Overview, When to Use, Refactoring Principles and Common Code Smells & Fixes, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Refactor is an agent skill from github/awesome-copilot, published by the product's own GitHub organization. Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Refactoring. The repository describes itself as: Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. The licence is MIT.

When your agent uses it

  • Gradual improvements
  • Tasks that involve Refactoring

Example prompts

  • “/refactor”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Long Method/Function
  2. Duplicated Code
  3. Large Class/Module
  4. Long Parameter List
  5. Feature Envy
  6. Primitive Obsession
  7. Magic Numbers/Strings
  8. Nested Conditionals
  9. Dead Code
  10. Inappropriate Intimacy

What it can do on your machine

Read from SKILL.md and the folder at commit 7cce7cf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are diff).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Refactor loads about 4.2k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 386 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from github/awesome-copilot at commit 7cce7cf, republished under its MIT licence (© github). 386 words, ~4,211 tokens.

Download SKILL.mdSave it as .claude/skills/refactor/SKILL.md (or your agent's skills folder).
name
refactor
description
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
license
MIT

Refactor

Overview

Improve code structure and readability without changing external behavior. Refactoring is gradual evolution, not revolution. Use this for improving existing code, not rewriting from scratch.

When to Use

Use this skill when:

  • Code is hard to understand or maintain
  • Functions/classes are too large
  • Code smells need addressing
  • Adding features is difficult due to code structure
  • User asks "clean up this code", "refactor this", "improve this"

Refactoring Principles

The Golden Rules
  1. Behavior is preserved - Refactoring doesn't change what the code does, only how
  2. Small steps - Make tiny changes, test after each
  3. Version control is your friend - Commit before and after each safe state
  4. Tests are essential - Without tests, you're not refactoring, you're editing
  5. One thing at a time - Don't mix refactoring with feature changes
When NOT to Refactor
- Code that works and won't change again (if it ain't broke...)
- Critical production code without tests (add tests first)
- When you're under a tight deadline
- "Just because" - need a clear purpose

Common Code Smells & Fixes

1. Long Method/Function
diff
# BAD: 200-line function that does everything
- async function processOrder(orderId) {
-   // 50 lines: fetch order
-   // 30 lines: validate order
-   // 40 lines: calculate pricing
-   // 30 lines: update inventory
-   // 20 lines: create shipment
-   // 30 lines: send notifications
- }

# GOOD: Broken into focused functions
+ async function processOrder(orderId) {
+   const order = await fetchOrder(orderId);
+   validateOrder(order);
+   const pricing = calculatePricing(order);
+   await updateInventory(order);
+   const shipment = await createShipment(order);
+   await sendNotifications(order, pricing, shipment);
+   return { order, pricing, shipment };
+ }
2. Duplicated Code
diff
# BAD: Same logic in multiple places
- function calculateUserDiscount(user) {
-   if (user.membership === 'gold') return user.total * 0.2;
-   if (user.membership === 'silver') return user.total * 0.1;
-   return 0;
- }
-
- function calculateOrderDiscount(order) {
-   if (order.user.membership === 'gold') return order.total * 0.2;
-   if (order.user.membership === 'silver') return order.total * 0.1;
-   return 0;
- }

# GOOD: Extract common logic
+ function getMembershipDiscountRate(membership) {
+   const rates = { gold: 0.2, silver: 0.1 };
+   return rates[membership] || 0;
+ }
+
+ function calculateUserDiscount(user) {
+   return user.total * getMembershipDiscountRate(user.membership);
+ }
+
+ function calculateOrderDiscount(order) {
+   return order.total * getMembershipDiscountRate(order.user.membership);
+ }
3. Large Class/Module
diff
# BAD: God object that knows too much
- class UserManager {
-   createUser() { /* ... */ }
-   updateUser() { /* ... */ }
-   deleteUser() { /* ... */ }
-   sendEmail() { /* ... */ }
-   generateReport() { /* ... */ }
-   handlePayment() { /* ... */ }
-   validateAddress() { /* ... */ }
-   // 50 more methods...
- }

# GOOD: Single responsibility per class
+ class UserService {
+   create(data) { /* ... */ }
+   update(id, data) { /* ... */ }
+   delete(id) { /* ... */ }
+ }
+
+ class EmailService {
+   send(to, subject, body) { /* ... */ }
+ }
+
+ class ReportService {
+   generate(type, params) { /* ... */ }
+ }
+
+ class PaymentService {
+   process(amount, method) { /* ... */ }
+ }
4. Long Parameter List
diff
# BAD: Too many parameters
- function createUser(email, password, name, age, address, city, country, phone) {
-   /* ... */
- }

# GOOD: Group related parameters
+ interface UserData {
+   email: string;
+   password: string;
+   name: string;
+   age?: number;
+   address?: Address;
+   phone?: string;
+ }
+
+ function createUser(data: UserData) {
+   /* ... */
+ }

# EVEN BETTER: Use builder pattern for complex construction
+ const user = UserBuilder
+   .email('test@example.com')
+   .password('secure123')
+   .name('Test User')
+   .address(address)
+   .build();
5. Feature Envy
diff
# BAD: Method that uses another object's data more than its own
- class Order {
-   calculateDiscount(user) {
-     if (user.membershipLevel === 'gold') {
+       return this.total * 0.2;
+     }
+     if (user.accountAge > 365) {
+       return this.total * 0.1;
+     }
+     return 0;
+   }
+ }

# GOOD: Move logic to the object that owns the data
+ class User {
+   getDiscountRate(orderTotal) {
+     if (this.membershipLevel === 'gold') return 0.2;
+     if (this.accountAge > 365) return 0.1;
+     return 0;
+   }
+ }
+
+ class Order {
+   calculateDiscount(user) {
+     return this.total * user.getDiscountRate(this.total);
+   }
+ }
6. Primitive Obsession
diff
# BAD: Using primitives for domain concepts
- function sendEmail(to, subject, body) { /* ... */ }
- sendEmail('user@example.com', 'Hello', '...');

- function createPhone(country, number) {
-   return `${country}-${number}`;
- }

# GOOD: Use domain types
+ class Email {
+   private constructor(public readonly value: string) {
+     if (!Email.isValid(value)) throw new Error('Invalid email');
+   }
+   static create(value: string) { return new Email(value); }
+   static isValid(email: string) { return /^[^\s@]+@[^\s@]+\.[^\s@]+$/.test(email); }
+ }
+
+ class PhoneNumber {
+   constructor(
+     public readonly country: string,
+     public readonly number: string
+   ) {
+     if (!PhoneNumber.isValid(country, number)) throw new Error('Invalid phone');
+   }
+   toString() { return `${this.country}-${this.number}`; }
+   static isValid(country: string, number: string) { /* ... */ }
+ }
+
+ // Usage
+ const email = Email.create('user@example.com');
+ const phone = new PhoneNumber('1', '555-1234');
7. Magic Numbers/Strings
diff
# BAD: Unexplained values
- if (user.status === 2) { /* ... */ }
- const discount = total * 0.15;
- setTimeout(callback, 86400000);

# GOOD: Named constants
+ const UserStatus = {
+   ACTIVE: 1,
+   INACTIVE: 2,
+   SUSPENDED: 3
+ } as const;
+
+ const DISCOUNT_RATES = {
+   STANDARD: 0.1,
+   PREMIUM: 0.15,
+   VIP: 0.2
+ } as const;
+
+ const ONE_DAY_MS = 24 * 60 * 60 * 1000;
+
+ if (user.status === UserStatus.INACTIVE) { /* ... */ }
+ const discount = total * DISCOUNT_RATES.PREMIUM;
+ setTimeout(callback, ONE_DAY_MS);
8. Nested Conditionals
diff
# BAD: Arrow code
- function process(order) {
-   if (order) {
-     if (order.user) {
-       if (order.user.isActive) {
-         if (order.total > 0) {
-           return processOrder(order);
+         } else {
+           return { error: 'Invalid total' };
+         }
+       } else {
+         return { error: 'User inactive' };
+       }
+     } else {
+       return { error: 'No user' };
+     }
+   } else {
+     return { error: 'No order' };
+   }
+ }

# GOOD: Guard clauses / early returns
+ function process(order) {
+   if (!order) return { error: 'No order' };
+   if (!order.user) return { error: 'No user' };
+   if (!order.user.isActive) return { error: 'User inactive' };
+   if (order.total <= 0) return { error: 'Invalid total' };
+   return processOrder(order);
+ }

# EVEN BETTER: Using Result type
+ function process(order): Result<ProcessedOrder, Error> {
+   return Result.combine([
+     validateOrderExists(order),
+     validateUserExists(order),
+     validateUserActive(order.user),
+     validateOrderTotal(order)
+   ]).flatMap(() => processOrder(order));
+ }
9. Dead Code
diff
# BAD: Unused code lingers
- function oldImplementation() { /* ... */ }
- const DEPRECATED_VALUE = 5;
- import { unusedThing } from './somewhere';
- // Commented out code
- // function oldCode() { /* ... */ }

# GOOD: Remove it
+ // Delete unused functions, imports, and commented code
+ // If you need it again, git history has it
10. Inappropriate Intimacy
diff
# BAD: One class reaches deep into another
- class OrderProcessor {
-   process(order) {
-     order.user.profile.address.street;  // Too intimate
-     order.repository.connection.config;  // Breaking encapsulation
+   }
+ }

# GOOD: Ask, don't tell
+ class OrderProcessor {
+   process(order) {
+     order.getShippingAddress();  // Order knows how to get it
+     order.save();  // Order knows how to save itself
+   }
+ }

Extract Method Refactoring

Before and After
diff
# Before: One long function
- function printReport(users) {
-   console.log('USER REPORT');
-   console.log('============');
-   console.log('');
-   console.log(`Total users: ${users.length}`);
-   console.log('');
-   console.log('ACTIVE USERS');
-   console.log('------------');
-   const active = users.filter(u => u.isActive);
-   active.forEach(u => {
-     console.log(`- ${u.name} (${u.email})`);
-   });
-   console.log('');
-   console.log(`Active: ${active.length}`);
-   console.log('');
-   console.log('INACTIVE USERS');
-   console.log('--------------');
-   const inactive = users.filter(u => !u.isActive);
-   inactive.forEach(u => {
-     console.log(`- ${u.name} (${u.email})`);
-   });
-   console.log('');
-   console.log(`Inactive: ${inactive.length}`);
- }

# After: Extracted methods
+ function printReport(users) {
+   printHeader('USER REPORT');
+   console.log(`Total users: ${users.length}\n`);
+   printUserSection('ACTIVE USERS', users.filter(u => u.isActive));
+   printUserSection('INACTIVE USERS', users.filter(u => !u.isActive));
+ }
+
+ function printHeader(title) {
+   const line = '='.repeat(title.length);
+   console.log(title);
+   console.log(line);
+   console.log('');
+ }
+
+ function printUserSection(title, users) {
+   console.log(title);
+   console.log('-'.repeat(title.length));
+   users.forEach(u => console.log(`- ${u.name} (${u.email})`));
+   console.log('');
+   console.log(`${title.split(' ')[0]}: ${users.length}`);
+   console.log('');
+ }

Introducing Type Safety

From Untyped to Typed
diff
# Before: No types
- function calculateDiscount(user, total, membership, date) {
-   if (membership === 'gold' && date.getDay() === 5) {
-     return total * 0.25;
-   }
-   if (membership === 'gold') return total * 0.2;
-   return total * 0.1;
- }

# After: Full type safety
+ type Membership = 'bronze' | 'silver' | 'gold';
+
+ interface User {
+   id: string;
+   name: string;
+   membership: Membership;
+ }
+
+ interface DiscountResult {
+   original: number;
+   discount: number;
+   final: number;
+   rate: number;
+ }
+
+ function calculateDiscount(
+   user: User,
+   total: number,
+   date: Date = new Date()
+ ): DiscountResult {
+   if (total < 0) throw new Error('Total cannot be negative');
+
+   let rate = 0.1; // Default bronze
+
+   if (user.membership === 'gold' && date.getDay() === 5) {
+     rate = 0.25; // Friday bonus for gold
+   } else if (user.membership === 'gold') {
+     rate = 0.2;
+   } else if (user.membership === 'silver') {
+     rate = 0.15;
+   }
+
+   const discount = total * rate;
+
+   return {
+     original: total,
+     discount,
+     final: total - discount,
+     rate
+   };
+ }

Design Patterns for Refactoring

Strategy Pattern
diff
# Before: Conditional logic
- function calculateShipping(order, method) {
-   if (method === 'standard') {
-     return order.total > 50 ? 0 : 5.99;
-   } else if (method === 'express') {
-     return order.total > 100 ? 9.99 : 14.99;
+   } else if (method === 'overnight') {
+     return 29.99;
+   }
+ }

# After: Strategy pattern
+ interface ShippingStrategy {
+   calculate(order: Order): number;
+ }
+
+ class StandardShipping implements ShippingStrategy {
+   calculate(order: Order) {
+     return order.total > 50 ? 0 : 5.99;
+   }
+ }
+
+ class ExpressShipping implements ShippingStrategy {
+   calculate(order: Order) {
+     return order.total > 100 ? 9.99 : 14.99;
+   }
+ }
+
+ class OvernightShipping implements ShippingStrategy {
+   calculate(order: Order) {
+     return 29.99;
+   }
+ }
+
+ function calculateShipping(order: Order, strategy: ShippingStrategy) {
+   return strategy.calculate(order);
+ }
Chain of Responsibility
diff
# Before: Nested validation
- function validate(user) {
-   const errors = [];
-   if (!user.email) errors.push('Email required');
+   else if (!isValidEmail(user.email)) errors.push('Invalid email');
+   if (!user.name) errors.push('Name required');
+   if (user.age < 18) errors.push('Must be 18+');
+   if (user.country === 'blocked') errors.push('Country not supported');
+   return errors;
+ }

# After: Chain of responsibility
+ abstract class Validator {
+   abstract validate(user: User): string | null;
+   setNext(validator: Validator): Validator {
+     this.next = validator;
+     return validator;
+   }
+   validate(user: User): string | null {
+     const error = this.doValidate(user);
+     if (error) return error;
+     return this.next?.validate(user) ?? null;
+   }
+ }
+
+ class EmailRequiredValidator extends Validator {
+   doValidate(user: User) {
+     return !user.email ? 'Email required' : null;
+   }
+ }
+
+ class EmailFormatValidator extends Validator {
+   doValidate(user: User) {
+     return user.email && !isValidEmail(user.email) ? 'Invalid email' : null;
+   }
+ }
+
+ // Build the chain
+ const validator = new EmailRequiredValidator()
+   .setNext(new EmailFormatValidator())
+   .setNext(new NameRequiredValidator())
+   .setNext(new AgeValidator())
+   .setNext(new CountryValidator());

Refactoring Steps

Safe Refactoring Process
1. PREPARE
   - Ensure tests exist (write them if missing)
   - Commit current state
   - Create feature branch

2. IDENTIFY
   - Find the code smell to address
   - Understand what the code does
   - Plan the refactoring

3. REFACTOR (small steps)
   - Make one small change
   - Run tests
   - Commit if tests pass
   - Repeat

4. VERIFY
   - All tests pass
   - Manual testing if needed
   - Performance unchanged or improved

5. CLEAN UP
   - Update comments
   - Update documentation
   - Final commit

Refactoring Checklist

Code Quality
  • Functions are small (< 50 lines)
  • Functions do one thing
  • No duplicated code
  • Descriptive names (variables, functions, classes)
  • No magic numbers/strings
  • Dead code removed
Structure
  • Related code is together
  • Clear module boundaries
  • Dependencies flow in one direction
  • No circular dependencies
Show full SKILL.md (147 more words)Show less
Type Safety
  • Types defined for all public APIs
  • No any types without justification
  • Nullable types explicitly marked
Testing
  • Refactored code is tested
  • Tests cover edge cases
  • All tests pass

Common Refactoring Operations

OperationDescription
Extract MethodTurn code fragment into method
Extract ClassMove behavior to new class
Extract InterfaceCreate interface from implementation
Inline MethodMove method body back to caller
Inline ClassMove class behavior to caller
Pull Up MethodMove method to superclass
Push Down MethodMove method to subclass
Rename Method/VariableImprove clarity
Introduce Parameter ObjectGroup related parameters
Replace Conditional with PolymorphismUse polymorphism instead of switch/if
Replace Magic Number with ConstantNamed constants
Decompose ConditionalBreak complex conditions
Consolidate ConditionalCombine duplicate conditions
Replace Nested Conditional with Guard ClausesEarly returns
Introduce Null ObjectEliminate null checks
Replace Type Code with Class/EnumStrong typing
Replace Inheritance with DelegationComposition over inheritance

© github, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/refactor of github/awesome-copilot.

Open the folder on GitHubat commit 7cce7cf

Used in 6 other repositories

We found 6 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in github/awesome-copilot, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Refactor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Refactor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Refactor this skillgithub/awesome-copilot40k6 repos~4.2kAutomated safety check: PassMIT
Guidelinesakash-network/node1.1k22 repos~577Automated safety check: PassMIT
Component Refactoringlangflow-ai/langflow156k—~3.5kAutomated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Systematic Code Refactoringluongnv89/claude-howto42k—~3kAutomated safety check: PassMIT
Codexskills-directory/skill-codex1.5k3 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 22 repos~577 tokens
    DevelopmentAuto-check passed
  • Component Refactoring

    langflow-ai/langflow

    Refactor high-complexity React components in Langflow frontend.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Codex

    skills-directory/skill-codex

    A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

    1.5k GitHub starsUsed in 3 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed

More from github/awesome-copilot

All 417 skills in this repo
  • Acquire Codebase Knowledge

    github/awesome-copilot

    Official

    Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups.

    40k GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed
  • Azure Architecture Autopilot

    github/awesome-copilot

    Official

    Designs Azure infrastructure from a natural-language description, or diagrams an existing resource group, then refines the design through conversation and deploys it with Bicep.

    40k GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Draw.io Diagram Generator

    github/awesome-copilot

    Official

    Generates, edits and validates draw.io files with correct mxGraph XML, covering flowcharts, architecture, sequence, ER and UML class diagrams.

    40k GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check passed
  • Credit Risk Data Cleaning

    github/awesome-copilot

    Official

    Cleans raw credit data and screens variables before loan modeling, dropping unstable, noisy or redundant features and writing an Excel report of every step.

    40k GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Daily Focus Board

    github/awesome-copilot

    Official

    Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover.

    40k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Python Pypi Package Builder

    github/awesome-copilot

    Official

    End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI.

    40k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Categories

Questions about Refactor

What does Refactor do?

Surgical code refactoring to improve maintainability without changing behavior. Refactor is an agent skill from github/awesome-copilot, published by the product's own GitHub organization. Surgical code refactoring to improve maintainability without changing behavior.

When should I use Refactor?

Refactor fits situations like: gradual improvements; tasks that involve Refactoring.

How do I install Refactor in Claude Code?

Run `npx skills add github/awesome-copilot --skill refactor -a claude-code`. Or copy the skill folder (skills/refactor in github/awesome-copilot) into .claude/skills/refactor in your project. Claude Code loads it when a task matches its description.

How do I install Refactor in Codex?

Run `npx skills add github/awesome-copilot --skill refactor -a codex`. Or copy the skill folder (skills/refactor in github/awesome-copilot) into .agents/skills/refactor in your project. Codex loads it when a task matches its description.

Can I use Refactor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add github/awesome-copilot --skill refactor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refactor, .gemini/skills/refactor, .github/skills/refactor and .opencode/skills/refactor in your project.

What does Refactor need to run?

SKILL.md names no scripts, command-line tools or credentials: Refactor is instructions for the agent only.

Does Refactor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Refactor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Refactor use?

Refactor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Refactor use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Refactor?

Skills that share tags, products or a category with Refactor: Guidelines (akash-network/node, 1.1k stars), Component Refactoring (langflow-ai/langflow, 156k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars) and Systematic Code Refactoring (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refactor?

github (a GitHub organization, an official publisher) maintains it in github/awesome-copilot, which has 39,792 GitHub stars. The repository holds 417 skills in this directory. The repository was last updated on October 8, 2026.

Source: github/awesome-copilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.