refactor
Executes automated refactoring for specific files, directories, or semantic queries. This skill should be used when the user asks to refactor specific files or directories, simplify recently changed code, clean up dead code in a limited scope, or invokes "/refactor".
Best use case
refactor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Executes automated refactoring for specific files, directories, or semantic queries. This skill should be used when the user asks to refactor specific files or directories, simplify recently changed code, clean up dead code in a limited scope, or invokes "/refactor".
Teams using refactor should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/refactor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How refactor Compares
| Feature / Agent | refactor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Executes automated refactoring for specific files, directories, or semantic queries. This skill should be used when the user asks to refactor specific files or directories, simplify recently changed code, clean up dead code in a limited scope, or invokes "/refactor".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Refactor Command Execute automated refactoring for $ARGUMENTS using `refactor:code-simplifier` agent. ## Pre-operation Checks **Goal**: Ensure scope resolution is deterministic before launching the agent. **Actions**: 1. Run `git rev-parse --is-inside-work-tree` and continue even if false when explicit paths are provided 2. Normalize arguments by trimming whitespace and preserving quoted path segments 3. Treat an empty argument list as "recent changes" mode ## Phase 1: Determine Target Scope **Goal**: Identify files to refactor based on arguments or session context. **Actions**: 1. If arguments provided: verify as file/directory paths using Glob 2. If paths exist: use them directly as refactoring scope 3. If paths don't exist: treat arguments as semantic query, search codebase with Grep 4. If no arguments: run `git diff --name-only` to find recently modified code files 5. If no recent changes found: inform user and exit without refactoring See `references/scope-determination.md` for search strategies and edge cases. ## Phase 2: Launch Refactoring Agent **Goal**: Execute `refactor:code-simplifier` agent with aggressive mode enabled. **Actions**: 1. Launch `refactor:code-simplifier` agent with target scope and aggressive mode flag 2. Pass scope determination method (paths, semantic query, or session context) 3. Agent auto-loads `refactor:best-practices` skill and applies language-specific patterns See `references/agent-configuration.md` for detailed Task parameters. ## Phase 3: Summary **Goal**: Report comprehensive summary of changes. **Actions**: 1. Report total files refactored and changes categorized by improvement type 2. List best practices applied and legacy code removed 3. Suggest tests to run and provide rollback command tailored to actual scope (for example: `git restore --worktree --staged <files>`) See `references/output-requirements.md` for detailed summary format. ## Requirements - Execute immediately without user confirmation - Refactor ALL matching files when semantic search returns multiple results - Direct users to `/refactor-project` for project-wide scope - Preserve behavior and public interfaces unless user explicitly requests a behavior change
Related Skills
refactor-project
Executes automated project-wide refactoring with a focus on cross-file optimization. This skill should be used when the user asks for project-wide refactoring, cross-file simplification, consistency standardization across the codebase, duplication reduction, or invokes "/refactor-project".
update-readme
Updates README.md and README.zh-CN.md to reflect the project's current state. Use this skill whenever the user asks to "update the README", "sync the docs", "update documentation", "reflect latest changes in README", or wants both the English and Chinese READMEs to match the current project. Always triggers when the user mentions updating or regenerating README files, especially for bilingual (EN/ZH) projects.
swiftui-review
Reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. This skill should be used when the user asks to review SwiftUI code, check for deprecated iOS/macOS APIs, validate data flow patterns, or audit accessibility compliance in Swift projects.
writing-plans
Creates executable implementation plans that break down designs into detailed tasks. This skill should be used when the user has completed a brainstorming design and asks to "write an implementation plan" or "create step-by-step tasks" for execution.
systematic-debugging
Provides a systematic debugging methodology with a 4-phase root cause analysis process. This skill should be used when the user reports a bug, error, test failure, or unexpected behavior, ensuring thorough investigation precedes any code changes.
need-vet
This skill should be used when the user invokes /need-vet to enable work verification for the current task. Claude must verify completion and append the verified tag before the session can end.
executing-plans
Executes written implementation plans efficiently using agent teams or subagents. This skill should be used when the user has a completed plan.md, asks to "execute the plan", or is ready to run batches of independent tasks in parallel following BDD principles.
build-like-iphone-team
Applies Apple's Project Purple design philosophy for radical innovation. This skill should be used when the user wants to challenge industry conventions, approach open-ended problems requiring disruptive thinking, or when standard brainstorming needs a breakthrough approach.
brainstorming
Structures collaborative dialogue to turn rough ideas into implementation-ready designs. This skill should be used when the user has a new idea, feature request, ambiguous requirement, or asks to "brainstorm a solution" before implementation begins.
behavior-driven-development
Applies behavior-driven development principles including Gherkin scenarios and test-driven development. This skill should be used when the user asks to implement features, fix bugs, or when writing executable specifications and tests before writing production code.
agent-team-driven-development
Provides guidance on coordinating multiple specialized teammates working in parallel. This skill should be used when the user needs to execute complex implementation plans, resolve cross-cutting concerns, or coordinate independent work streams requiring communication.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".