♻️
QualityTypeScript

Refactor

by first-fluke

Refactor is a Quality skill for Claude Code, published by first-fluke in oh-my-agent.

1.2K stars145 forkson first-fluke/oh-my-agentAdded 2026/08/20Repository updated 2026/08/20
View source on GitHubDownload repo ZIP
agent-harnessagent-skillsagentic-codingai-agentsclaude-codeclicodexcursordeveloper-toolsllmmulti-agentmulti-agent-systemsoh-my-agentopencodeorchestrationorchestratorserena
Install in seconds
Install Refactor
Copy Refactor into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/first-fluke/oh-my-agent/tree/main/skills/oma-refactor ~/.claude/skills/oma-refactor

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/first-fluke/oh-my-agent.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/oma-refactor/SKILL.md in first-fluke/oh-my-agent
Installs to
~/.claude/skills/oma-refactor
Collection
One of 25 skills cataloged from this repository
Category
Quality — 1354 skills

What Refactor does

Refactor plans and executes behavior-preserving restructuring through small, test-gated transformations. Use it when cleaning up legacy code, reducing complexity, or preparing a codebase for a feature.

Refactor is cataloged under Quality on DirSkills. Refactor comes from a repository tagged agent-harness, agent-skills, agentic-coding, ai-agents and claude-code.

Documentation

README

Refactor Agent - Behavior-Preserving Restructuring Specialist

Scheduling

Goal

Improve internal code structure - readability first - without changing observable behavior, through small verified transformations, each gated by a safety net (tests / tooling / types) and committed separately from any behavior change.

Intent signature

  • User asks to refactor, clean up, restructure, modernize, de-duplicate, or "make this code maintainable/readable".
  • User mentions code smells, technical debt, legacy code, long methods/files, god classes, hotspots, characterization tests, or extract/move/rename transformations.
  • User asks "where should we refactor first?" or wants a refactoring plan/priority for a codebase.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Refactor

  • What else does first-fluke publish alongside Refactor?

    Refactor is one of 25 skills that DirSkills catalogs from first-fluke/oh-my-agent, the repository it ships in. Its siblings there include AI Conversation Recap, Academic Writer and Architecture Agent. Each one is a separate skill with its own page in this directory, installs the same way Refactor does, and is maintained by first-fluke in that same repository. The rest of the collection is listed on the first-fluke/oh-my-agent page.

  • How does Refactor compare to other Quality skills?

    Refactor ranks #735 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Refactor against them. Open each page to compare what they document and how they install.

More from first-fluke/oh-my-agent

Refactor is one of 25 skills cataloged on DirSkills from first-fluke/oh-my-agent.

See all 25 skills →
📊
2w ago

AI Conversation Recap

AI Conversation Recap analyzes conversation histories from multiple AI tools for a date range and generates themed, project-oriented work summaries in Markdown. Use it for daily standups, weekly retros, or understanding tool-switching patterns.
Data
1.2K145
✍️
2w ago

Academic Writer

Academic Writer drafts, revises, and audits publication-grade academic English prose, enforcing sentence structure, verb, hedging, and anti-AI protocols with claims mapped to evidence. Use it for academic reports, essays, conclusions, literature reviews, or polishing AI-sounding drafts.
Writing
1.2K145
🏗️
2w ago

Architecture Agent

Architecture Agent analyzes software architecture choices, boundaries, and tradeoffs, then documents recommendations or ADRs. Use it when comparing designs, reviewing risks, or planning API and module evolution.
AI Engineering
1.2K145
⚙️
2w ago

Backend Agent

Backend Agent implements or reviews backend APIs, authentication, database integration, server-side business logic, and migrations using the project's existing backend stack and clean architecture boundaries.
DevOps
1.2K145
💡
2w ago

Brainstorm

Brainstorm explores user intent, constraints, and alternative approaches before planning or implementation, then preserves an approved design for downstream planning. Use it when an idea is ambiguous or needs design-first ideation.
AI Engineering
1.2K145
🗄️
2w ago

Database Architect

Database Architect designs, reviews, and optimizes SQL, NoSQL, and vector database schemas, models, and retrieval systems. Use it for entity-relationship design, indexing, transactions, capacity planning, and RAG vector database configuration.
Data
1.2K145

More Quality skills

Refactor is one of 1354 Quality skills cataloged on DirSkills, ranked #735 by stars among them.

Browse all Quality skills →
⏱️
3w ago

Benchmark

Benchmark measures performance baselines, detects regressions before and after PRs, and compares stack alternatives for pages, APIs, and builds.
Quality
239.8K36.4K
⏱️
3w ago

Benchmark Optimization Loop

Benchmark Optimization Loop turns vague performance goals into a bounded, measured optimization process. Use it when asked to make something faster, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
Quality
239.8K36.4K
🔌
3w ago

API Design Patterns

API Design Patterns provides conventions and best practices for designing consistent REST APIs. Use it when creating endpoints, reviewing contracts, handling pagination, error responses, status codes, filtering, or versioning.
Quality
239.8K36.4K