Refactoring logo

Refactoring

Community
andreaswasita
refactoring

Safe, test-backed code restructuring in small steps.

Overview

Publisherandreaswasita
Repositorycopilot-agents-dojo
Skill namerefactoring
Stars
54
Forks
15
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by andreaswasita on GitHub. Read the source before you install it.

Installation

Install the Refactoring AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/andreaswasita/copilot-agents-dojo/tree/main/skills/refactoring
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo.git /tmp/copilot-agents-dojo
mkdir -p .claude/skills
cp -r /tmp/copilot-agents-dojo/skills/refactoring .claude/skills/refactoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Refactoring in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Refactoring on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Refactoring is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Refactoring Skill

Restructures existing code without changing behavior, in small atomic steps each backed by a green test suite. Does NOT add features in the same change — refactoring and feature work travel in separate PRs.

When to Use

  • A function, class, or file has grown unmanageable.
  • Duplication is spreading across modules.
  • The demand-elegance skill flagged a hacky solution.
  • Names no longer reflect purpose after a domain shift.
  • Before adding a new feature into a messy area.
  • NOT when there is no test coverage and the change is high-risk — write tests first.

Prerequisites

  • Working test suite (or willingness to write characterization tests first).
  • git for atomic commits per transformation.
  • The view, edit, grep, and glob Copilot tools.
  • A baseline run of the test suite passing (proven, not assumed).

How to Run

text
1. Run the full test suite. Confirm green baseline.
2. If no tests cover the target, write characterization tests; commit separately.
3. Apply one named transformation.
4. Re-run tests. If red, revert.
5. Commit. Repeat for next transformation.
6. Final pass: full suite + review of the whole diff.

Quick Reference

SmellRefactoring
Long function (>30 lines)Extract smaller, named functions
Duplicate codeExtract shared function or module
Deep nesting (>3 levels)Early returns, extract conditions
God class / fileSplit by responsibility
Primitive obsessionIntroduce domain types
Feature envyMove logic to the class that owns the data
Long parameter list (>4)Introduce parameter object
Dead codeDelete it — version control remembers

Procedure

Step 1: Establish the Safety Net

Identify tests covering the target with grep / glob. Run them via the powershell tool. If they fail or do not exist, write characterization tests first and commit them in a separate commit before any refactor.

Step 2: Name the Transformation

Each step in the refactor must have a name from the rubric above ("extract method", "introduce parameter object", "rename for clarity"). If you cannot name it, you are freelancing — stop.

Step 3: One Transformation, One Commit

For each step:

  1. Apply the change with the edit tool.
  2. Run the full test suite.
  3. If red, revert immediately.
  4. If green, commit with message refactor: <named transformation>.
text
refactor: extract validateInput() from handleRequest()
refactor: rename UserManager to UserRepository
refactor: move email logic to NotificationService
refactor: delete unused formatLegacyDate()

Step 4: Verify the Whole

Run the full suite a final time. Review the cumulative diff (git diff main). Ask: is the result actually clearer, or just rearranged? If not clearer, revert.

Pitfalls

  • DO NOT refactor without a green test baseline. You are gambling, not refactoring.
  • DO NOT mix refactor and feature work in one PR. Reviewers cannot tell signal from noise.
  • DO NOT rename a symbol without searching every reference first (grep on the symbol).
  • DO NOT rewrite for a hypothetical future ("we might need this pluggable"). Refactor for today.
  • DO NOT big-bang refactor across the whole repo in one commit — small atomic steps, always.

Verification

  • Test suite is green before the first transformation.
  • Test suite is green after every commit.
  • Each commit is named refactor: <transformation>.
  • No public API changed (or, if it did, callers were updated in the same PR).
  • Final diff is meaningfully clearer than the starting code.

Frequently asked questions

What does the Refactoring AI skill do?

Safe, test-backed code restructuring in small steps.

Why use Refactoring on TypingMind?

Because you install it once and use it with any model. Refactoring is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Refactoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/andreaswasita/copilot-agents-dojo/tree/main/skills/refactoring. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Refactoring?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Refactoring?

As many as you like. As long as a model supports skills, you can use Refactoring with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Refactoring AI skill free?

Yes. It is published on GitHub by andreaswasita under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇