Add Refactoring

OrganizationPopular

dotnet

add-refactoring

Use when adding a new RR#### refactoring in roslynator, editing Refactorings.xml, registering in RefactoringContext, or when refactorings-testing.md shows XunitRefactoringVerifier — in-repo uses AbstractCSharpRefactoringVerifier and CHANGELOG.md.

Overview

Publisher	dotnet
Repository	`roslynator`
Skill name	`add-refactoring`
Stars	3.5K
Forks	297
Bundled files	1
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by dotnet on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/dotnet/roslynator/tree/main/.claude/skills/add-refactoring
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.

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/dotnet/roslynator.git /tmp/roslynator
mkdir -p .claude/skills
cp -r /tmp/roslynator/.claude/skills/add-refactoring .claude/skills/add-refactoring

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add 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 Add 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 Add 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.

Add Refactoring

Overview

Refactorings are metadata-driven: Refactorings.xml → codegen → register in RefactoringContext → implement → test → changelog.

When to Use

New RR#### refactoring in an approved issue
Registering a refactoring action on a syntax kind
<OptionKey> required on every refactoring entry

Not for: analyzers (add-analyzer), compiler fixes (add-compiler-diagnostic-fix), deprecation (deprecate-analyzer-or-refactoring).

Gate: approved GitHub issue (CONTRIBUTING.md).

Read references/implementation.md before writing tests — public refactorings-testing.md uses XunitRefactoringVerifier, which does not match in-repo tests.

Confirm metadata parameters (hard gate)

STOP. Do NOT edit Refactorings.xml, run codegen, or implement until the user has confirmed every required parameter below. Do not invent values the user (or issue) did not state.

Use AskQuestion when available; otherwise ask conversationally. Batch related choices.

Parameter	Required?	Notes
`Id`	propose	Compute next free `RR####` from `Refactorings.xml`; do not ask unless the issue conflicts or multiple ids are plausible
`Identifier`	yes	PascalCase; drives generated names
`Title`	yes	Short description (light-bulb text)
`OptionKey`	yes	EditorConfig key segment → `roslynator_refactoring.<key>.enabled`
`Syntaxes` / `Span`	yes for docs	Where it can be invoked (documentation only; registration is in code)
`Summary` / samples	recommended	Confirm if not in the issue

When proposing Id, state the chosen value in your plan/summary (e.g. “using next free RR0218”). Skip asking other parameters only when the approved issue or the user's message already states the value explicitly.

Quick Reference

Step	Location / command
Metadata	`src/Refactorings.xml`
Codegen	`cd tools && pwsh ./generate_code.ps1`
Register	`RefactoringContext.cs` or helper under `Refactorings/CSharp/Refactorings/`
Implement	same folder
Tests	`src/Tests/Refactorings.Tests/RR####IdentifierTests.cs`
Changelog	`CHANGELOG.md` under `## [Unreleased]`

Implementation

Confirm metadata parameters (hard gate above).
Details and examples: references/implementation.md.

Changelog:

markdown
- Add refactoring "TITLE" ([RR####](https://josefpihrt.github.io/docs/roslynator/refactorings/RR####)) ([#PR](https://github.com/dotnet/roslynator/pull/PR))

Verify:

bash
cd tools && pwsh ./generate_code.ps1
cd src && dotnet build Roslynator.sln
cd src && dotnet test Tests/Refactorings.Tests --no-build --filter "FullyQualifiedName~RR####"
cd src && dotnet format Roslynator.sln --no-restore --verify-no-changes --severity info

Common Mistakes

Mistake	Fix
Guess `Title` / `OptionKey` / `Identifier`	Ask — hard gate above
Follow `refactorings-testing.md` verbatim	In-repo: `AbstractCSharpRefactoringVerifier` + `RefactoringId` override
Missing `<OptionKey>`	Required — EditorConfig id for enable/disable
Codegen from repo root	`cd tools && pwsh ./generate_code.ps1`
`[	...
Only `<Syntaxes>` / `<Span>`	Documentation-only; registration is in code

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/implementation.md2 KB

Frequently asked questions

What does the Add Refactoring AI skill do?

Why use Add Refactoring on TypingMind?

Because you install it once and use it with any model. Add 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 Add Refactoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dotnet/roslynator/tree/main/.claude/skills/add-refactoring. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Add 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 Add Refactoring?

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

Is the Add Refactoring AI skill free?

It is published on GitHub by dotnet. Check the repository for licensing terms. 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

Graincrawl

openclaw

OrganizationPopular

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Add Refactoring

Overview

When to Use

Confirm metadata parameters (hard gate)

Quick Reference

Implementation

Common Mistakes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now