De Sloppify logo

De Sloppify

Organization
codewithmukesh
de-sloppify

Systematic code cleanup pipeline for .NET projects. Runs 7 ordered steps: formatting, unused usings, analyzer warnings, dead code removal, TODO resolution, sealed class audit, and CancellationToken propagation. Each step is verified independently with tests between phases. Load this skill when: "clean up", "de-sloppify", "tidy up", "remove dead code", "code cleanup", "housekeeping", "tech debt", "fix warnings", "seal classes", "add CancellationToken", "unused usings", "format code".

Overview

Publishercodewithmukesh
Repositorydotnet-claude-kit
Skill namede-sloppify
Stars
721
Forks
170
Bundled files
1
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.

  • 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 codewithmukesh on GitHub. Read the source before you install it.

Installation

Install the De Sloppify 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.
  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/codewithmukesh/dotnet-claude-kit.git /tmp/dotnet-claude-kit
mkdir -p .claude/skills
cp -r /tmp/dotnet-claude-kit/skills/de-sloppify .claude/skills/de-sloppify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable De Sloppify 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 De Sloppify 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 De Sloppify 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.

/de-sloppify — 7-Step Cleanup Pipeline

What

Runs an ordered, verified cleanup pipeline over a .NET codebase. Order matters: formatting first (it touches every file — get the churn out of the way before anything else), dead code late (earlier steps reveal it). Random cleanup misses things and creates merge conflicts; the pipeline doesn't.

Three rules make it safe:

  1. Verify after each stepdotnet build + dotnet test between steps. A cleanup that breaks something is worse than the mess it was fixing.
  2. Commit per step — each step is its own commit, so a bad Step 4 reverts without losing Steps 1-3.
  3. Safe removals only — before deleting "dead" code, check for reflection, DI-convention, and serialization usage that Roslyn cannot see.

Per-step commands, safety checklists, and code examples live in references/cleanup-steps.md — read it before executing.

When

  • "Clean up", "tidy up", "de-sloppify", "housekeeping", "tech debt"
  • After a large feature merge or dependency upgrade (new warnings accumulate)
  • Pre-release hardening, or a scheduled quarterly cleanup sprint
  • Before performance work (dead code out, classes sealed for devirtualization)
  • Never mixed with feature work — cleanup commits stay pure

How

Step 0: Pick the Steps

ScenarioSteps to run
Full cleanup pass / pre-release / quarterlyAll 7
Quick tidy before PR1, 2, 6
After large feature merge1, 2, 3, 4
After dependency upgrade2, 3
Before performance work4, 6
CI warning threshold exceeded3 only
Tech debt sprint4, 5

Steps 1-7 (execute in order, details in references/cleanup-steps.md)

#StepToolCommit message
1Format all codedotnet formatchore: apply dotnet format
2Remove unused usingsdotnet format analyzers --diagnostics IDE0005chore: remove unused using statements
3Fix analyzer warningsMCP get_diagnostics → triage by categorychore: fix analyzer warnings
4Remove dead codeMCP find_dead_code + safety check (reflection/DI/serialization grep)chore: remove dead code
5Resolve TODOsgrep TODO/HACK/FIXME → fix, file issue, or deletechore: resolve TODO comments
6Seal non-inherited classesMCP get_type_hierarchy per candidate + test-project grepchore: seal non-inherited classes
7Propagate CancellationTokenMCP detect_antipatterns → trace async chainschore: propagate CancellationToken through async chains

After every step: dotnet build + dotnet test, then commit. If a step breaks the build or tests, fix or revert that step before continuing — never carry a red state into the next step. Delegate structural steps (4, 6, 7) to the refactor-cleaner agent.

Final Report

markdown
## De-Sloppify Report

| Step | Changes | Files Affected |
|------|---------|----------------|
| 1. Format | Applied consistent formatting | 23 files |
| 2. Usings | Removed 47 unused usings | 18 files |
| 3. Analyzers | Fixed 12 warnings (8 nullability, 3 unused vars, 1 obsolete) | 9 files |
| 4. Dead Code | Removed 3 unused types, 5 unused methods | 6 files |
| 5. TODOs | Fixed 2, created issues for 3, removed 1 stale | 5 files |
| 6. Sealed | Sealed 14 classes | 14 files |
| 7. CancellationToken | Added propagation to 8 async chains | 11 files |

**Total: 7 commits, 86 files improved**

Example

User: /de-sloppify — full pass before the release

Claude: Running the 7-step pipeline...

Step 1: dotnet format — 23 files reformatted. Build + tests green. Committed.
Step 2: IDE0005 — 47 unused usings removed across 18 files. Green. Committed.
Step 3: 12 warnings triaged: 8 nullability fixed with null checks,
  3 unused vars removed, 1 CS0618 migrated off the obsolete API. Committed.
Step 4: find_dead_code → 9 candidates. Safety check: PaymentProcessor is
  registered via DI convention — kept. Removed 3 types, 5 methods. Committed.
Step 5: 6 TODOs → 2 fixed, 3 became issues (#141-#143), 1 stale removed. Committed.
Step 6: 14 classes sealed (2 skipped: xUnit fixture base, virtual members). Committed.
Step 7: 8 async chains now propagate ct end-to-end. Committed.

7 commits, 86 files improved. Full report above.

Related

  • references/cleanup-steps.md — per-step commands, safety checks, examples
  • /verify — run the full verification pipeline after cleanup
  • /health-check — re-grade the project to quantify the improvement
  • /code-review — cleanup handles style; review handles logic and design

Bundled files

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

Frequently asked questions

What does the De Sloppify AI skill do?

Systematic code cleanup pipeline for .NET projects. Runs 7 ordered steps: formatting, unused usings, analyzer warnings, dead code removal, TODO resolution, sealed class audit, and CancellationToken propagation. Each step is verified independently with tests between phases. Load this skill when: "clean up", "de-sloppify", "tidy up", "remove dead code", "code cleanup", "housekeeping", "tech debt", "fix warnings", "seal classes", "add CancellationToken", "unused usings", "format code".

Why use De Sloppify on TypingMind?

Because you install it once and use it with any model. De Sloppify 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 De Sloppify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/codewithmukesh/dotnet-claude-kit/tree/main/skills/de-sloppify. 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 De Sloppify?

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 De Sloppify?

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

Is the De Sloppify AI skill free?

Yes. It is published on GitHub by codewithmukesh 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 👇