Dotnet Init logo

Dotnet Init

Organization
codewithmukesh
dotnet-init

Interactive project initialization. Detects project type, asks architecture questions, and generates a customized CLAUDE.md — no manual template copying. Use when: "init project", "setup project", "initialize", "new project setup", "generate CLAUDE.md", "configure for dotnet-claude-kit", or starting Claude Code on a fresh or existing .NET codebase.

Overview

Publishercodewithmukesh
Repositorydotnet-claude-kit
Skill namedotnet-init
Stars
721
Forks
170
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 codewithmukesh on GitHub. Read the source before you install it.

Installation

Install the Dotnet Init 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/dotnet-init .claude/skills/dotnet-init
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dotnet Init 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 Dotnet Init 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 Dotnet Init 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.

/dotnet-init

What

Interactively initializes a .NET project for use with dotnet-claude-kit. Detects the project type, asks targeted questions about architecture and tech stack, then generates a fully customized CLAUDE.md in the project root.

No manual template copying required.

When

  • Starting a new .NET project with Claude Code
  • Adding dotnet-claude-kit to an existing project
  • "init project", "setup project", "generate CLAUDE.md", "configure for dotnet-claude-kit"

How

Step 1: Detect or Ask Project Type

Analyze the current directory to determine if this is an existing or greenfield project:

→ Look for .slnx / .sln files
→ If found, scan .csproj files for SDK type:
  - Microsoft.NET.Sdk.Web → web-api or blazor-app
  - Microsoft.NET.Sdk.Worker → worker-service
  - Microsoft.NET.Sdk → class-library
  - Multiple projects with inter-module references → modular-monolith
  - If ambiguous, ask the user

→ If NO solution/project found (greenfield):
  - Ask: "What are you building?"
    - REST API / microservice → web-api
    - Blazor application → blazor-app
    - Background worker / queue processor → worker-service
    - NuGet package / shared library → class-library
    - Multi-module system → modular-monolith
  - Ask: "Project name?"
  - Scaffold the solution structure:
    - dotnet new sln -n ProjectName --format slnx   (modern XML solution format)
    - dotnet new webapi / worker / classlib as appropriate
    - Set up Directory.Build.props with .NET 10 defaults
    - Create src/ and tests/ folder structure

Step 2: Architecture Questionnaire

Load the architecture-advisor skill and ask targeted questions:

  1. Domain complexity — CRUD-heavy, moderate business rules, or rich domain?
  2. Team size — Solo, small team, or large team?
  3. Module boundaries — Single deployable or multiple bounded contexts?
  4. Existing patterns — (existing projects only) Detect conventions via convention-learner skill

→ Recommend: VSA, Clean Architecture, DDD, or Modular Monolith with rationale.

Step 3: Tech Stack Selection

Ask about specific technology choices:

  • Database: PostgreSQL, SQL Server, SQLite, or none yet
  • Auth: JWT, OIDC, Cookie, or none yet
  • Caching: HybridCache, Redis, or none yet
  • Messaging: Wolverine, MassTransit, or none yet
  • Testing: Confirm xUnit + Testcontainers defaults

Step 4: Generate CLAUDE.md

Load the appropriate template from templates/ as a base, then customize:

  • Replace [ProjectName] with the actual project/solution name
  • Set the chosen architecture
  • Configure the tech stack section
  • For existing projects: add project-specific conventions detected in Step 2
  • For greenfield: add recommended conventions based on architecture choice

Before writing, check for an existing CLAUDE.md. Never overwrite it silently.

→ If ./CLAUDE.md does NOT exist:
  - Write the generated content to ./CLAUDE.md

→ If ./CLAUDE.md ALREADY exists:
  - Read it and identify hand-written / custom sections
    (anything not produced by a kit template)
  - Ask: "You already have a CLAUDE.md. How should I proceed?"
    - Merge (recommended) → keep the user's custom sections, add or refresh the
      kit's architecture, tech-stack, and convention sections in place
    - Overwrite → replace it entirely with the freshly generated file
    - Keep → leave the file untouched and print the generated content so the
      user can copy what they want by hand
  - For Merge and Overwrite: back the original up to ./CLAUDE.md.bak first.
    Never discard user content without a .bak backup.

Step 5: Verify Setup

→ Confirm .mcp.json exists or create it (for Roslyn MCP server)
→ For existing projects:
  - Verify the solution file is discoverable
  - Run a quick health check to establish baseline
  - Report: "Project initialized. Run /health-check to see your baseline."
→ For greenfield projects:
  - Verify dotnet build succeeds on the scaffolded solution
  - Report: "Project created. Run /scaffold to add your first feature."

Skills invoked: project-setup, architecture-advisor, convention-learner Agent: dotnet-architect

Example — Existing Project

User: /dotnet-init

Claude: Detected:
  - Solution: MyApp.slnx (3 projects)
  - SDK: Microsoft.NET.Sdk.Web → Web API
  - Database: PostgreSQL (from connection string)
  - Auth: JWT (from appsettings)

  1. Domain complexity? [CRUD-heavy / Moderate / Rich domain]
  > Moderate

  2. Team size? [Solo / Small / Large]
  > Small

  Recommendation: Vertical Slice Architecture
  Generated: ./CLAUDE.md (MyApp + VSA + PostgreSQL + JWT)
  Run /health-check to see your baseline.

Example — Greenfield Project

User: /dotnet-init

Claude: No .sln or .csproj found. Let's set up a new project.

  1. What are you building? [REST API / Blazor / Worker / Library / Modular Monolith]
  > REST API

  2. Project name?
  > OrderService

  3. Domain complexity? [CRUD-heavy / Moderate / Rich domain]
  > CRUD-heavy

  Recommendation: Vertical Slice Architecture

  Creating solution...
  → dotnet new sln -n OrderService --format slnx
  → dotnet new webapi -n OrderService.Api -o src/OrderService.Api
  → dotnet new xunit3 -n OrderService.Tests -o tests/OrderService.Tests
  → Directory.Build.props with .NET 10 defaults
  → Generated: ./CLAUDE.md (OrderService + VSA + scaffold-ready)

  Run /scaffold to add your first feature.

Example — Existing Project With a CLAUDE.md

User: /dotnet-init

Claude: Detected:
  - Solution: MyApp.slnx (3 projects) → Web API
  - Found an existing CLAUDE.md (custom "Deployment" and "Team conventions" sections)

  You already have a CLAUDE.md. How should I proceed?
  [Merge (recommended) / Overwrite / Keep]
  > Merge

  → Backed up original to ./CLAUDE.md.bak
  → Kept your Deployment + Team conventions sections
  → Refreshed architecture (VSA), tech-stack (PostgreSQL + JWT), and convention sections
  Generated: ./CLAUDE.md
  Run /health-check to see your baseline.

Related

  • /plan — Plan before building features
  • /health-check — Assess project health after init
  • /scaffold — Scaffold features using the chosen architecture

Frequently asked questions

What does the Dotnet Init AI skill do?

Interactive project initialization. Detects project type, asks architecture questions, and generates a customized CLAUDE.md — no manual template copying. Use when: "init project", "setup project", "initialize", "new project setup", "generate CLAUDE.md", "configure for dotnet-claude-kit", or starting Claude Code on a fresh or existing .NET codebase.

Why use Dotnet Init on TypingMind?

Because you install it once and use it with any model. Dotnet Init 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 Dotnet Init in TypingMind?

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

Which AI models can use Dotnet Init?

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 Dotnet Init?

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

Is the Dotnet Init 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 👇