Skip to content
Agentmart
Submit a tool

vs-project-starter

Interactive guide to create the right Visual Studio 2026 project from scratch, step by step.

Skill by tattooinmtl

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying vs-project-starter?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tattooinmtl-vs-project-starter

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Interactive guide to create the right Visual Studio 2026 project from scratch, step by step.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/vs-project-starter

What's inside

Skill name
vs-project-starter
Description
Interactive guide to create the right Visual Studio 2026 project from scratch, step by step.
License
MIT
Instructions
165 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Visual Studio 2026 Project Starter

## Purpose
Guide the user through an interactive questionnaire to determine the best Visual Studio 2026 project type, then create and configure the project step by step.

## When to use
Use this skill when the user runs:

/new-project

## Phase 1 — Discovery Questions

Ask the user the following questions ONE AT A TIME (wait for each answer before asking the next). Keep a running summary of their answers.

### Q1 — Purpose
**What is the application for? What problem does it solve or what does it do?**
→ This determines the broad category (web, desktop, mobile, service, library, game, data, etc.)

### Q2 — Users & Platform
**Who will use it and on what device/platform?**
Examples: internal team on Windows PCs, public users on phones, browser-based, cross-platform, etc.
→ This narrows the UI technology and target framework.

### Q3 — Data & Backend
**Does the app need to store data, call APIs, or run a backend service?**
→ This determines if we need a database, API layer, or backend project.

### Q4 — Scale & Complexity
**What scale are you targeting?**
Options: prototype/MVP, small personal tool, medium business app, large enterprise system
→ This influences architecture decisions (monolith vs layered vs microservices).

### Q5 — Tech Preferences
**Do you have any technology preferences or constraints?**
Examples: must use C#, prefer F#, need .NET 9, must support Linux, company uses React, etc.
→ This locks in language and framework choices.

### Q6 — Team & Experience
**What's your team's experience level and size?**
Options: solo beginner, solo experienced, small team, large team
→ This affects project structure complexity and boilerplate amount.

## Phase 2 — Recommendation

After collecting all answers, present a clear recommendation with:

1. **Project Type** — The exact Visual Studio 2026 project template to use
2. **Language** — Recommended programming language
3. **Framework** — Target framework (e.g., .NET 9, .NET Framework 4.8)
4. **Architecture** — Suggested project structure (monolith, layered, clean architecture, etc.)
5. **Key NuGet Packages** — Essential packages to install upfront
6. **Why this choice** — 2-3 sentence justification linking back to the user's answers

Present this as a formatted recommendation block. Ask the user to confirm or adjust before proceeding.

## Phase 3 — Project Creation (Step by Step)

Once the user confirms the recommendation, execute the following steps ONE AT A TIME, explaining each before running it:

### Step 1 — Create the solution
Use `dotnet` CLI commands to scaffold the solution and projects. Example patterns:

```
dotnet new sln -n <SolutionName>
dotnet new <template> -n <ProjectName> -o <ProjectName> -f <framework>
dotnet sln add <ProjectName>
```

Common templates for Visual Studio 2026:
- `console` — Console Application
- `webapp` — ASP.NET Core Web App (Razor Pages)
- `web` — ASP.NET Core Web App (MVC)
- `webapi` — ASP.NET Core Web API
- `blazor` — Blazor Server
- `blazorwasm` — Blazor WebAssembly
- `winforms` — Windows Forms
- `wpf` — WPF Application
- `maui` — .NET MAUI (cross-platform)
- `classlib` — Class Library
- `worker` — Worker Service / Background Service
- `grpc` — gRPC Service
- `xunit` / `nunit` / `mstest` — Test projects

### Step 2 — Add additional projects
If the architecture calls for multiple projects (e.g., separate class library for business logic, test project, etc.), create each one and add to the solution.

### Step 3 — Add project references
Wire up project-to-project references:
```
dotnet add <ProjectName> reference <OtherProjectName>
```

### Step 4 — Install NuGet packages
Install the recommended packages:
```
dotnet add <ProjectName> package <PackageName>
```

### Step 5 — Create folder structure
Create the recommended folder structure inside each project using `make_dir`. Common patterns:

**Clean Architecture pattern:**
- `Domain/Entities`
- `Domain/Interfaces`
- `Application/Services`
- `Application/DTOs`
- `Infrastructure/Data`
- `Infrastructure/Services`
- `Presentation/Controllers` (or Pages/ViewModels)
- `Presentation/Middleware`

**Simple layered pattern:**
- `Models`
- `Services`
- `Repositories`
- `Controllers` (or ViewModels)
- `Views` (if applicable)

### Step 6 — Add starter files

From tattooinmtl/NimAgent2, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 9, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from tattooinmtl

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get vs-project-starter running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying vs-project-starter?

CallGet help
Cite this page

vs-project-starter skill. Agent Mart. https://agentmart.dev/skills/tattooinmtl-vs-project-starter (last updated 2026-10-24)