Project Setup

What it does

When your agent uses it

• Says tech stack
• Recommended defaults
• What should I use for

Example prompts

• “s tech stack, or when the user says”
• “which database”
• “pick a stack”
• “/project-setup”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Recommend a default, explain the why, let the user choose — Every dimension has a kit default, but defaults are starting points, not…
2. 2Prefer built-in .NET over third-party — HybridCache over Redis-client wrappers, built-in rate limiting over packages, built-in OpenAPI…
3. 3License-aware picks — MediatR (v13+), MassTransit (v9+), and FluentAssertions (v8+) went commercial. The kit defaults to MIT alternatives…
4. 4Add messaging later, not never — Most projects don't need a message bus on day one. Default to "None (add later)" and reach for Wolverine…

What it can do on your machine

Read from SKILL.md and the folder at commit 2330089. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Project Setup loads about 1.2k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 420 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~126

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from codewithmukesh/dotnet-claude-kit at commit 2330089, republished under its MIT licence (© codewithmukesh). 420 words, ~1,162 tokens.

name

project-setup

description

Tech-stack selection advisor for .NET projects: recommended defaults for database, auth, caching, messaging, observability, and resilience, with the rationale behind each default. Load when choosing or reviewing a project's tech stack, or when the user says "tech stack", "which database", "pick a stack", "recommended defaults", or "what should I use for". For project initialization use dotnet-init, for codebase assessment use health-check, for upgrades and schema changes use migrate.

# BAD — assuming the kit defaults apply everywhere
"You should use PostgreSQL and Wolverine."
# The team runs SQL Server enterprise-wide and has zero async workflows.

# GOOD — default + trade-off + question
"Kit default is PostgreSQL (best OSS EF provider). Any organizational
constraint — existing SQL Server licenses, DBA support — that should
override it?"

# BAD — improvising a health grading or init flow from this skill
"Let me grade your codebase across 5 categories..."
# That grading conflicts with the canonical one.

# GOOD — route to the owner
Init/CLAUDE.md → dotnet-init | Assessment → health-check | Upgrades → migrate

© codewithmukesh, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/project-setup of codewithmukesh/dotnet-claude-kit.

Open the folder on GitHubat commit 2330089