Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

project-setup项目设置

Agent Skill

project-setup 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

524

周安装

21

GitHub Stars

315

下载量

170
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:project-setup(项目设置)
来源仓库:https://github.com/codewithmukesh/dotnet-claude-kit
仓库路径:skills/project-setup
安装命令:
npx skills add https://github.com/codewithmukesh/dotnet-claude-kit --skill project-setup
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/codewithmukesh/dotnet-claude-kit --skill project-setup

简介

提供交互式项目初始化与上下文感知模板生成。

  • 适用于根据实际需求定制 CLAUDE.md 与解决方案结构。
  • 可结合 Roslyn MCP 工具分析现有代码库健康状况。
  • 强调架构先行与避免通用占位符填充。project-setup 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 建议在安装前明确项目类型与技术栈偏好。

SKILL.md

Project Setup & Workflows

Core Principles

  1. Interactive over passive — Don't dump a generic template. Ask questions, gather context, then generate a customized result tailored to the specific project.
  2. MCP-driven analysis — Use Roslyn MCP tools for health checks and migration analysis instead of reading files manually. Token-efficient and semantically accurate.
  3. Generate, don't template — CLAUDE.md files should be fully populated with specific choices (not [PLACEHOLDER] values). Every section should reflect the actual project decisions.
  4. Architecture-first — Every workflow starts by understanding or selecting the project's architecture. Architecture drives folder structure, naming, patterns, and test organization.
  5. Verify after action — After any workflow completes (init, migration, health check), verify the result. Run builds, tests, or health checks to confirm success.

Patterns

Project Init Workflow

Interactive conversational flow for new projects. Execute steps in order, waiting for user input at each decision point.

Step 1: Project Identity Ask:

  • Project name (used for solution, namespaces, CLAUDE.md)
  • Project type: API, Blazor, Worker Service, Class Library, or Modular Monolith

Step 2: Architecture Selection Delegate to the architecture-advisor skill:

  • Run the full questionnaire (15+ questions across 6 categories)
  • Recommend VSA, Clean Architecture, DDD + CA, or Modular Monolith
  • Explain the rationale for the recommendation

Step 3: Tech Stack Selection Ask about each dimension with a recommended default:

DimensionOptionsDefault
DatabasePostgreSQL, SQL Server, SQLitePostgreSQL
AuthJWT Bearer, OIDC (Keycloak/Auth0), NoneJWT Bearer
CachingHybridCache, Redis, NoneHybridCache
MessagingWolverine (RabbitMQ), MassTransit, NoneNone (add later)
ObservabilitySerilog + OpenTelemetry, Basic loggingSerilog + OTEL
ResiliencePolly v8 pipelines, Basic retryPolly v8

Step 4: Generate CLAUDE.md Generate a customized CLAUDE.md with all choices baked in:

# [ProjectName] — Development Instructions

## Architecture
This project uses [Selected Architecture].
[Architecture-specific conventions and rules]

## Tech Stack
- **Runtime**: .NET 10 / C# 14
- **Database**: [Selected] with EF Core 10
- **Auth**: [Selected]
- **Caching**: [Selected]
- **Observability**: [Selected]

## Conventions
[Architecture-specific patterns, naming, folder structure]

## Skills
[List of relevant skills to load based on choices]

Step 5: Next Steps Suggest:

  • Initial project structure with dotnet new commands
  • Directory.Build.props with common settings
  • First feature scaffold to validate the architecture

Health Check Workflow

Automated codebase analysis that produces a graded report card. Run this when asked to "check health", "analyze the project", or "how's the codebase".

Step 1: Solution Analysis

→ get_project_graph
  Analyze: project count, dependency direction, target frameworks, naming consistency

Step 2: Anti-pattern Scan

→ detect_antipatterns (scope: solution)
  Count and categorize: async void, sync-over-async, DateTime.Now, new HttpClient(), etc.

Step 3: Compiler Diagnostics

→ get_diagnostics (severity: warning, scope: solution)
  Count warnings by category: CS8600 (nullability), CS0219 (unused vars), etc.

Step 4: Dead Code Detection

→ find_dead_code (scope: solution)
  Identify unused types, methods, and properties that can be removed.

Step 5: Test Coverage Assessment

→ get_test_coverage_map
  Check: test project exists, percentage of types with corresponding tests.

Step 6: Report Card

Generate a structured report:

## Codebase Health Report

### Grade: B+ (82/100)

| Category | Score | Issues |
|----------|-------|--------|
| Architecture | 18/20 | Clean dependency direction, 1 questionable reference |
| Anti-patterns | 14/20 | 3 DateTime.Now usages, 1 async void |
| Diagnostics | 20/20 | 0 warnings |
| Dead Code | 16/20 | 4 unused methods found |
| Test Coverage | 14/20 | 70% of types have test coverage |

### Priority Actions
1. **Replace DateTime.Now with TimeProvider** (3 locations) — error-handling skill
2. **Fix async void** in EventService.OnMessage — critical, exceptions will be unobserved
3. **Remove dead code** — 4 unused methods in OrderService, PaymentHelper
4. **Add tests** for ShippingService, NotificationService

Grading scale:

  • A (90-100): Production-ready, well-maintained
  • B (75-89): Good shape, minor improvements needed
  • C (60-74): Needs attention, several areas to improve
  • D (40-59): Significant issues, prioritize cleanup
  • F (<40): Critical problems, stop feature work and fix

Migration Workflow

For complete migration workflows (EF Core, NuGet,.NET version upgrades), see the migration-workflow skill.

Anti-patterns

Skipping Architecture Questionnaire

# BAD — Generating CLAUDE.md without asking about the project
"Here's your CLAUDE.md with VSA architecture..."
# GOOD — Running the full questionnaire first
"Let me understand your project first. What's the domain complexity? How many developers?
How important is independent deployability? ..."
→ Based on answers: "I recommend Clean Architecture because..."

Generic CLAUDE.md with Placeholders

<!-- BAD — User has to fill in everything manually -->
## Architecture
This project uses [ARCHITECTURE].
Database: [DATABASE]
Auth: [AUTH_METHOD]
<!-- GOOD — Fully populated from the conversation -->
## Architecture
This project uses Vertical Slice Architecture.
Database: PostgreSQL with EF Core 10
Auth: JWT Bearer with ASP.NET Core Identity

Health Check Without MCP Tools

# BAD — Reading random files and guessing at quality
"I read Program.cs and it looks fine..."
# GOOD — Systematic analysis with MCP tools
→ get_project_graph: 5 projects, clean dependency direction
→ detect_antipatterns: 3 violations (2 warning, 1 error)
→ get_diagnostics: 7 warnings (5 CS8600, 2 CS0219)
→ find_dead_code: 4 unused symbols
→ get_test_coverage_map: 65% coverage
Grade: B (78/100)

Running Migration Without a Plan

# BAD — Just changing the TFM and hoping for the best
sed -i 's/net8.0/net10.0/g' **/*.csproj
dotnet build  # 47 errors
# GOOD — Systematic migration with verification at each step
# Phase 1: Update framework → build → fix
# Phase 2: Update packages → build → fix
# Phase 3: Adopt new features → build → test
# Phase 4: Full verification

Decision Guide

ScenarioWorkflowKey Tool
New greenfield projectProject Initarchitecture-advisor skill
Joining existing projectHealth Check → Init (for CLAUDE.md)get_project_graph
"How's our codebase?"Health Checkdetect_antipatterns, get_diagnostics
"Upgrade to.NET 10"Migrationget_project_graph, breaking-changes.md
"Generate CLAUDE.md for this project"Project Init (skip new project steps)get_project_graph
Code quality decliningHealth Check → set baseline → periodic re-checkAll MCP tools
Onboarding new developersHealth Check + Init (generates CLAUDE.md documenting conventions)convention-learner skill

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.76%
按下载量换算57

Claude

29.39%
按下载量换算50

Cursor

19.79%
按下载量换算34

Gemini CLI

8.74%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills