project-setup
Skill235 starsChanged 3 months agoApache-2.0View on GitHub
Interactive project setup, health check, and migration workflows. Guides developers through project initialization with customized AGENTS.md generation, codebase health analysis using MCP tools, and .NET version migration. Load when: "init project", "setup project", "new project", "health check", "analyze project", "project report", "migrate", "upgrade dotnet", "upgrade .NET", "generate AGENTS.md".
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Run the full questionnaire (15+ questions across 6 categories)
- Distinctive: line 40
Ask about each dimension with a recommended default:
“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Project Setup & Workflows
Core Principles
- Interactive over passive — Don't dump a generic template. Ask questions, gather context, then generate a customized result tailored to the specific project.
- MCP-driven analysis — Use Roslyn MCP tools for health checks and migration analysis instead of reading files manually. Token-efficient and semantically accurate.
- Generate, don't template — AGENTS.md files should be fully populated with specific choices (not
[PLACEHOLDER]values). Every section should reflect the actual project decisions. - Architecture-first — Every workflow starts by understanding or selecting the project's architecture. Architecture drives folder structure, naming, patterns, and test organization.
- 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, AGENTS.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:
| Dimension | Options | Default |
| Database | PostgreSQL, SQL Server, SQLite | PostgreSQL |
| Auth | JWT Bearer, OIDC (Keycloak/Auth0), None | JWT Bearer |
| Caching | HybridCache, Redis, None | HybridCache |
| Messaging | Wolverine (RabbitMQ), MassTransit, None | None (add later) |
| Observability | Serilog + OpenTelemetry, Basic logging | Serilog + OTEL |
| Resilience | Polly v8 pipelines, Basic retry | Polly v8 |
Step 4: Generate AGENTS.md Generate a customized AGENTS.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 newcommands - 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 consistencyStep 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, NotificationServiceGrading 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 AGENTS.md without asking about the project
"Here's your AGENTS.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 AGENTS.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 IdentityHealth 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 verificationDecision Guide
| Scenario | Workflow | Key Tool |
| New greenfield project | Project Init | architecture-advisor skill |
| Joining existing project | Health Check → Init (for AGENTS.md) | get_project_graph |
| "How's our codebase?" | Health Check | detect_antipatterns, get_diagnostics |
| "Upgrade to .NET 10" | Migration | get_project_graph, breaking-changes.md |
| "Generate AGENTS.md for this project" | Project Init (skip new project steps) | get_project_graph |
| Code quality declining | Health Check → set baseline → periodic re-check | All MCP tools |
| Onboarding new developers | Health Check + Init (generates AGENTS.md documenting conventions) | convention-learner skill |
Other versions44 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 44
- karrioapi/karrio★ 799same name
- haowjy/creative-writing-skills★ 555same name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- fltman/project-scaffolder★ 88same name
- markshust/hcf★ 79same name
- dleerdefi/claude-code-construction★ 53same name
- vaayne/agent-kit★ 53same name
- wolverin0/claude-skills★ 41same name
- gricha/dangerous-skills★ 38same name
34 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use creative-writing-craft, creative-writing-muse and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Abdullokh-NSkillcreative-writing-craft
Справочник ремесла: проза, сцена, стиль, голос. Загружать, когда нужно знание "как писать", а не режим производства.
Also in 3 projects that use this
Abdullokh-NSkillcreative-writing-muse
Точка входа в набор скилов для длинной прозы. Включается, когда автор просит спланировать, написать, продолжить, переписать или разобрать художественный текст — роман, повесть, цикл рассказов. Ведёт маршрут от замысла к готовому куску и держит базу знаний проекта.
Also in 3 projects that use this
badgidsSkillcharacter-sim
Pressure-test a character by speaking or reasoning strictly from that character's current voice, goals, relationships, emotional pressure, and knowledge boundary without creating canon by accident.
Also in 3 projects that use this
jpsweeney97Skillwriting-principles
Enforces writing principles for instruction documents (SKILL.md, skill supporting files, subagents, CLAUDE.md). Use when writing, reviewing, or editing any file in **/skills/**/*.md, **/agents/*.md, or **/CLAUDE.md. Triggers on skill creation, skill file updates, CLAUDE.md changes, subagent authoring, or instruction document review.
Also in 3 projects that use this
ItsSidharthaSkillstory-planning
Collaborative planning skill for a GitHub issue. Takes issue content and codebase context as input. Runs an iterative clarification loop until the user explicitly agrees to a plan, then saves it to docs/<story_number>/plan.md. Used by the user-story-implementation skill — load this skill at the start of Phase 1 and follow it completely before returning to the orchestrator.
Also in 3 projects that use this
badgidsSkillstory-review
Diagnose existing prose at a chosen editorial level, from whole-story and developmental problems through scene, line, copy, and proof passes, without rewriting until the diagnosis is accepted.
Also in 3 projects that use this
- +4 more from Abdullokh-N
In this repository96 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- 80-20-reviewSkill
- api-versioningSkill
- architecture-advisorSkill
- aspireSkill
- authenticationSkill
- autonomous-loopsSkill
- cachingSkill
- ci-cdSkill
- clean-architectureSkill
- code-review-workflowSkill
- configurationSkill
- container-publishSkill
- context-disciplineSkill
- convention-learnerSkill
- dddSkill
- dependency-injectionSkill
- de-sloppifySkill
- dockerSkill
- ef-coreSkill
- error-handlingSkill
- health-checkSkill
- httpclient-factorySkill
- instinct-systemSkill
- learning-logSkill
- loggingSkill
- messagingSkill
- migration-workflowSkill
- minimal-apiSkill
- model-selectionSkill
- modern-csharpSkill
- openapiSkill
- opentelemetrySkill
- project-structureSkill
- resilienceSkill
- scaffoldingSkill
- scalarSkill
- security-scanSkill
- self-correction-loopSkill
- serilogSkill
- session-managementSkill
- split-memorySkill
- testingSkill
- verification-loopSkill
- vertical-sliceSkill
- workflow-masterySkill
- wrap-up-ritualSkill
- 80-20-reviewSkill
- api-versioningSkill
- architecture-advisorSkill
- aspireSkill
- authenticationSkill
- autonomous-loopsSkill
- cachingSkill
- ci-cdSkill
- clean-architectureSkill
- code-review-workflowSkill
- configurationSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

