dotnet-claude-kit

Iteratively fix dotnet build errors. Runs an autonomous build-fix loop that parses compiler errors, categorizes them, applies fixes, and rebuilds until the build is green or the iteration limit is reached. Invoke when the build is broken, after a major refactor, after dependency updates, or when the user says "fix the build", "build is broken", "make it compile".

Save progress by creating a descriptive git commit and writing a handoff note. Use when the user wants to checkpoint work, save progress before a risky change, switch tasks, or pause for the day. Invoke when the user says "checkpoint", "save progress", "commit and handoff", "save state", "pause here".

MCP-powered multi-dimensional code review for .NET projects. Uses Roslyn analysis tools for antipatterns, diagnostics, references, and dependency graphs combined with structured manual review. Produces categorized findings with severity levels and actionable fix suggestions. Use when: "review", "code review", "PR review", "review this", "review my code", "check code quality", "review changes".

Systematic code cleanup pass. Triggers on: /de-sloppify, "clean this up", "cleanup pass", "tidy the code", "fix the mess", "before PR cleanup". Runs formatting, dead code removal, analyzer fixes, and structural improvements.

Interactive project initialization. Detects project type, asks architecture questions, and generates a customized CLAUDE.md — no manual template copying.

Multi-dimensional project health assessment that produces letter grades (A-F) across code quality, architecture compliance, test coverage, dead code, anti-patterns, and circular dependencies. Uses Roslyn MCP tools for deep static analysis. Invoke when: "health check", "project health", "quality report", "assess codebase", starting on a new codebase, periodic quality audit.

Export instincts to a shareable format. Triggers on: /instinct-export, "export instincts", "share instincts", "save instincts for another project".

Import instincts from another project. Triggers on: /instinct-import, "import instincts", "load instincts from", "bring in instincts".

Display all learned instincts with confidence scores. Triggers on: /instinct-status, "show instincts", "what have you learned", "list instincts", "review learned patterns".

Guided, safe EF Core migration workflow. Reviews pending model changes, generates a migration with a descriptive name, reviews the generated SQL for safety, and applies with rollback readiness. Invoke when: "add migration", "update database", "create migration", "schema change", "new table", "rename column".

Enter plan mode for .NET projects with architecture awareness. Analyzes tasks through the lens of supported architectures (VSA, Clean Architecture, DDD, Modular Monolith) and produces structured implementation plans before any code is written. Use when: "plan", "let's plan", "think through", "design this", "how should I implement", or any non-trivial task requiring 3+ steps.

Architecture-aware feature scaffolding for .NET 10 projects. Detects the project's architecture (VSA, Clean Architecture, DDD, Modular Monolith) and generates complete feature slices with all required layers: endpoint, handler, validator, DTOs, EF configuration, and integration tests. Use when: "scaffold", "create feature", "add feature", "new endpoint", "generate", "add entity", "scaffold a module", "add module".

Deep security audit covering OWASP Top 10, secrets detection, vulnerable NuGet packages, authentication configuration, CORS policy, and data protection. Produces a structured report with severity-ranked findings. Invoke when: "security scan", "security audit", "check for vulnerabilities", before production deployment, after adding auth or payment features.

Guided test-driven development workflow for .NET 10 using xUnit v3, WebApplicationFactory, Testcontainers, and Verify snapshots. Follows the strict red-green-refactor cycle. Use when: "TDD", "test-driven", "let's TDD this", "red green refactor", "write the test first", or when building a feature with clear acceptance criteria.

Run a comprehensive 7-phase verification pipeline for .NET projects. Covers build, analyzers, antipattern detection, tests, security, formatting, and diff review. Each phase produces PASS/FAIL with actionable output. Short-circuits on critical failures. Use when: "verify", "check everything", "is this ready", "pre-PR check", "run all checks", or after completing a feature or refactor.

End-of-session wrap-up ritual. Triggers on: /wrap-up, "done for today", "wrap up", "that's all", "end session", "signing off". Captures completed work, pending tasks, and learnings for the next session.

You are the API Designer — the expert on building HTTP APIs with ASP.NET Core Minimal APIs. You design clean, well-documented, and versioned APIs that follow REST conventions and produce excellent OpenAPI specifications.

Model recommendation: Sonnet (routine, iterative task)

You are the Code Reviewer — the quality gatekeeper. You perform multi-dimensional code reviews covering correctness, maintainability, performance, security, and adherence to project conventions. You load skills contextually based on the code being reviewed.

You are the DevOps Engineer — the deployment and infrastructure expert. You design Docker containers, CI/CD pipelines, and .NET Aspire orchestration. You ensure applications are production-ready with proper health checks, logging, and deployment strategies.

You are the .NET Architect — the primary decision-maker for project structure, architecture, and module boundaries. You help teams select and implement the right architecture for their project, guiding them through the architecture-advisor questionnaire and recommending the best fit from VSA, Clean Architecture, DDD, or Modular Monolith.

You are the EF Core Specialist — the database expert. You design DbContext configurations, write efficient queries, manage migrations, and optimize data access patterns. EF Core is the default ORM, and you know when to use it directly and when to escape to raw SQL.

You are the Performance Analyst — the optimization expert. You profile applications, identify bottlenecks, recommend caching strategies, and ensure async patterns are used correctly. You focus on measurable improvements, not premature optimization.

Model recommendation: Sonnet (routine, systematic task)

You are the Security Auditor — the security expert. You review code for vulnerabilities, design authentication and authorization systems, manage secrets, and ensure applications follow OWASP best practices. Security concerns always get surfaced, even when another agent is primary.

You are the Test Engineer — the testing expert. You design test strategies, write integration and unit tests, set up test infrastructure with WebApplicationFactory and Testcontainers, and ensure tests are maintainable and meaningful.

Focus code review effort on the 20% of code that causes 80% of issues. Prioritizes data access, security, concurrency, and integration boundaries over formatting and style. Uses blast radius scoring to determine review depth. Includes checkpoint schedules, critical path identification, and a batch review checklist. Load this skill when reviewing code, PRs, or architecture, or when the user mentions "review", "code review", "PR review", "what should I review", "review priorities", "blast radius", or "critical path".

API versioning strategies for ASP.NET Core. Covers Asp.Versioning library, URL segment, header, and query string strategies, version deprecation, and OpenAPI integration. Load this skill when adding versioning to an API, evolving an API with breaking changes, or when the user mentions "API version", "versioning", "v1/v2", "Asp.Versioning", "deprecation", "breaking change", or "backward compatibility".

Architecture selection advisor for .NET applications. Asks structured questions about domain complexity, team size, system lifetime, compliance, and integration needs, then recommends the best-fit architecture: Vertical Slice, Clean Architecture, DDD + Clean Architecture, or Modular Monolith. Load this skill when the user asks "which architecture", "choose architecture", "set up project", "new project", "architecture decision", "restructure", or "how should I organize". Always load BEFORE any architecture-specific skill.

.NET Aspire for cloud-native orchestration. Covers AppHost configuration, service defaults, resource configuration, service discovery, and the Aspire dashboard. Load this skill when setting up local development orchestration, service discovery, or Aspire-managed infrastructure, or when the user mentions "Aspire", "AppHost", "service defaults", "service discovery", "orchestration", "Aspire dashboard", "AddProject", "WithReference", or "cloud-native .NET".

Authentication and authorization for ASP.NET Core. Covers JWT bearer tokens, OpenID Connect, ASP.NET Identity, authorization policies, role and claim-based authorization, and API key authentication. Load this skill when implementing login, protecting endpoints, designing authorization rules, or when the user mentions "auth", "JWT", "bearer token", "OIDC", "OpenID Connect", "Identity", "claims", "roles", "authorize", "RequireAuthorization", "API key", or "cookie auth".

Autonomous iteration loops for .NET development: build-fix, test-fix, refactor, and scaffold loops. Each loop has bounded iterations, progress detection, and fail-safe guards that prevent infinite retries and wasted tokens. Load this skill when Claude needs to fix build errors, fix failing tests, perform multi-step refactoring, scaffold a new feature, or when the user says "fix the build", "make the tests pass", "refactor this", "scaffold", "generate and verify", "keep going until it works", "autonomous", or "loop".

Caching strategies for .NET 10 applications. Covers HybridCache (the default), output caching, response caching, and distributed cache patterns. Load this skill when implementing caching, optimizing read performance, reducing database load, or when the user mentions "cache", "HybridCache", "Redis", "output cache", "response cache", "distributed cache", "IMemoryCache", "cache invalidation", "stampede protection", or "cache-aside".

CI/CD pipelines for .NET applications. Covers GitHub Actions and Azure DevOps YAML pipelines with build, test, publish, and deploy stages. Load this skill when setting up continuous integration, automated testing, deployment workflows, or when the user mentions "CI/CD", "pipeline", "GitHub Actions", "Azure DevOps", "workflow", "deploy", "build pipeline", "publish", "NuGet push", "release", or "continuous integration".

Clean Architecture for .NET applications. Covers the 4-project layout (Domain, Application, Infrastructure, Api), dependency inversion, use case handlers, domain entities with behavior, and infrastructure as a plugin. Load this skill when building a project with Clean Architecture, discussing layered architecture, dependency inversion, use cases, or when the architecture-advisor recommends Clean Architecture.

Structured code review workflow for .NET projects using Roslyn MCP tools. Multi-dimensional review covering correctness, security, performance, architecture compliance, and test coverage. Load when: "review PR", "review code", "code review", "PR review", "review changes", "review my code", "check code quality".

Configuration patterns for .NET 10 applications. Covers the Options pattern, IOptionsSnapshot vs IOptions, secrets management, and environment-based configuration. Load this skill when setting up application configuration, managing secrets, binding configuration sections, or when the user mentions "configuration", "appsettings", "Options pattern", "IOptions", "IOptionsSnapshot", "secrets", "user secrets", "environment variables", "connection string", or "config binding".

Dockerfile-less containerization using the .NET 10 SDK container publishing feature. Covers MSBuild properties, chiseled images, multi-arch builds, and registry publishing — all without writing a Dockerfile. Load this skill when the user wants to containerize without a Dockerfile, or mentions "dotnet publish container", "PublishContainer", "ContainerRepository", "ContainerFamily", "chiseled", "distroless", "container publish", "SDK container", "no Dockerfile", or "containerize without Docker".

Token budget management for Claude Code sessions. Teaches how to minimize context consumption using MCP-first navigation, lazy loading, subagent isolation, and strategic file reading. Keeps Claude effective throughout long sessions by treating the 200k token window as a budget, not a dumping ground. Load this skill when context is running low, sessions feel sluggish, Claude starts forgetting earlier context, or when planning how to explore a large codebase efficiently. Keywords: "context", "tokens", "budget", "running out of context", "too many files", "large codebase", "memory".

Detects and enforces project-specific coding conventions by analyzing existing codebase patterns. Learns naming conventions, folder structure, test organization, and coding style from the existing code. Load when: "conventions", "coding standards", "project patterns", "enforce style", "detect patterns", "learn conventions", "code consistency".

Domain-Driven Design tactical patterns for .NET applications. Covers aggregates, aggregate roots, value objects, domain events, domain services, strongly-typed IDs, and repository patterns for aggregate persistence. Load this skill when implementing DDD, working with aggregates, value objects, domain events, bounded contexts, or when the architecture-advisor recommends DDD + Clean Architecture. Pair with the clean-architecture skill.

Systematic code cleanup pipeline for .NET projects. Runs 7 ordered steps: formatting, unused usings, analyzer warnings, dead code removal, TODO resolution, sealed class audit, and CancellationToken propagation. Each step is verified independently with tests between phases. Load this skill when: "clean up", "de-sloppify", "tidy up", "remove dead code", "code cleanup", "housekeeping", "tech debt", "fix warnings", "seal classes", "add CancellationToken", "unused usings", "format code".

Dependency injection patterns for .NET 10. Covers service lifetimes, keyed services, the decorator pattern, factory pattern, and common DI pitfalls. Load this skill when registering services, resolving lifetime issues, designing service composition, or when the user mentions "DI", "dependency injection", "service registration", "AddScoped", "AddTransient", "AddSingleton", "keyed services", "decorator", "Scrutor", "IServiceCollection", or "captive dependency".

Docker containerization for .NET 10 applications. Covers multi-stage builds, .NET container images, non-root user configuration, health checks, and .dockerignore. Load this skill when containerizing an application, optimizing image size, setting up Docker Compose for local development, or when the user mentions "Docker", "Dockerfile", "container", "docker-compose", "image", "multi-stage", "non-root", ".dockerignore", "container health check", or "dotnet publish container".

Entity Framework Core patterns for .NET 10. Covers DbContext configuration, migrations workflow, interceptors, compiled queries, ExecuteUpdateAsync, ExecuteDeleteAsync, value converters, and query optimization. Load this skill when working with databases, writing queries, managing schema changes, or when the user mentions "EF Core", "Entity Framework", "DbContext", "migration", "LINQ query", "database", "SQL", "N+1", "Include", "split query", "value converter", "interceptor", or "compiled query".

Error handling strategy for .NET 10 applications. Covers the Result pattern, ProblemDetails (RFC 9457), global exception handling, FluentValidation, and structured error responses. Load this skill when implementing error handling, validation, or designing API error contracts, or when the user mentions "error handling", "Result pattern", "ProblemDetails", "exception", "validation", "FluentValidation", "error response", "global exception handler", or "RFC 9457".

Multi-dimensional health assessment for .NET projects with letter grades (A-F) using Roslyn MCP tools. Evaluates 8 dimensions: build health, code quality, architecture, test coverage, dead code, API surface, security posture, and documentation. Produces a structured report card with actionable recommendations. Load this skill when: "health check", "how healthy is this", "project health", "code quality report", "grade this project", "assess codebase", "quality audit", "technical assessment", "codebase review", "report card".

IHttpClientFactory and typed HTTP clients for .NET 10 applications. Covers named/typed/keyed clients, DelegatingHandlers, resilience with Microsoft.Extensions.Http.Resilience, and testing patterns. Load this skill when configuring HTTP clients, adding retry/circuit breaker policies, or when the user mentions "HttpClient", "IHttpClientFactory", "AddHttpClient", "typed client", "named client", "DelegatingHandler", "resilience", "retry", "circuit breaker", "hedging", "Polly", "AddStandardResilienceHandler", "socket exhaustion", or "Refit".

Confidence-scored instinct system for learning project-specific patterns through an observe-hypothesize-confirm cycle. Instincts start as low-confidence hypotheses and graduate to permanent rules in MEMORY.md once confirmed. Stored per-project in .claude/instincts.md. Load this skill when you notice a recurring pattern, want to track a project convention, encounter "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", or when starting a session (to load existing instincts).

Auto-document insights and discoveries during development sessions. Unlike MEMORY.md (corrective rules from the self-correction-loop skill), the learning log captures organic discoveries: non-obvious bugs, undocumented architecture decisions, performance findings, workarounds, and gotchas. Stored at .claude/learning-log.md. Load this skill when Claude discovers something non-obvious, finds a workaround, uncovers an undocumented decision, or when the user asks about "learnings", "discoveries", "gotchas", "what did we learn", or "document this finding".

Observability for .NET 10 applications. Covers Serilog structured logging, OpenTelemetry traces and metrics, health checks, and correlation IDs. Load this skill when setting up logging, tracing, metrics, or health monitoring, or when the user mentions "Serilog", "logging", "structured log", "OpenTelemetry", "traces", "metrics", "health check", "correlation ID", "observability", "telemetry", "log enrichment", or "ILogger".

Asynchronous messaging patterns for .NET applications. Covers Wolverine and MassTransit, outbox pattern, saga and choreography, and broker configuration for RabbitMQ and Azure Service Bus. Load this skill when implementing event-driven communication, background processing, module-to-module messaging, or when the user mentions "Wolverine", "MassTransit", "message bus", "RabbitMQ", "Azure Service Bus", "event", "publish", "consumer", "outbox", "saga", "integration event", "queue", or "pub/sub".

Safe migration workflows for EF Core database migrations, .NET version upgrades, and NuGet dependency updates. Includes rollback strategies and verification steps. Load when: "migration", "add migration", "ef migration", "update database", "upgrade nuget", "update packages", "dependency update", "version upgrade".

.NET 10 minimal APIs — the default for building HTTP endpoints. Covers MapGroup, endpoint filters, TypedResults, OpenAPI metadata, parameter binding, and route conventions. Load this skill when creating API endpoints, configuring routing, setting up OpenAPI documentation, or when the user mentions "endpoint", "MapGet", "MapPost", "MapGroup", "TypedResults", "route", "minimal API", "OpenAPI", "swagger", "rate limiting", or "output caching".

Strategic Claude model selection for .NET development workflows. Guides when to use Opus 4.6 (deep reasoning, architecture, ambiguous problems) vs Sonnet 4.6 (throughput, large context, routine implementation) vs Haiku 4.5 (fast, cheap subagent tasks). Covers model switching workflows, subagent model assignment, and cost-effective task routing. Load this skill when choosing models for tasks, optimizing costs, working with subagents, or when the user mentions "model", "Opus", "Sonnet", "Haiku", "which model", "cost", "switch model", or "fast mode".

Modern C# language features for .NET 10 and C# 14. Covers primary constructors, collection expressions, the field keyword, extension members, records, pattern matching, spans, and raw string literals. Load this skill when writing any new C# code, reviewing existing code for modernization, using "modern C#", "C# 14", "primary constructor", "collection expression", "records", "pattern matching", "span", "field keyword", or "extension members". Always loaded as the baseline for all agents.

Built-in OpenAPI support for .NET 10 applications. Covers document generation, transformers, TypedResults metadata, security schemes, XML comments, build-time generation, and multiple document support. No Swashbuckle needed. Load this skill when setting up API documentation, customizing OpenAPI output, adding security schemes to docs, or when the user mentions "OpenAPI", "AddOpenApi", "MapOpenApi", "document transformer", "operation transformer", "schema transformer", "OpenAPI 3.1", "API documentation", "Swashbuckle replacement", "Produces", "WithSummary", "WithDescription", "ProblemDetails", "Kiota", or "client generation".

OpenTelemetry observability for .NET 10 applications. Covers traces, metrics, and logs using the OpenTelemetry SDK with OTLP export. Includes custom ActivitySource, IMeterFactory metrics, resource configuration, and Aspire Dashboard integration. Load this skill when setting up distributed tracing, custom metrics, OTLP export, or when the user mentions "OpenTelemetry", "OTLP", "traces", "spans", "Activity", "ActivitySource", "metrics", "IMeterFactory", "Meter", "Counter", "Histogram", "Gauge", "telemetry", "observability", "distributed tracing", "OTEL", or "Aspire Dashboard".

Interactive project setup, health check, and migration workflows. Guides developers through project initialization with customized CLAUDE.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 CLAUDE.md".

.NET solution and project structure conventions. Covers .slnx format, Directory.Build.props, Directory.Packages.props for central package management, global usings, and naming conventions. Load this skill when setting up a new solution, adding projects, configuring build properties, or when the user mentions "solution structure", ".slnx", "Directory.Build.props", "central package management", "Directory.Packages.props", "global usings", ".editorconfig", "project layout", or "naming conventions".

Resilience patterns for .NET 10 applications using Polly v8. Covers retry, circuit breaker, timeout, fallback, rate limiter, hedging, and composing resilience pipelines. Load this skill when implementing retry logic, circuit breakers, handling transient failures, or when the user mentions "Polly", "resilience", "retry", "circuit breaker", "timeout", "fallback", "rate limit", "hedging", "transient fault", "HttpClient resilience", or "resilience pipeline".

Code scaffolding patterns for .NET 10 features, entities, and tests. Generates complete feature slices, entities with EF Core configuration, and integration tests following the project's chosen architecture. Load when: "scaffold", "create feature", "add feature", "new endpoint", "generate", "add entity", "new entity", "scaffold test", "add module".

Scalar API documentation UI for .NET 10 applications. Covers setup, themes, authentication prefill, multiple documents, layout options, and security. A modern replacement for Swagger UI. Load this skill when setting up API documentation UI, or when the user mentions "Scalar", "MapScalarApiReference", "API reference", "Swagger UI replacement", "API documentation UI", "Scalar theme", "interactive API docs", or "Try It".

Deep security scanning for .NET applications across 6 layers: vulnerable packages, secrets detection, OWASP code patterns, auth configuration, CORS policy, and data protection. Produces severity-rated findings with specific remediation steps. Load this skill when: "security scan", "security audit", "check for vulnerabilities", "find secrets", "OWASP", "auth review", "CORS check", "security review", "penetration test prep", "CVE check", "vulnerability scan", "hardcoded password", "data protection", "security posture".

Self-improving correction capture system. After ANY user correction, detect it, generalize the lesson, and store it as a reusable rule in MEMORY.md. Ensures Claude's mistake rate drops over time by compounding corrections into permanent knowledge. Load this skill when a user corrects Claude's output, mentions "remember this", "don't do that again", "learn from mistakes", "update memory", or when starting a new session (to review existing rules).

Structured logging with Serilog for .NET 10 applications. Covers two-stage bootstrap, appsettings configuration, enrichers, sinks, request logging, destructuring, and Serilog.Expressions. Load this skill when setting up Serilog, configuring log sinks, enrichers, or structured logging, or when the user mentions "Serilog", "structured logging", "log enrichment", "Seq", "LogContext", "UseSerilog", "WriteTo", "message template", "Serilog.Expressions", "request logging", "log sink", "rolling file", or "audit log".

End-to-end session lifecycle management for .NET projects. Handles session start (load handoff, MEMORY.md, instincts, detect .NET solution), session end (capture completed work, persist learnings, write handoff), and context preservation across sessions. Load this skill when starting a new session, ending a session, when the user says "new session", "pick up where we left off", "what were we working on", "session start", "session end", "handoff", "context", "resume", or when Claude needs to bootstrap itself in an unfamiliar project.

Modular CLAUDE.md management strategy for projects that outgrow a single instruction file. Covers when and how to split a monolithic CLAUDE.md into multiple files, organizing by concern, module, or team. Includes precedence rules to prevent conflicting instructions. Load this skill when CLAUDE.md exceeds 300 lines, when multiple teams need different instructions, when the user mentions "split CLAUDE.md", "modular instructions", "too long", "organize instructions", or "multiple CLAUDE files".

Testing strategy for .NET 10 applications. Covers xUnit v3, WebApplicationFactory for integration tests, Testcontainers for real database testing, Verify for snapshot testing, and the AAA pattern. Load this skill when writing tests, setting up test infrastructure, reviewing test coverage, or when the user mentions "test", "xUnit", "WebApplicationFactory", "Testcontainers", "integration test", "unit test", "bUnit", "snapshot test", "Verify", "test coverage", "AAA pattern", "WireMock", or "FakeTimeProvider".

7-phase .NET verification pipeline with structured PASS/FAIL reporting. Ensures every change is build-verified, diagnostics-clean, anti-pattern-free, test-passing, security-scanned, format-compliant, and diff-reviewed before marking work as complete. Load this skill when: "verify", "check everything", "run verification", "pre-PR check", "is this ready", "validate changes", "build and test", "quality gate", "pipeline check", "ready to merge".

Vertical Slice Architecture (VSA) for .NET applications — one of several supported architectures in dotnet-claude-kit. Covers feature folders, endpoint grouping, and handler patterns for Mediator, Wolverine, and raw handler classes. Load this skill when the architecture-advisor recommends VSA, when working in an existing VSA codebase, when adding features to a feature-folder project, or when discussing vertical slice patterns, feature folders, or handler patterns.

Claude Code workflow mastery for .NET developers. Covers parallel execution with git worktrees, plan mode strategy, verification loops, auto-formatting hooks, permission setup for dotnet CLI, prompting techniques, and subagent patterns — all adapted for the .NET ecosystem. Load this skill when setting up Claude Code for a .NET project, optimizing workflows, running parallel sessions, or when the user mentions "productivity", "workflow", "parallel", "worktree", "plan mode", "permissions", "hooks", "10x", "setup Claude Code", or "speed up development". Inspired by tips from Boris Cherny (creator of Claude Code) and the Anthropic team.

Structured session ending ritual that captures completed work, pending tasks, and learnings before a session ends. Writes a handoff note to .claude/handoff.md so the next session (or a different developer) can pick up exactly where this session left off. Load this skill when the user signals they're wrapping up, says "let's stop here", "that's all for now", "end of session", "wrap up", "save progress", "handoff", or "I'm done for today".

3 hooks across 2 events