Loading...
Loading...
Found 501 Skills
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".
Interactive project initialization. Detects project type, asks architecture questions, and generates a customized CLAUDE.md — no manual template copying. Use when: "init project", "setup project", "initialize", "new project setup", "generate CLAUDE.md", "configure for dotnet-claude-kit", or starting Claude Code on a fresh or existing .NET codebase.
Autonomous iteration loops for .NET: drive a broken build or failing test suite to green with bounded iterations, progress detection, and fail-safe guards that prevent infinite retries and wasted tokens. The build-fix loop (dotnet build, parse, categorize, fix, rebuild) is the primary flow; the test-fix loop is a first-class variant. Invoke when the build is broken, after a major refactor or dependency update, or when the user says "fix the build", "build is broken", "make it compile", "make the tests pass", "fix failing tests", "keep going until it works", "autonomous", "loop", "auto-fix", or "keep fixing".
Diagnoses and fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test).
Compares two or more dotnet new templates side by side to help users choose between them based on parameters, feature support, frameworks, and classifications. USE FOR: deciding between similar templates (webapi vs webapp, blazor vs blazorwasm, console vs worker), producing a side-by-side comparison of parameters and feature support, understanding how templates differ before creating a project. DO NOT USE FOR: creating a project from a template (use template-instantiation), authoring or validating custom templates (use template-authoring and template-validation), general single-template discovery (use template-discovery).
Create a new ASP.NET Core web application or web site using Blazor. USE FOR: creating a new Blazor web app, scaffolding a new web project, starting a new web site, choosing render modes (Static SSR, Interactive Server, Interactive WebAssembly, Auto), running dotnet new blazor with the right options, setting up initial project structure. DO NOT USE FOR: adding features to existing projects, changing how an existing app renders, or component authoring (use author-component).
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.
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, subagent patterns, and context discipline — token budget management, MCP-first navigation, lazy loading, and subagent isolation — all adapted for the .NET ecosystem. Load this skill when setting up Claude Code for a .NET project, optimizing workflows, running parallel sessions, when context is running low or sessions feel sluggish, when exploring a large codebase efficiently, or when the user mentions "productivity", "workflow", "parallel", "worktree", "plan mode", "permissions", "hooks", "10x", "setup Claude Code", "speed up development", "context", "tokens", "budget", "running out of context", "too many files", or "large codebase". Inspired by tips from Boris Cherny (creator of Claude Code) and the Anthropic team.
Applies cross-parameter default rules when creating .NET projects with dotnet new, filling gaps consistently without overriding values the user set explicitly. USE FOR: choosing which target framework to pair with native AOT, deciding whether to keep HTTPS when authentication is enabled, recognizing that controllers and minimal-API flags are mutually exclusive, filling unset related parameters during project creation, explaining why a default was applied and ensuring an explicit user value is never overridden. DO NOT USE FOR: creating the project itself (use template-instantiation), finding or comparing templates (use template-discovery and template-comparison), authoring or validating custom templates (use template-authoring and template-validation).
Refactor ASP.NET Core/C# code to improve maintainability, readability, and adherence to best practices. Transforms fat controllers, duplicate code, and outdated patterns into clean, modern .NET code. Applies C# 12 features like primary constructors and collection expressions, SOLID principles, Clean Architecture patterns, and proper dependency injection. Identifies and fixes anti-patterns including service locator, captive dependencies, and missing async/await patterns.
Debug ASP.NET Core and .NET applications with systematic diagnostic approaches. This skill covers troubleshooting dependency injection container errors, middleware pipeline issues, Entity Framework Core query problems, configuration binding failures, authentication/authorization issues, and startup failures. Includes Visual Studio and VS Code debugging, dotnet-trace, dotnet-dump, dotnet-counters tools, Serilog configuration, Application Insights integration, and four-phase debugging methodology.
Analyze code coverage and CRAP (Change Risk Anti-Patterns) scores to identify high-risk code. Use OpenCover format with ReportGenerator for Risk Hotspots showing cyclomatic complexity and untested code paths.