roslyn-analyzers

USE FOR: Writing custom Roslyn diagnostic analyzers and code fix providers that report warnings and errors during compilation, and optionally provide automated code transformations. DO NOT USE FOR: Source generators that emit new files (use IIncrementalGenerator), post-compilation IL weaving (use Fody), or standalone static analysis tools (use NDepend or Semgrep).

跳到安装

仓库: Tyler-R-Kendrick/agent-skills
最近来源活动: 2026年2月11日 05:14
检测到的 SKILL.md 语言: 英语
星标: 10
分支: 4

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/Tyler-R-Kendrick/agent-skills --skill roslyn-analyzers

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

21 个文件

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

improve

Use when producing agent/LLM evals, synthetic simulation data, or self-improvement pipelines for prompts, code, skills, agents, harnesses, and workflows. Covers AgentEvals/AgentV, Agent Skills evals, ASSERT, GEPA, Trace, VISTA, Agent Lightning, SkillOpt, Simula-style data design, progressive disclosure, deterministic workspaces, and release evidence. USE FOR: eval creation, EVAL.yaml, AgentEvals, AgentV, evals.json, ASSERT, judge-traces, behavior taxonomy, judges, graders, rubrics, synthetic data, simulation data, Simula, QDC, source-grounded generation, prompt optimization, agent improvement, skill improvement, harness hardening, progressive disclosure, deterministic workflows, GEPA, Trace, VISTA, Agent Lightning, SkillOpt DO NOT USE FOR: ordinary unit/integration tests without AI quality criteria (use testing), refactoring without eval or trace feedback (use refactor), generic Agent Skills packaging without eval or improvement work (use agent-skills)

2026-06-09

Use when working with AI agent protocols, standards, interoperability specifications, evaluation contracts, synthetic simulation data, improvement pipelines, and agent steering workflows. Covers MCP, A2A, ACP, Agent Skills, AGENTS.md, ADL, Improve, x402, AP2, MCP Apps, cagent, and learn. USE FOR: agent protocol selection, comparing MCP vs A2A vs ACP, understanding agent standards ecosystem, choosing payment protocols, choosing eval standards, choosing improvement techniques, choosing synthetic data simulation techniques, steering from user feedback DO NOT USE FOR: specific protocol, eval, or improvement implementation details (use the sub-skills: mcp, a2a, acp, improve, learn, x402, etc.)

2026-06-09

learn

Use when a user corrects, rejects, edits, or redirects an LLM/agent response and the correction should become a reusable reasoning strategy. Converts feedback into generalized learnings for ~/.agents/STEERING.md with linked RDF/Turtle evidence. USE FOR: user corrections, preference feedback, rejected agent behavior, reasoning strategy updates, steering file maintenance DO NOT USE FOR: storing task facts (use memory), ordinary skill authoring (use agent-skills), project instruction files unrelated to feedback (use agents-md)

2026-06-08

查看这个仓库的全部 Skills

name	roslyn-analyzers
description	USE FOR: Writing custom Roslyn diagnostic analyzers and code fix providers that report warnings and errors during compilation, and optionally provide automated code transformations. DO NOT USE FOR: Source generators that emit new files (use IIncrementalGenerator), post-compilation IL weaving (use Fody), or standalone static analysis tools (use NDepend or Semgrep).
license	MIT
metadata	{"displayName":"Roslyn Analyzers","author":"Tyler-R-Kendrick","version":"1.0.0"}
compatibility	["claude","copilot","cursor"]
references	[{"title":"Roslyn Analyzers Overview","url":"https://learn.microsoft.com/en-us/visualstudio/code-quality/roslyn-analyzers-overview"},{"title":"dotnet/roslyn-analyzers GitHub Repository","url":"https://github.com/dotnet/roslyn-analyzers"},{"title":"Microsoft.CodeAnalysis.NetAnalyzers NuGet Package","url":"https://www.nuget.org/packages/Microsoft.CodeAnalysis.NetAnalyzers"}]

Roslyn Analyzers

Overview

Roslyn analyzers are components that plug into the C# and VB.NET compilers to perform custom static analysis during compilation. They report diagnostics (errors, warnings, info messages) and can optionally provide code fix providers that offer automated refactorings through the IDE lightbulb menu. Analyzers are distributed as NuGet packages and run in both the IDE (real-time) and during (batch).

using System.Collections.Immutable; using Microsoft.CodeAnalysis; using Microsoft.CodeAnalysis.CSharp; using Microsoft.CodeAnalysis.CSharp.Syntax; using Microsoft.CodeAnalysis.Diagnostics; namespace MyAnalyzers; [DiagnosticAnalyzer(LanguageNames.CSharp)] public sealed class AsyncMethodNamingAnalyzer : DiagnosticAnalyzer { public const string DiagnosticId = "MA001"; private static readonly DiagnosticDescriptor Rule = new( id: DiagnosticId, title: "Async method should end with 'Async'", messageFormat: "Method '{0}' returns Task but does not end with 'Async'", category: "Naming", defaultSeverity: DiagnosticSeverity.Warning, isEnabledByDefault: true, helpLinkUri: "https://learn.microsoft.com/dotnet/fundamentals/code-analysis/style-rules/ide1006"); public override ImmutableArray<DiagnosticDescriptor> SupportedDiagnostics => ImmutableArray.Create(Rule); public override void Initialize(AnalysisContext context) { context.ConfigureGeneratedCodeAnalysis( GeneratedCodeAnalysisFlags.None); context.EnableConcurrentExecution(); context.RegisterSymbolAction(AnalyzeMethod, SymbolKind.Method); } private static void AnalyzeMethod(SymbolAnalysisContext context) { var method = (IMethodSymbol)context.Symbol; // Skip if already ends with Async if (method.Name.EndsWith("Async")) return; // Skip special methods if (method.IsOverride || method.IsImplicitlyDeclared || method.MethodKind != MethodKind.Ordinary) return; // Check if return type is Task or Task<T> INamedTypeSymbol? returnType = method.ReturnType as INamedTypeSymbol; if (returnType is null) return; string returnTypeName = returnType.ContainingNamespace?.ToDisplayString() + "." + returnType.MetadataName; bool isTaskLike = returnTypeName is "System.Threading.Tasks.Task" or "System.Threading.Tasks.Task`1" or "System.Threading.Tasks.ValueTask" or "System.Threading.Tasks.ValueTask`1"; if (isTaskLike) { var diagnostic = Diagnostic.Create(Rule, method.Locations[0], method.Name); context.ReportDiagnostic(diagnostic); } } }

using System.Collections.Immutable; using System.Composition; using System.Threading; using System.Threading.Tasks; using Microsoft.CodeAnalysis; using Microsoft.CodeAnalysis.CodeActions; using Microsoft.CodeAnalysis.CodeFixes; using Microsoft.CodeAnalysis.CSharp; using Microsoft.CodeAnalysis.CSharp.Syntax; using Microsoft.CodeAnalysis.Rename; namespace MyAnalyzers; [ExportCodeFixProvider(LanguageNames.CSharp, Name = nameof(AsyncMethodNamingCodeFix))] [Shared] public sealed class AsyncMethodNamingCodeFix : CodeFixProvider { public override ImmutableArray<string> FixableDiagnosticIds => ImmutableArray.Create(AsyncMethodNamingAnalyzer.DiagnosticId); public override FixAllProvider GetFixAllProvider() => WellKnownFixAllProviders.BatchFixer; public override async Task RegisterCodeFixesAsync(CodeFixContext context) { var root = await context.Document.GetSyntaxRootAsync(context.CancellationToken); if (root is null) return; var diagnostic = context.Diagnostics[0]; var diagnosticSpan = diagnostic.Location.SourceSpan; var declaration = root.FindToken(diagnosticSpan.Start) .Parent? .AncestorsAndSelf() .OfType<MethodDeclarationSyntax>() .First(); if (declaration is null) return; string newName = declaration.Identifier.Text + "Async"; context.RegisterCodeFix( CodeAction.Create( title: $"Rename to '{newName}'", createChangedSolution: ct => RenameMethodAsync( context.Document, declaration, newName, ct), equivalenceKey: DiagnosticId), diagnostic); } private static async Task<Solution> RenameMethodAsync( Document document, MethodDeclarationSyntax declaration, string newName, CancellationToken cancellationToken) { var semanticModel = await document.GetSemanticModelAsync(cancellationToken); if (semanticModel is null) return document.Project.Solution; var symbol = semanticModel.GetDeclaredSymbol(declaration, cancellationToken); if (symbol is null) return document.Project.Solution; return await Renamer.RenameSymbolAsync( document.Project.Solution, symbol, new SymbolRenameOptions(), newName, cancellationToken); } private const string DiagnosticId = AsyncMethodNamingAnalyzer.DiagnosticId; }

Registration Method	Scope	Use Case
`RegisterSymbolAction`	Named symbols	Naming conventions, accessibility checks
`RegisterSyntaxNodeAction`	Specific syntax node kinds	Pattern detection, anti-patterns
`RegisterOperationAction`	IOperation (semantic ops)	Data flow, assignment analysis
`RegisterCompilationStartAction`	Full compilation scope	Cross-file analysis, type collection
`RegisterSyntaxTreeAction`	Per syntax tree	File-level checks (line count, etc.)
`RegisterCodeBlockAction`	Method/property bodies	Control flow within a single member
`RegisterAdditionalFileAction`	Non-C# files in project	Configuration file validation

roslyn-analyzers

安装方式

检查来源文件

Roslyn Analyzers

Overview

Roslyn Analyzers

Overview

Project Setup

Writing a Diagnostic Analyzer

Writing a Code Fix Provider

Syntax-Based Analyzer

Registration Method Comparison

Unit Testing Analyzers

Best Practices

roslyn-analyzers

来源信息

安装方式

检查来源文件

同仓库更多 Skills

同仓库更多 Skills

Roslyn Analyzers

Overview

Roslyn Analyzers

Overview

Project Setup

Writing a Diagnostic Analyzer

Writing a Code Fix Provider

Syntax-Based Analyzer

Registration Method Comparison

Unit Testing Analyzers

Best Practices