Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use the open-source free `Roslynator` analyzer packages and optional CLI for .NET. USE FOR: Roslynator.Analyzers setup; Roslynator CLI checks or cleanup; C# linting, static analysis, and code-fix automation. DO NOT USE FOR: overlapping analyzer packs with no consolidation plan; formatting-only work owned by another formatter. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
.claude/skills/managedcode-roslynator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 773% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 56% | 0% |
Roslynator.Analyzersdotnet format or CSharpierAGENTS.md.editorconfigAGENTS.md and confirm scope and constraints.Workflow through the Ralph Loop until outcomes are acceptable.Required Result Format with concrete artifacts and verification evidence.analyzefixfind-unusedformat.editorconfig.If Roslynator is not configured yet:
rg -n "Roslynator\\.Analyzers" -g '*.csproj' .rg --files -g '.config/dotnet-tools.json'dotnet tool list --localdotnet tool list --globalcommand -v roslynatordotnet add PROJECT.csproj package Roslynator.Analyzersdotnet new tool-manifest (if missing) and dotnet tool install roslynator.dotnet.cli.editorconfig so Roslynator does not fight SDK analyzers, StyleCop, or Meziantou.AGENTS.md and CI, such as:dotnet tool run roslynator analyze SOLUTION_OR_PROJECTdotnet tool run roslynator fix SOLUTION_OR_PROJECTdotnet build SOLUTION_OR_PROJECT and the selected Roslynator command, then return status: configured or status: improved.status: not_applicable.Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
status: not_applicable with explicit reason and fallback path.status: complete | clean | improved | configured | not_applicable | blockedplan: concise plan and current iteration stepactions_taken: concrete changes madevalidation_skills: final skills run, or skipped with reasonsverification: commands, checks, or review evidence summaryremaining: top unresolved items or noneFor setup-only requests with no execution, return status: configured and exact next commands.
Other measured skills in the registry, with their headline benchmark lift.