[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.
Prerequisites: MUST READ before executing:
-
.claude/skills/shared/understand-code-first-protocol.md
-
.claude/skills/shared/evidence-based-reasoning-protocol.md
Quick Summary
Goal: Run linters (.NET analyzers and/or ESLint/Prettier) and report or auto-fix code quality issues.
Workflow:
-
Parse — Determine scope from arguments: backend, frontend, or both; fix mode or report-only
-
Execute — Run dotnet build for .NET analyzers or nx lint / prettier for Angular
-
Report — Group issues by severity (error/warning/info) with file paths and line numbers
Key Rules:
-
No argument = run both backend + frontend in report-only mode
-
fix argument = apply safe auto-fixes, report remaining manual items
-
Always show file paths and line numbers in output
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Run linting: $ARGUMENTS
Instructions
Parse arguments:
-
backend or be → Run .NET analyzers
-
frontend or fe → Run ESLint/Prettier
-
fix → Auto-fix issues where possible
-
No argument → Run both, report only
For Backend (.NET):
dotnet build {SolutionName}.sln /p:TreatWarningsAsErrors=false
-
Check for analyzer warnings (CA*, IDE*, etc.)
-
Report code style violations
For Frontend (Angular/Nx):
cd src/{ExampleAppWeb} nx lint playground-text-snippet nx lint {lib-name}
With auto-fix:
nx lint playground-text-snippet --fix npx prettier --write "apps//*.{ts,html,scss}" "libs//*.{ts,html,scss}"
Report format:
-
Group issues by severity (error, warning, info)
-
Show file paths and line numbers
-
Suggest fixes for common issues
Auto-fix behavior:
-
If fix argument provided, apply safe auto-fixes
-
Report what was fixed vs what needs manual attention
IMPORTANT Task Planning Notes (MUST FOLLOW)
-
Always plan and break work into many small todo tasks
-
Always add a final review todo task to verify work quality and identify fixes/enhancements