asynkron-skills

Keep iterating on the next logical step in a project until a clear stop condition is reached. Use when the user says `/continue-loop`, asks to "keep going", "continue iterating", or wants Codex to repeatedly choose the highest-leverage next task, execute it, verify it, and then continue. Good for open-ended cleanup, refactoring, polish, debt burn-down, and project advancement where the next step should be discovered from the current repo state instead of handed over explicitly.

Find and explain churn hotspots and unstable code clusters in a git repo. Goes beyond a flat "most-edited files" list — auto-detects clusters by directory, by filename stem (foo.go + foo_test.go), and by co-change (files that change together) — then classifies each cluster (unstable / under-development / buggy / tightly-coupled / spec-shifting) and explains *why* it's a problem. Trigger whenever the user asks about churn, hotspots, unstable code, files that change a lot, refactoring candidates, technical debt hotspots, "what's a mess", "/hotmess", or any combination of folder + time window where they want insight rather than just numbers. Auto-detects code files when no extension is given.

Scan web pages for UI consistency issues — misalignment, bad contrast, near-miss colors, inconsistent spacing, and more. Requires Chrome DevTools MCP. Use when the user asks to "check the UI", "scan for design issues", "run UXly", or "audit the page".

Generate color palettes with Tailwind-scale shades. Use when the user asks about color palettes, color schemes, Tailwind colors, or generating colors for a UI theme.

Systematic debugging techniques for unclear root causes. Use when a bug's origin is unknown, multiple hypotheses need testing, you need to narrow down a failing area, end-to-end tests fail but you can't tell where, or the user says "I don't know why this is broken". Includes test bombs (hypothesis elimination) and layered tests (pipeline stage isolation).

Apply strict .NET/C# coding standards to a project or solution. Adds Roslynator and Meziantou analyzers, a comprehensive .editorconfig with 80+ diagnostic rules, naming conventions, and performance warnings. Use when the user wants to enforce strict code quality, set up analyzers, or add an .editorconfig to a .NET project.

Run C# static analysis, auto-fix code issues, format code, find unused code, and enforce coding standards in .NET projects. Use when the user asks about code quality, linting, static analysis, code cleanup, unused code, or formatting in C# / .NET projects.

Profile .NET applications for CPU performance, memory allocations, lock contention, exceptions, heap analysis, and JIT inlining. Use when the user asks about performance bottlenecks, memory leaks, high CPU, slow code, lock contention, excessive exceptions, GC pressure, heap growth, or JIT compilation in .NET projects.

Run mandatory pre-PR quality checks for .NET projects before creating a pull request. Use before creating any PR, or when the user says "prepare for PR", "pre-PR checks", or "quality gate".

Find and reduce code duplication, clean up redundant code, detect code clones, reduce codebase size, DRY violations, copy-paste detection. Use when the user asks about duplicate code, code cleanup, reducing code size, DRY principles, or finding copy-pasted code.

Count lines of code, analyze codebase size and composition, compare code between versions. Use when the user asks about lines of code, codebase size, language breakdown, or code statistics.

Handle flaky tests, crashing tests, hanging tests, out of memory tests, stack overflow tests, test isolation, test suite stability issues in .NET projects. Use when dotnet test hangs, crashes, produces OOM or stack overflow errors, or when the user has an unstable/flaky test suite. Do NOT use for normal test runs — only when standard dotnet test is insufficient.