Total 53,839 skills, Code Quality has 2427 skills
Showing 12 of 2427 skills
Reviews Elixir documentation for completeness, quality, and ExDoc best practices. Use when auditing @moduledoc, @doc, @spec coverage, doctest correctness, and cross-reference usage in .ex files.
Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.
Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint propagation, and continuous validation. Use when refactoring existing code, optimizing architecture, or consolidating technical debt through systematic hole-driven development.
Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.
Design error handling strategies for TypeScript and Python applications — exception hierarchies, Result/Either types, retry patterns, error boundaries, and structured error logging. Use when designing error handling architecture, choosing between exceptions and Result types, implementing retry logic, or building error recovery flows. Activate on "error handling", "exception hierarchy", "Result type", "retry pattern", "circuit breaker", "error boundary", "Pokemon exception". NOT for debugging specific runtime errors, logging infrastructure setup, or monitoring/alerting configuration.
Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage.
Iteratively improves a PR until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully optimize a PR against Greptile's code review standards.
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".
Refactoring using Extract Methods in Java Language
Use when a request asks for software design patterns or design principles, including explanations, comparisons, summaries, or quick reference grounded in local docs.
Audit project dependencies for risk when the user asks to check dependencies, audit packages, review dependency health, check for vulnerabilities, or assess supply chain risk
Use when addressing open PR review comments from any reviewer (human or bot) within the current agent session. For a fresh-context-per-comment approach, use ralph-wiggum-loop instead.