Total 53,748 skills, Code Quality has 2423 skills
Showing 12 of 2423 skills
Diagnoses and fixes Aptos Move compilation, runtime, and deployment errors. Triggers on: 'error', 'fix this', 'debug', 'troubleshoot', 'why is this failing', error codes like 'EOBJECT_DOES_NOT_EXIST', 'ABORTED', 'RESOURCE_NOT_FOUND', 'Type mismatch', 'ability constraint'.
Architecture optimization team skill. Analyzes codebase architecture, designs refactoring plans, implements changes, validates improvements, and reviews code quality via CSV wave pipeline with interactive review-fix cycles.
Module and file-structure patterns for clean JavaScript architecture.
SonarQube/SonarCloud integration for continuous code quality. Setup, configuration, quality gates, and CI/CD integration. USE WHEN: user mentions "SonarQube", "SonarCloud", "quality gates", asks about "code coverage", "technical debt", "code smells", "sonar-project.properties", "SonarScanner" DO NOT USE FOR: ESLint/Biome - use linting skills, OWASP security - use security skills, testing tools - use Vitest/Playwright skills
Per-package implementation review producing structured findings per review-findings.schema.json
Use this skill when writing or reviewing C# code to follow project conventions. Covers naming standards, async patterns, CancellationToken usage, structured logging, nullable reference types, and formatting rules. Apply when authoring new C# classes, reviewing code style, or ensuring consistency with existing patterns.
Track, categorize, and prioritize technical debt when the user asks to manage tech debt, create a tech debt register, assess code quality, or plan refactoring work
Create production grade smart contracts. Use this skill when the user asks to write smart contracts, specially if they are going to be deployed to production (to a mainnet, or used in a mainnet script).
Perform automated code reviews on GitLab merge requests. Analyzes code for style, bugs, security, performance, and error handling issues. Generates HTML report for easy reading.
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Internal guidance for presenting Codex helper output back to the user