Total 30,661 skills, Code Quality has 1619 skills
Showing 12 of 1619 skills
LOAD THIS SKILL when: auditing Effect TypeScript compliance, user mentions 'effect scan', 'effect audit', 'effect best practices check', 'scan-effect-solutions'. Contains Effect compliance audit checklist covering tsconfig, services, data modeling, error handling, config, testing, runtime usage, and Option/Either anti-patterns.
Sub-agent powered code reviews spanning correctness, tests, consistency, and fit
Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.
Biome linter and formatter for JavaScript/TypeScript. Covers configuration, rules, and integration patterns. Replaces ESLint + Prettier for faster development experience. USE WHEN: user mentions "biome", "linting", "formatting", "code style", "biome.json", asks about "setup linter", "format code", "migrate from ESLint", "migrate from Prettier", "biome rules", "biome configuration" DO NOT USE FOR: ESLint configuration - Biome is an ESLint replacement, Prettier configuration - Biome is a Prettier replacement, TypeScript compilation - use TypeScript compiler, Code quality principles - use `clean-code` skill
Fix findings from the active review session — reads reviewer findings files, applies fixes by priority, and updates the resolution log. Use after pasting reviewer output into findings files.
Break the Loop - Deep Bug Analysis
Use this skill when the user asks to review a PR, do a code review, check a pull request, "review this PR", "review-pr", or "look at this pull request". Requires Gitee MCP Server to be configured.
Final review pass to ensure code is as simple and minimal as possible. Use after implementation is complete to identify YAGNI violations and simplification opportunities.
Evidence-based investigative code review using deductive reasoning to determine what actually happened versus what was claimed. Use when verifying implementation claims, investigating bugs, validating fixes, or conducting root cause analysis. Elementary approach to finding truth through systematic observation.
Apply effective software quality consultancy practices. Use when consulting, advising clients, or establishing consultancy workflows.
Use when a request asks for software design patterns or design principles, including explanations, comparisons, summaries, or quick reference grounded in local docs.
R package development with devtools, testthat, and roxygen2. Use when the user is working on an R package, running tests, writing documentation, or building package infrastructure.