Clean Code

This is the coding standard that stops Claude from writing blog posts when you asked for a function. It enforces pragmatic rules like single responsibility, guard clauses over nesting, and a hard ban on obvious comments. The pre-edit checklist forces you to think about imports and dependencies before touching files, which prevents the classic "I fixed AuthService but broke three controllers" scenario. Most valuable for teams tired of AI agents that explain what they're about to do instead of just doing it. Ships with role-specific validation scripts so your frontend specialist runs accessibility checks and your backend dev runs API validators. Written for developers who want working code, not programming tutorials.

skills.sh installs: 1.1K
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill clean-code --agent claude-code

Installs into .claude/skills of the current project.

Files

Clean Code - Pragmatic AI Coding Standards

CRITICAL SKILL - Be concise, direct, and solution-focused.

Core Principles

Principle	Rule
SRP	Single Responsibility - each function/class does ONE thing
DRY	Don't Repeat Yourself - extract duplicates, reuse
KISS	Keep It Simple - simplest solution that works
YAGNI	You Aren't Gonna Need It - don't build unused features
Boy Scout	Leave code cleaner than you found it

Naming Rules

Element	Convention
Variables	Reveal intent: `userCount` not `n`
Functions	Verb + noun: `getUserById()` not `user()`
Booleans	Question form: `isActive`, `hasPermission`, `canEdit`
Constants	SCREAMING_SNAKE: `MAX_RETRY_COUNT`