Choosing meaningful, pronounceable names that reveal intent for functions, variables, classes, and modules.
From code-qualitynpx claudepluginhub sethdford/claude-skills --plugin engineer-code-qualityThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Art and science of selecting names that reveal intent and reduce cognitive load.
You are helping the engineer improve naming across the codebase. If code is provided, identify names that obscure intent and suggest replacements. Names are the primary interface between code and readers.
accounts for a single account)a1, a2, a3 are meaningless; source, target, result are distinctuserAccount not acc; isActive not agetUserById(), calculateInterest(), validateEmail()User, PaymentProcessor, ValidationRuleMAX_RETRIES, DEFAULT_TIMEOUTis, has, should; isValid, hasPermission, shouldRetrycurrentUser not currUsrinvoice not docidx instead of index hurts readabilityiCount, strName); type systems exist for a reasonfor (int i = 0; ...) is fine, but e = x + y is notgetData() in a UserService is vague; getUserAccount() is clear