How to use the Coding Standards Baseline agent skill

What is an agent skill and what does this one do?

An agent skill is a folder containing a SKILL.md file that tells an AI agent when to apply a set of instructions and what rules to follow. This skill, named coding-standards, is the shared baseline: it covers conventions that apply across projects rather than detailed framework playbooks.

When it is active, the agent checks and writes code against common style rules: descriptive names, verb-noun function names, avoiding mutation (using spreads instead of direct changes), clear error handling, parallel async calls where possible, and avoiding the 'any' type. It also applies simplicity principles: KISS, DRY and YAGNI.

• Descriptive variable and function names, with verb-noun patterns for functions
• Immutability by default: spread operators instead of direct changes such as items.push
• Error handling that checks response status and does not swallow failures
• Promise.all for independent async calls instead of sequential awaits
• Explicit types instead of 'any'

Install the coding-standards skill

Download the ZIP for this skill from this page and unzip it. You can install it in one of two places. For a personal setup across all your work, unzip it into ~/.claude/skills/. For a single project, unzip it into that project's .claude/skills/ folder.

If you use the Claude apps instead, open Settings, go to Capabilities, and upload the skill under Skills.

• Personal install: ~/.claude/skills/ (applies wherever you use the skill)
• Project install: the project's .claude/skills/ folder (applies to that project only)
• Claude apps: Settings → Capabilities → Skills, then upload

Trigger the skill with natural requests

You do not need a special command. The skill is meant to activate when you ask for a review of code quality or naming and no framework-specific skill fits the task. Its description says to use it when reviewing code quality or naming with no framework-specific skill that applies.

The skill also activates for refactoring existing code to follow conventions, enforcing naming or structural consistency, setting up linting, formatting or type-checking rules, and onboarding new contributors. Phrase requests in plain language that names the goal, such as the examples below.

• Review this file for naming and readability problems.
• Refactor this module so it follows our coding conventions.
• Check this function for mutation and tell me where to use spreads instead.
• Look for 'any' types and suggest proper interfaces.
• Explain the KISS, DRY and YAGNI issues in this diff.

Know when to use a narrower skill instead

This skill is the shared floor, not the detailed framework guide. The skill itself points to other skills for specific work: frontend-patterns for React, state, forms, rendering and UI architecture; backend-patterns or api-design for repository and service layers, endpoint design, validation and server concerns.

For React hooks or backend architecture questions, ask the agent to use those narrower skills. The source only references them; they are not included in this download.

Read the safety notes before installing

This skill requires nothing listed, does not run scripts and does not use the network. The package contains two files: agents/openai.yaml and SKILL.md. It is licensed under MIT.

Because it only provides instructions, the main risk is that its rules may conflict with your team's own style guide. Check its suggestions against local conventions before applying large changes.

• Requires: nothing listed
• Runs scripts: no
• Uses network: no
• Files: agents/openai.yaml, SKILL.md