playbooks

home / skills / bejranonda / llm-autonomous-agent-plugin-for-claude / quality-standards

quality-standards skill

/skills/quality-standards

This skill helps enforce code quality by applying language-specific standards, linting, and documentation benchmarks to maintain high-quality codebases.

npx playbooks add skill bejranonda/llm-autonomous-agent-plugin-for-claude --skill quality-standards

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.3 KB
---
name: quality-standards
description: Defines code quality benchmarks, standards compliance, and best practices for maintaining high-quality codebases
version: 1.0.0
---

## Overview

This skill provides standards and benchmarks for code quality including linting rules, formatting standards, naming conventions, and quality thresholds across programming languages.

## Quality Score Thresholds

- **Excellent**: 90-100
- **Good**: 70-89
- **Acceptable**: 50-69
- **Needs Improvement**: Below 50

## Language-Specific Standards

### Python
- **PEP 8**: Style guide for Python code
- **Type Hints**: Use for public APIs
- **Docstrings**: Google or NumPy style
- **Line Length**: Max 88-100 characters (Black standard)

### JavaScript/TypeScript
- **ESLint**: Use recommended config + project rules
- **Prettier**: For consistent formatting
- **Naming**: camelCase for variables, PascalCase for classes
- **TypeScript**: Enable strict mode

## Quality Components

1. **Tests Passing** (30%): All tests must pass
2. **Standards Compliance** (25%): Linting/formatting adherence
3. **Documentation** (20%): Complete docstrings/comments
4. **Pattern Adherence** (15%): Follow established patterns
5. **Code Metrics** (10%): Complexity and duplication

## When to Apply

Use when validating code quality, enforcing standards, or setting quality benchmarks for projects.

Overview

This skill defines practical code quality benchmarks, language-specific standards, and enforceable best practices to keep codebases healthy and maintainable. It gives clear quality score thresholds and a weighted breakdown of components that determine overall quality. The guidance applies across Python, JavaScript/TypeScript, and general project workflows. Use it to set measurable targets and automated checks for teams and CI pipelines.

How this skill works

The skill inspects linting and formatting results, test outcomes, documentation coverage, pattern adherence, and basic code metrics to compute a composite quality score. It maps findings to predefined thresholds (Excellent, Good, Acceptable, Needs Improvement) and highlights which component weights drove the score. Language-specific rules (PEP 8, ESLint/Prettier, TypeScript strict mode) and conventions are enforced where applicable, producing actionable remediation items.

When to use it

  • Setting quality gates for CI/CD pipelines
  • Defining team or project coding standards
  • Evaluating repositories before releases or merges
  • Onboarding new contributors with clear benchmarks
  • Auditing legacy code to prioritize refactoring

Best practices

  • Adopt automated linters and formatters in pre-commit hooks and CI
  • Use type hints and strict TypeScript to reduce runtime errors
  • Write and maintain docstrings for public APIs using a consistent style
  • Treat failing tests as the highest-priority fix (tests = 30% weight)
  • Monitor complexity and duplication; refactor to keep code metrics within thresholds

Example use cases

  • Block pull requests that drop the quality score below a configured gate
  • Run scheduled audits to track quality score trends across services
  • Enforce Python PEP 8 and Black line-length standards in CI
  • Require TypeScript strict mode and ESLint recommended rules for frontend repos
  • Prioritize remediation tasks based on component weights (tests, standards, docs)

FAQ

How is the overall quality score calculated?

The score is a weighted sum: Tests Passing 30%, Standards Compliance 25%, Documentation 20%, Pattern Adherence 15%, Code Metrics 10%.

What thresholds should my project enforce?

Use the provided bands as a starting point: Excellent 90–100, Good 70–89, Acceptable 50–69, Needs Improvement below 50. Adjust gates to team maturity and risk tolerance.