How does this skill help prevent technical debt?

It defines specific 'Red Flag Patterns' and a 'Rule of Three' for duplication, ensuring the AI avoids over-engineering early while preventing common smells like multiple responsibilities in single files.

What is the 3-stage impact analysis process?

It is a mandatory sequence of Discovery, Understanding, and Identification that evaluates dependencies, data flow, and risks before any code is modified.

How are quality gates handled in this guide?

The guide follows a four-phase quality assurance workflow: Static Analysis, Build Verification, Comprehensive Testing, and a Final Quality Gate to ensure zero errors before deployment.

Does this skill include debugging frameworks?

Yes, it provides a structured '5 Whys' root cause analysis procedure and guidelines for creating minimal reproduction code to isolate complex bugs.

AI Development Engineering Guide

Name: AI Development Engineering Guide
Author: Tahir-yamin

byTahir-yamin

•

Productivity & Workflow

Enforces professional engineering standards through anti-pattern detection, technical decision frameworks, and structured debugging workflows.

About

This skill provides a comprehensive framework for maintaining high code quality and architectural integrity during AI-assisted development. It equips Claude with systematic criteria for identifying technical debt, implementing fail-fast error handling, and applying the 'Rule of Three' for refactoring. By integrating structured impact analysis and a four-phase quality assurance workflow, the guide ensures that technical decisions are made with transparency and rigor, preventing common failure patterns like error-fix chains, silent failures, and unplanned large-scale changes.

Key Features

Anti-pattern detection for identifying code quality and design red flags
Mandatory three-stage impact analysis for all code modifications
Structured 5 Whys root cause analysis and minimal reproduction debugging techniques
3 GitHub stars
Fail-fast fallback principles to prevent silent error masking in distributed systems
Multi-phase quality check workflow covering static analysis, builds, and testing

Use Cases

Debugging complex logic errors using structured analysis and specialized logging
Evaluating whether to commonalize duplicated code based on the Rule of Three
Performing detailed impact analysis before implementing architectural changes

About

Key Features

Anti-pattern detection for identifying code quality and design red flags
Mandatory three-stage impact analysis for all code modifications
Structured 5 Whys root cause analysis and minimal reproduction debugging techniques
3 GitHub stars
Fail-fast fallback principles to prevent silent error masking in distributed systems
Multi-phase quality check workflow covering static analysis, builds, and testing

Use Cases

Debugging complex logic errors using structured analysis and specialized logging
Evaluating whether to commonalize duplicated code based on the Rule of Three
Performing detailed impact analysis before implementing architectural changes