ai-development-guide

Guide AI development with technical decision criteria and debugging workflows.

1|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/simoabid/ABID.Dev-Portfolio --skill ai-development-guide-simoabid
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-development-guide
Source: https://github.com/simoabid/ABID.Dev-Portfolio/tree/main/.agent/skills/ai-development-guide
Command: npx skills add https://github.com/simoabid/ABID.Dev-Portfolio --skill ai-development-guide-simoabid

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive guide to making sound technical decisions, identifying and avoiding common anti-patterns, implementing effective debugging strategies, and establishing a robust quality assurance workflow for AI development.

Core Features & Use Cases

  • Technical Decision Criteria: Offers guidelines for choosing abstractions, balancing performance vs. readability, and defining contract granularity.
  • Anti-pattern Detection: Lists and explains numerous code and design anti-patterns to avoid.
  • Debugging Techniques: Provides structured procedures for error analysis, root cause identification (5 Whys), and creating minimal reproductions.
  • Quality Check Workflow: Outlines a universal, multi-phase quality assurance process from static analysis to final gate.
  • Use Case: When faced with a complex architectural choice, consult this Skill for criteria on making the most maintainable and robust decision. When debugging a persistent issue, follow the outlined error analysis and 5 Whys procedure to find the root cause.

Quick Start

Consult the AI development guide for best practices on handling technical decisions.

Frequently Asked Questions about ai-development-guide

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What are the best practices for making technical decisions in AI development?▼

AI development debugging techniques include structured error analysis, root cause identification using the 5 Whys method, and creating minimal reproductions to isolate and resolve persistent issues effectively.

How do I detect and avoid code anti-patterns during AI development?▼

Detecting code anti-patterns during AI development requires checking designs against documented lists of common pitfalls, ensuring fail-fast principles, and applying the rule of three to eliminate code duplication.

How do I implement a quality assurance workflow for AI applications?▼

Implementing a quality assurance workflow for AI applications involves executing a multi-phase process spanning from static analysis to a final gate, ensuring completeness in error handling and design quality.

When should I apply the fail-fast principle in AI development?▼

Apply the fail-fast principle in AI development during error handling and impact analysis to expose invalid states and structural flaws immediately, preventing downstream logic failures and debugging complexity.

Can I use structured impact analysis for architectural choices in AI projects?▼

Structured impact analysis evaluates architectural choices in AI projects by mapping technical decision criteria against maintainability and robustness, ensuring design completeness and preventing anti-patterns before implementation.