opinionated-engineer

Enforce engineering best practices on AI-generated code with tests, error handling, and security controls.

1|1|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/gaoqiongxie/skills-ai --skill opinionated-engineer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opinionated-engineer
Source: https://github.com/gaoqiongxie/skills-ai/tree/main/opinionated-engineer
Command: npx skills add https://github.com/gaoqiongxie/skills-ai --skill opinionated-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-generated code often lacks production readiness, with common issues including unfinished TODOs, missing test coverage, unhandled errors, and insufficient security controls. This Skill eliminates those gaps by enforcing strict, opinionated engineering best practices to ensure all generated code meets senior engineer-level quality standards.

Core Features & Use Cases

  • 10 Hard Guardrails: Mandatory rules banning TODOs/pseudocode, requiring full test coverage, complete error handling, structured logging, type safety, input validation, database transactions, audit trails for sensitive operations, and rollback capability.
  • TDD-First Workflow: Forces test-writing before implementation to define clear interface contracts and edge case coverage.
  • End-to-End Deliverables: Requires full, deployable code units with organized source, test, and documentation files instead of fragmented code snippets.
  • Use Case: When building a user login API, the Skill ensures the output includes rate limiting, password hashing, JWT issuance, audit logging, and full unit/integration test coverage, rather than just a basic functional snippet.

Quick Start

Ask the AI to build a production-ready user authentication API following all engineering discipline rules.

Frequently Asked Questions about opinionated-engineer

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

FAQPage Schema
How do I enforce production-ready engineering standards for AI-generated code?

To enforce production-ready engineering standards for AI-generated code, apply strict guardrails that mandate full test coverage, complete type annotations, structured error handling, and transaction safety. This eliminates unfinished TODOs and ensures maintainable deliverables.

Why does AI-generated code often lack production readiness and security controls?

AI-generated code often lacks production readiness because it outputs fragmented snippets with missing test coverage, unhandled errors, and incomplete type safety. Enforcing opinionated engineering standards eliminates these gaps to deliver senior engineer-level quality.

What is a TDD-first workflow for AI coding and how does it improve code quality?

A TDD-first workflow for AI coding forces the generation of tests before implementation to define clear interface contracts and edge case coverage. This practice improves code quality by ensuring full test coverage and auditable deliverables.

How do I build a user authentication API with full test coverage and audit logging?

To build a user authentication API with full test coverage and audit logging, prompt the AI to follow engineering discipline rules. This ensures the output includes rate limiting, password hashing, JWT issuance, and complete unit and integration tests.

Can I use this approach to eliminate pseudocode and TODOs from AI code snippets?

Yes, you can eliminate pseudocode and TODOs from AI code by applying hard guardrails that ban unfinished implementations. This forces the AI to deliver complete, deployable code units with organized source, test, and documentation files.

What are the limitations of using strict engineering standards for AI code generation?

Strict engineering standards for AI code generation require mandatory input validation, database transactions, and rollback capability for all outputs. This approach is limited to production or enterprise environments requiring highly maintainable and auditable code.