code-review

Automate evidence-based code review for pull requests and feature branches.

Updated Aug 20, 2025
One-click install
npx skills add https://github.com/BRANDNEWSHVT/mercora --skill code-review-brandnewshvt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/BRANDNEWSHVT/mercora/tree/main/storefront-nuxt/.agents/skills/code-review
Command: npx skills add https://github.com/BRANDNEWSHVT/mercora --skill code-review-brandnewshvt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code review helps catch issues early, ensuring correctness, security, performance, and maintainability before shipping. It supports a systematic review process that emphasizes evidence over guesswork.

Core Features & Use Cases

  • Structured, evidence-based review process covering correctness, security, performance, and maintainability.
  • The Iron Law: NO MERGE WITHOUT REVIEW. NO REVIEW WITHOUT EVIDENCE.
  • When to Use: Mandatory checks before merging to main/production, after major features, after each task in a plan, and before deploy; Optional checks when stuck, before refactoring, after fixing complex bugs, or when learning a new codebase.
  • When NOT to Use: Avoid reviewing auto-generated diffs without verifying outputs; skip trivial one-character fixes.
  • Anti-Shortcut Rules & Iron Questions: Guidelines to avoid rubber-stamping and to probe edge cases and security considerations.
  • The Review Process: A structured sequence from context understanding to detailed checks ensuring correctness, security, performance, and maintainability.

Quick Start

Apply the structured checklist to the current change set to identify issues and provide actionable feedback before merging.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate a thorough code review for a pull request?

Automated code review applies a structured checklist to pull requests, verifying correctness, security, performance, and maintainability across all files. It surfaces actionable findings with recommended fixes before merging to production.

What is the best way to enforce evidence-based code reviews before merging?

Evidence-based code review requires verifying outputs and probing edge cases rather than rubber-stamping changes. The process enforces an iron law: no merge without review, and no review without evidence, ensuring high software quality.

When should I perform a systematic code review on feature branches?

Perform systematic code reviews before merging to main, after major features, after each task in a plan, and before deployment. Optional checks are useful when stuck, before refactoring, or after fixing complex bugs.

When should I avoid running an automated code review?

Avoid running automated code review on auto-generated diffs unless you verify the outputs. Trivial one-character fixes can also skip the full structured checklist to save development time.

Does structured code review check for security and performance issues?

Yes, structured code review explicitly checks for security and performance issues alongside correctness and maintainability. It applies anti-shortcut rules to probe edge cases and enforce best practices across the entire change set.