correctness-review

Analyze source code for logic errors, concurrency bugs, and contract violations.

3|Updated May 12, 2026
One-click install
npx skills add https://github.com/gao-hongnan/omniagents --skill correctness-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: correctness-review
Source: https://github.com/gao-hongnan/omniagents/tree/main/plugins/reviewer/skills/correctness-review
Command: npx skills add https://github.com/gao-hongnan/omniagents --skill correctness-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the difficulty of catching subtle, high-impact bugs like race conditions, boundary errors, and state corruption during code reviews.

Core Features & Use Cases

  • Protocol-Driven Analysis: Provides structured hunt protocols for stale call-sites, boundary conditions, concurrency races, and async lifecycle issues.
  • Severity Grading: Uses a standardized rubric to distinguish between critical blockers and minor suggestions.
  • Use Case: Use this during a pull request review to systematically verify that a new async function correctly handles exceptions and that shared state mutations are properly protected by locks.

Quick Start

Perform a correctness review on the current diff to identify potential logic bugs and concurrency issues.

Frequently Asked Questions about correctness-review

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

FAQPage Schema
How do I find race conditions and concurrency bugs during a code review?

To find race conditions during a code review, you can use protocol-driven analysis to systematically inspect shared state mutations and verify they are properly protected by locks. This ensures production-grade reliability by identifying concurrency bugs early.

What is the best way to check for unhandled async exceptions in my source code?

Checking for unhandled async exceptions requires deep inspection of control flow and error handling paths. Using systematic hunt protocols identifies async lifecycle issues and contract violations to ensure robust software quality.

How do I systematically verify boundary arithmetic errors in a pull request diff?

You can systematically verify boundary arithmetic errors by applying structured hunt protocols to the current diff. This deep inspection of state management identifies logic errors and grades their severity to distinguish critical blockers from minor suggestions.

Can I use protocol-driven analysis to detect contract violations and state corruption?

Yes, you can use protocol-driven analysis to detect contract violations and state corruption. It provides structured hunt protocols for stale call-sites and boundary conditions, ensuring production-grade reliability through systematic logic analysis.

When do I need a systematic hunt protocol for logic analysis?

You need a systematic hunt protocol for logic analysis when catching subtle, high-impact bugs like race conditions, boundary errors, and state corruption during code reviews. It applies structured severity grading to identify production-grade reliability issues.