code-review

Identify and report code violations in local changes and remote pull requests.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/s1nyx/ai-workflow --skill code-review-s1nyx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/s1nyx/ai-workflow/tree/main/.agent/skills/code-review
Command: npx skills add https://github.com/s1nyx/ai-workflow --skill code-review-s1nyx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps ensure code quality by identifying and reporting violations found in code changes or pull requests.

Core Features & Use Cases

  • Evidence-backed reviews: Every issue is supported by verifiable proof in the form of citations or minimal reproducing tests.
  • Cross-workflow applicability: Works with local changes and remote pull requests across languages and project setups.
  • Actionable outputs: Produces structured findings ready for inclusion in code reviews and ticketing systems.

Quick Start

Review code changes and report the first violation with verifiable evidence.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I identify code violations in local changes and remote pull requests?

You can identify code violations in local changes and remote pull requests by analyzing codebases across languages to produce structured findings, ensuring each violation is backed by verifiable citations or minimal reproducing tests.

How does evidence-backed code review work for ensuring code quality?

Evidence-backed code review works by requiring verifiable proof for every reported issue, meaning each violation must be supported either by a citation with a URL and excerpt or a minimal reproducible test showing the failing behavior.

Can I use static analysis to review code quality across different programming languages?

Yes, you can apply static analysis to review code quality across different programming languages, as the review process is designed to work with codebases across various languages and project workflows without being restricted to a single setup.

What is the best way to provide verifiable proof for code violations found during a pull request review?

The best way to provide verifiable proof for code violations is to supply either a citation including a URL and an excerpt or a minimal reproducible test that demonstrates the failing behavior, ensuring findings are actionable and ready for ticketing systems.

What are the limitations of automated code review when detecting security issues and best practices violations?

A limitation of automated code review is that detection requires verifiable proof for each violation; without a supporting citation with a URL and excerpt or a minimal reproducible test showing the failing behavior, an issue cannot be formally reported.