review

Analyze code diffs for SQL safety and structural issues.

1|Updated May 25, 2026
One-click install
npx skills add https://github.com/chiruu12/nudge --skill review-chiruu12
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/chiruu12/nudge/tree/main/.agents/skills/gstack-review
Command: npx skills add https://github.com/chiruu12/nudge --skill review-chiruu12

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Bash, Read, Edit, Write, Grep, Glob, Agent, AskUserQuestion, WebSearch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the code review process, analyzing diffs against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues, helping developers catch potential problems before merging.

Core Features & Use Cases

  • Automated Code Review: Analyzes diffs for potential issues like SQL safety, LLM trust boundary violations, and conditional side effects.
  • Pre-Landing Review: Suggests proactive reviews when users are about to merge or land code changes.
  • Use Case: When a developer is asked to "review this PR", "code review", "pre-landing review", or "check my diff", this Skill can be used to automate the review process.

Quick Start

Run the 'review' command to start the code review process for the current PR.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate code review for a PR diff?

Automate code review by running the 'review' command to analyze PR diffs against the base branch. It identifies SQL safety issues, LLM trust boundary violations, and conditional side effects before code lands.

What does automated diff analysis check for SQL safety?

Diff analysis evaluates SQL safety by scanning code changes for risky query patterns and structural issues. It catches potential injection risks and unsafe database operations before merging.

How does pre-landing review detect LLM trust boundary violations?

Pre-landing review detects LLM trust boundary violations by analyzing diffs for improper trust assumptions in AI workflows. It flags code changes that might pass unvalidated LLM outputs to critical execution paths.

Can I use this automated review tool with my existing bash development workflow?

Yes, the automated review tool integrates with bash workflows using Read, Edit, Write, Grep, and Glob operations. It requires Bash access to analyze diffs and execute the code review process.

What is the best way to check for conditional side effects before merging code?

The best way to check for conditional side effects is running an automated diff analysis before landing code. It reviews structural changes against the base branch to identify unintended conditional execution paths.