review

Review pull request diffs for correctness, safety, and boundary issues.

Updated Apr 22, 2026

Search Tags:#diff analysis #code review #pull request #race conditions #sql safety #llm trust boundary

Ready to run

npx skills add https://github.com/codetail-ai/skillwright --skill review-codetail-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review
Source: https://github.com/codetail-ai/skillwright/tree/main/registry/skills/review
Command: npx skills add https://github.com/codetail-ai/skillwright --skill review-codetail-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you review code changes before they land, so you catch correctness bugs, safety issues, and boundary mistakes before they reach users.

Core Features & Use Cases

Pre-landing PR review: Checks the diff against the base branch for structural issues that are easy to miss in a quick manual pass.
Safety and correctness checks: Looks for SQL safety problems, LLM trust boundary issues, shell injection, race conditions, and enum completeness gaps.
Review workflow support: Useful when someone asks for a code review, a pre-merge check, or a sanity pass on a diff before shipping.

Quick Start

Use the review skill to inspect the current pull request diff and flag any real bugs, safety risks, or missing cases before merging.

Frequently Asked Questions about review

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

FAQPage Schema

How do I review a pull request diff for SQL safety and race conditions before merging?▼

To review a pull request diff for SQL safety and race conditions, analyze the changed files against the base branch to flag correctness bugs, boundary issues, and safety risks before the code lands.

What is an LLM trust boundary and how do I check it during code review?▼

An LLM trust boundary check during code review verifies whether untrusted inputs cross security limits unexpectedly. Inspect the pull request diff to find boundary mistakes and safety issues before the code reaches users.

Can I use an automated pre-merge check to catch shell injection vulnerabilities?▼

Yes, you can use an automated pre-merge check to catch shell injection vulnerabilities by reading the changed files and surrounding project context to verify whether each security issue is real and actionable before shipping.

What's the best way to find enum completeness gaps in a pre-landing code review?▼

The best way to find enum completeness gaps in a pre-landing code review is to apply structural checks against the pull request diff, verifying that all cases are covered and flagging missing entries before the code lands.

Does pre-merge diff analysis work without reading the surrounding project context?▼

Pre-merge diff analysis requires reading the changed files and the surrounding project context to verify whether each issue is real and actionable, ensuring correctness and safety checks are accurate before landing code.