review

Identifies defects and risks in a PR diff by analyzing SQL safety, LLM trust boundaries, and side effects.

9|1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/CarbeneAI/Forge --skill review-carbeneai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/CarbeneAI/Forge/tree/main/.claude/skills/review
Command: npx skills add https://github.com/CarbeneAI/Forge --skill review-carbeneai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The review skill identifies defects and risks in a PR diff against the base branch to prevent bugs and security issues before merging.

Core Features & Use Cases

  • Analyzes diffs for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.
  • Proactively surfaces actionable recommendations and questions when automation alone can't decide.
  • Use case: before landing a PR, run /review to verify risks across code, prompts, and data handling.

Quick Start

Run /review on your feature branch to perform a pre-landing PR review.

Frequently Asked Questions about review

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

FAQPage Schema
How do I check a pull request diff for SQL injection risks before merging?

To check a pull request diff for SQL injection risks, analyze the changes against the base branch for SQL safety, LLM trust boundary violations, and conditional side effects to surface concrete, testable recommendations.

What is a pre-landing code review for LLM trust boundaries?

A pre-landing code review for LLM trust boundaries identifies defects and risks in a PR diff by analyzing prompt handling and data operations, ensuring risky LLM interactions map to the base branch and preventing security issues before merging.

How do I review a PR diff for side effects and risky operations?

Review a PR diff for side effects by mapping changes to the base branch and analyzing data stores, prompts, and risky operations, proactively surfacing actionable recommendations and questions when automation alone cannot decide.

Does pre-landing code review work for analyzing prompt and data handling risks?

Yes, pre-landing code review works for analyzing prompt and data handling risks by verifying safety across data stores and prompts, proactively surfacing actionable recommendations and follow-ups when automation alone cannot decide.

What's the best way to prevent bugs and security issues in a pull request before landing?

The best way to prevent bugs and security issues before landing is to run a pre-landing review that identifies defects and risks in the PR diff, checking SQL safety, LLM trust boundaries, and side effects against the base branch.

When do I need to run a pre-landing PR review?

Run a pre-landing PR review on your feature branch before merging to verify risks across code, prompts, and data handling, ensuring checks map to the diff and base branch to prevent bugs and security issues.