review

Analyze diffs against the base branch for SQL safety and trust boundary issues.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/bananaduck1/storylab --skill review-bananaduck1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/bananaduck1/storylab/tree/main/.claude/skills/gstack/review
Command: npx skills add https://github.com/bananaduck1/storylab --skill review-bananaduck1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines PR reviews by automatically analyzing diffs against the base branch to surface data safety issues, trust boundary violations, and structural risks before merging.

Core Features & Use Cases

  • Analyzes SQL safety, trust boundaries, and conditional side effects in diffs.
  • Flags potential LLM prompt injection or leakage risks and other trust boundary violations.
  • Proactively suggests merge-time risk mitigations and review improvements for code changes.

Quick Start

Run /review on the current branch to generate a PR-diff audit for SQL safety, LLM trust, and structural issues.

Frequently Asked Questions about review

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

FAQPage Schema
How do I audit PR diffs for SQL safety and LLM trust boundary violations?

To audit PR diffs for SQL safety and LLM trust boundary violations, run a review against the base branch. The tool uses diff data and rule-based checks to surface data risks, prompt injection, and side effects before merging.

What is a pre-landing code review for LLM prompt injection risks?

A pre-landing code review for LLM prompt injection risks analyzes your branch diff to identify trust boundary violations and potential data leakage. It flags these structural risks to provide actionable guidance before code changes are merged.

Can I automatically check my diff for SQL safety issues before merging?

Yes, you can automatically check your diff for SQL safety issues before merging. The tool proactively analyzes diffs against the base branch to surface data safety issues and conditional side effects when you are about to land code changes.

Does the PR review tool work without external dependencies?

Yes, the PR review tool works without external dependencies. It relies entirely on diff data and internal rule-based checks to surface risks, requiring no additional environment setup or installed packages to analyze your code changes.

What is the best way to surface side effects in code reviews?

The best way to surface side effects in code reviews is to analyze the branch diff against the base. This approach identifies conditional side effects, LLM trust violations, and SQL safety issues, providing actionable merge-time risk mitigations.

When should I use an automated diff review instead of a manual code review?

You should use an automated diff review instead of a manual code review when you need to systematically surface SQL safety, LLM trust boundaries, and structural risks before landing code changes, ensuring merge-time mitigations are proactively addressed.