review

Analyze branch diffs for SQL safety, LLM trust boundaries, and side effects.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/TobiasPerry/aws-hackathon --skill review-tobiasperry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/TobiasPerry/aws-hackathon/tree/main/.claude/skills/gstack/review
Command: npx skills add https://github.com/TobiasPerry/aws-hackathon --skill review-tobiasperry

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pre-landing PR reviews often miss or rush critical issues in diffs; this skill analyzes diffs against the base branch to surface SQL safety risks, LLM trust boundary violations, and conditional side effects, ensuring safer merges.

Core Features & Use Cases

  • Diff analysis for SQL safety, data integrity, and race-condition risks.
  • LLM trust boundary checks, including prompt injection and URL safety validations.
  • Actionable remediation suggestions and a structured reviewer checklist for PRs.

Quick Start

Run the review on the current PR branch to automatically generate a structured risk report and recommended fixes.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate pre-landing PR review for SQL safety and LLM trust boundaries?

Automated pre-landing PR review analyzes your current branch diff against the base branch to identify SQL safety issues, LLM trust boundary violations, and conditional side effects, surfacing actionable risks before a merge.

What is LLM trust boundary validation in a code review diff?

LLM trust boundary validation in a code review diff detects prompt injection risks and verifies URL safety within the code changes to ensure that untrusted inputs do not compromise language model integrations.

How do I check a diff for SQL safety issues and race conditions before merging?

You can check a diff for SQL safety issues and race conditions by running an automated risk analysis on your current branch, which produces a structured report with concrete file references and suggested fixes.

Can I use automated risk analysis on any pre-landing code review?

Yes, you can apply automated risk analysis to any pre-landing code review or diff check to surface data integrity risks, providing a structured reviewer checklist with recommended next steps for follow-up tests.

What is the best way to generate a reviewer checklist for conditional side effects in a PR?

The best way to generate a reviewer checklist for conditional side effects is to analyze the branch diff against the base branch, which automatically produces a structured report of findings and actionable remediation suggestions.