review

Analyze PR branch diffs for SQL safety, trust boundary, and side-effect risks.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/pcaokhai/gradion-response-report-api --skill review-pcaokhai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/pcaokhai/gradion-response-report-api/tree/main/.claude/skills/gstack/review
Command: npx skills add https://github.com/pcaokhai/gradion-response-report-api --skill review-pcaokhai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes diffs between the current branch and the base branch to surface SQL safety issues, LLM trust boundary violations, and unintended side effects before merging.

Core Features & Use Cases

  • Diff-based SQL safety checks: detect risky queries and unsafe data-handling in changes.
  • LLM trust boundary validation: guard against leaking prompts or unsafe content in model outputs.
  • Conditional side-effect detection: flag code paths that run only under certain conditions to prevent hidden behavior.
  • Use Case: Before landing a feature branch, run this review to surface potential security or consistency issues that tests may miss.

Quick Start

Run the review workflow on a feature branch to analyze the diff against the base branch and surface issues before merging.

Frequently Asked Questions about review

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

FAQPage Schema
How do I check SQL safety risks in a pull request diff before merging?

To check SQL safety risks in a pull request diff, analyze the changes between your feature branch and the base branch to detect risky queries and unsafe data handling before merging.

What is LLM trust boundary validation in pre-landing code review?

LLM trust boundary validation in pre-landing code review is the process of analyzing diffs to guard against leaking prompts or allowing unsafe content in model outputs before merging.

How do I detect conditional side effects in a feature branch diff?

You detect conditional side effects in a feature branch diff by analyzing code paths that run only under certain conditions, flagging hidden behaviors to prevent unintended consequences during pre-landing review.

Can I surface merge risks that automated tests might miss?

Yes, you can surface merge risks that tests miss by running an AI-assisted pre-landing review on the diff to identify SQL safety issues, LLM trust boundary violations, and conditional side effects.

Does pre-landing PR review work without running the test suite?

Pre-landing PR review works without running tests by directly analyzing the diff against the base branch to surface potential security or consistency issues, providing actionable findings for safe merge decisions.