review

Identify safety and quality issues in code diffs against main.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/GS-Personal/gstack --skill review-gs-personal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/GS-Personal/gstack/tree/main/review
Command: npx skills add https://github.com/GS-Personal/gstack --skill review-gs-personal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pre-landing PR review and diff analysis that detects SQL safety issues, LLM trust boundary violations, conditional side effects, and other structural problems before merging.

Core Features & Use Cases

  • Diff analysis against main: checks diffs for safety, correctness, and potential side effects.
  • SQL safety & data integrity checks: identifies risky interpolations or schema changes.
  • LLM trust boundary checks: flags prompts, outputs, or tool usage that may leak context or bypass safeguards.
  • Deterministic review prompts: guides reviewers with a structured checklist and actionable feedback via prompts like AskUserQuestion.

Quick Start

Run the /review workflow on your feature branch to generate a structured, safety-focused 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 for SQL safety and LLM trust boundary violations?

Run a pre-landing diff analysis against the main branch to identify SQL safety issues, LLM trust boundary violations, and conditional side effects before merging your pull request.

How does diff analysis detect conditional side effects in a feature branch?

Diff analysis detects conditional side effects by comparing your feature branch against main, structurally evaluating code changes to flag potential safety and correctness issues before they land.

Can I automate code review for LLM output trust boundary checks?

You can automate code review for LLM output trust boundaries by applying structured diff analysis that flags prompts, outputs, or tool usage bypassing safeguards before merge.

What is the best way to review code diffs for unsafe SQL interpolations?

The best way to review code diffs for unsafe SQL interpolations is applying a structured, safety-focused pre-landing review workflow that guides reviewers with actionable feedback on risky schema changes.

Does the code review workflow prompt for user input during diff analysis?

The code review workflow does prompt for user input during diff analysis, using structured review prompts to guide reviewers through safety and quality checks interactively.