review

Analyze diffs against the base branch for SQL safety, trust boundary, and side-effect issues.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/kunalrawat425/conductor-playground --skill review-kunalrawat425
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/kunalrawat425/conductor-playground/tree/main/.claude/skills/gstack/review
Command: npx skills add https://github.com/kunalrawat425/conductor-playground --skill review-kunalrawat425

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes diffs against the base branch to surface SQL safety issues, LLM trust boundary violations, and conditional side effects in code changes. It helps reviewers catch structural issues before merging.

Core Features & Use Cases

  • Analyzes diffs against the base branch focusing on data safety, LLM prompt safety, and side effects.
  • Generates actionable recommendations and flags to guide code changes.
  • Supports PR reviews, code reviews, and pre-landing checks to proactively surface issues.

Quick Start

Review a patch by running the review against a PR diff and report the top actionable issues with suggested fixes.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate PR reviews to check for SQL safety and LLM trust boundary violations?

Automated PR reviews analyze diffs against a base branch to surface SQL safety issues, LLM trust boundary violations, and conditional side effects. They generate actionable recommendations with suggested fixes and risk assessments to guide code changes before merging.

Can I use automated code review for pre-landing checks on diff patches?

Yes, automated code review supports pre-landing checks by analyzing diff patches to surface structural issues. It focuses on data safety, LLM prompt safety, and conditional side effects to proactively catch problems before code lands.

What is an LLM trust boundary violation in a code diff?

An LLM trust boundary violation in a code diff occurs when changes improperly handle the trust level between the LLM and surrounding systems. Automated PR review surfaces these violations to ensure prompt safety and structural integrity.

Does automated diff review provide suggested fixes for code quality issues?

Yes, automated diff review provides suggested fixes for code quality issues. It ensures findings are concrete with actionable recommendations and risk assessments, and surfaces new best practices for future patches.

What's the best way to surface conditional side effects before merging a PR?

The best way to surface conditional side effects before merging is to run an automated diff analysis against the base branch. This review flags side effects alongside SQL safety and LLM trust issues to guide structural code changes.

Are there limitations when using automated code review for data safety checks?

Automated code review for data safety checks focuses on structural issues found in diffs, such as SQL safety and LLM trust boundaries. It may not catch runtime or environmental issues outside the analyzed diff patch.