skills.rest
MFS-code
MFS-codeCOMMUNITY
Explore all skills by this author →
Website𝕏@miguelfsernaGitHub

review

Review git diffs for SQL, LLM trust, and concurrency risks.

8|2|Updated Mar 24, 2026
Search Tags:#diff analysis#code review#concurrency#test gaps#sql safety#pre-landing#llm trust boundary
One-click install
npx skills add https://github.com/MFS-code/gstack --skill review-mfs-code
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/MFS-code/gstack/tree/main/review
Command: npx skills add https://github.com/MFS-code/gstack --skill review-mfs-code

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The /review skill helps you catch risky SQL/data-safety issues and unreliable LLM output patterns before code lands, so you don’t merge changes that could break security, correctness, or side-effect behavior.

Core Features & Use Cases

  • Pre-landing PR review: Analyzes the diff against the base branch for SQL safety, trust-boundary violations, race/concurrency hazards, and enum/value completeness problems.
  • Two-pass findings: Uses a critical pass for high-risk issues first (safety/trust), then an informational pass for secondary concerns like conditional side effects and test gaps.
  • Actionable guidance: Produces Fix-First style outputs, applying obvious mechanical fixes automatically and batching ambiguous items for user input.
  • Optional Greptile triage: When Greptile comments exist, it classifies them to help avoid duplicate work and improve the review signal.

Quick Start

Invoke this skill by typing /review when you want a pre-landing review of your current diff against the base branch.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate a pre-merge code review for SQL safety and concurrency hazards?▼

Automating a pre-merge code review involves analyzing a git diff against the base branch to detect SQL safety issues, concurrency hazards, and LLM output trust boundary violations before the changes land.

What is an LLM trust boundary violation in code review?▼

An LLM trust boundary violation occurs when code implicitly trusts unverified LLM outputs. Pre-landing diff analysis identifies these patterns to prevent merging changes that could break security, correctness, or side-effect behavior.

How do I review a git diff for test gaps and conditional side effects?▼

Reviewing a git diff for test gaps uses a two-pass analysis: a critical pass for high-risk safety issues followed by an informational pass to surface secondary concerns like conditional side effects and missing test coverage.

Can I classify existing Greptile triage comments during a PR review?▼

Yes, you can classify existing Greptile comments during a PR review. The diff analysis integrates Greptile comment classification to help avoid duplicate work and improve the overall review signal.

Does the pre-landing review automatically apply mechanical fixes to ambiguous diff findings?▼

The pre-landing review produces Fix-First style outputs, applying obvious mechanical fixes automatically while batching ambiguous items for user input to ensure safe code integration.

Related Skills

Explore More Software Engineering Skills→
bhianerdbhianerd
1

review

Review pull request diffs for SQL safety, LLM trust boundaries, and concurrency hazards.

Community
Advanced
g4rcezg4rcez
48

review

Analyze diffs against the base branch and auto-fix mechanical issues during PR reviews.

Community
Advanced
Fandhe-AIFandhe-AI
1

implement-review

Automate code review via git diff analysis for quality and security.

Official
Intermediate
agwacomagwacom

review

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

Official
Advanced