skills.rest
curielmc
curielmcCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

review

Analyze PR diffs for SQL safety, LLM trust, and structural issues.

Updated Feb 27, 2026
Search Tags:#automation#git#review#guardrails#diff-analysis#sql-safety#llm-boundaries
One-click install
npx skills add https://github.com/curielmc/beat-SPY --skill review-curielmc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/curielmc/beat-SPY/tree/main/.claude/skills/gstack/review
Command: npx skills add https://github.com/curielmc/beat-SPY --skill review-curielmc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PR reviews are slow and error-prone, especially when diffs touch SQL, data handling, or model prompts. This Skill analyzes diffs against the base branch to surface structural issues, trust boundary violations, and potential side effects before merging.

Core Features & Use Cases

  • Analyzes PR diffs for SQL safety, data-flow integrity, and LLM prompt risks.
  • Proactively suggests fixes or guardrails to prevent regressions before land.
  • Use cases: a "pre-landing review" or "code review" where you want a second set of checks on diffs.

Quick Start

Review the current PR diff to surface SQL safety issues, LLM trust boundaries, and structural defects before you merge.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate PR review for SQL safety and LLM prompt risks?▼

Automate PR review by analyzing diffs against the base branch to proactively surface SQL safety issues, LLM trust violations, and structural problems before merging. This pre-landing review outputs recommended actions, potential fixes, and a concise remediation status to prevent regressions.

What is pre-landing diff analysis and when do I need it?▼

Pre-landing diff analysis is the process of examining code changes before merging to catch structural defects, data-flow integrity issues, and trust boundary violations. You need it when PRs touch SQL, data handling, or model prompts to prevent error-prone manual reviews.

Can I use automated code review to check LLM trust boundaries in my diffs?▼

Yes, you can check LLM trust boundaries by analyzing PR diffs for prompt risks and trust violations. The review proactively flags these boundary issues alongside SQL safety and structural defects, providing recommended fixes before code lands.

What's the best way to prevent SQL safety issues before merging a PR?▼

Prevent SQL safety issues by running an automated pre-landing review that examines diffs against the base branch. This analysis surfaces SQL risks and data-flow integrity problems, outputting actionable remediation steps to fix vulnerabilities before they merge.

Does automated diff analysis work without external dependencies?▼

Yes, automated diff analysis works without external dependencies. The Skill operates independently to analyze PR diffs, checking for SQL safety, LLM trust boundaries, and structural guardrails, ensuring no additional environment setup is required to flag risks.

What types of structural problems can automated PR review catch?▼

Automated PR review catches structural problems including SQL safety issues, data-flow integrity violations, LLM prompt risks, and trust boundary breaches. By analyzing diffs against the base branch, it proactively identifies these defects and suggests guardrails before merging.

Related Skills

Explore More Software Engineering Skills→
ligianehualigianehua

review

Analyze git diffs for SQL safety, LLM trust boundaries, and structural defects.

Community
Advanced
DariusCorvusDariusCorvus
37

review

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

Community
Advanced
scanbottscanbott

review

Analyze PR diffs for SQL safety, LLM trust boundary, and side-effect issues.

Community
Advanced
OneKeyHQOneKeyHQ
2.4k

pr-review

Review pull request diffs for security risks and vulnerabilities.

Official
Advanced