skills.rest
algorithmbasics
algorithmbasicsCOMMUNITY
Explore all skills by this author →
𝕏@AlgorithmLlcGitHub

review

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

Updated Apr 18, 2026
Search Tags:#review#diff#code-review#pull-request#sql-safety#llm-boundaries
One-click install
npx skills add https://github.com/algorithmbasics/gstack --skill review-algorithmbasics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/algorithmbasics/gstack/tree/main/review
Command: npx skills add https://github.com/algorithmbasics/gstack --skill review-algorithmbasics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PR diffs can hide structural issues that cause bugs or unsafe merges. This skill analyzes diffs against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural risks to help teams land safer code.

Core Features & Use Cases

  • Detects SQL safety issues in diffs and flags risky patterns before merging.
  • Checks LLM trust boundaries and ensures user-provided prompts or tool calls won't leak or misbehave.
  • Proactively suggests improvements or alternative verification steps before landing a PR.
  • Use Case: A maintainer reviewing a feature branch with potentially unsafe diffs can run this skill to surface critical issues before merge.

Quick Start

Review the latest PR diff against the base branch and surface SQL safety issues, LLM boundary risks, and structural problems with actionable remediation.

Frequently Asked Questions about review

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

FAQPage Schema
How do I review a PR diff for SQL safety issues before merging?▼

To review a PR diff for SQL safety issues, you analyze the code changes against a base branch to detect risky SQL patterns and flag them. This process surfaces critical structural risks to help teams land safer code.

How do code reviews catch LLM trust boundary violations in pull requests?▼

Code reviews catch LLM trust boundary violations by analyzing PR diffs to ensure user-provided prompts or tool calls won't leak or misbehave. This mechanism proactively identifies potential LLM boundary risks before merging.

What is the best way to surface unintended side effects in multi-service PRs?▼

The best way to surface unintended side effects in multi-service PRs is to analyze the diffs against the base branch. This approach identifies conditional side effects and structural risks, returning a structured prioritized remediation plan.

Do I need a base branch to perform automated code reviews on feature branches?▼

Yes, you need a base branch to perform automated code reviews on feature branches. The analysis requires a base branch to accurately compare PR diffs and generate a structured, prioritized remediation plan for SQL and LLM boundary risks.

Can I use automated PR reviews for SQL-heavy changes across different services?▼

Yes, you can use automated PR reviews for SQL-heavy changes across different services. The analysis is applicable to pre-landing reviews across multi-service PRs, detecting SQL safety issues and structural risks before merging.

What limitations exist when reviewing diffs for LLM boundary violations?▼

A limitation when reviewing diffs for LLM boundary violations is that the analysis focuses on structural patterns within the code changes. It checks trust boundaries to prevent prompt leaks but may require alternative verification steps for complex logic.

Related Skills

Explore More Software Engineering Skills→
jm199seojm199seo

review

Analyze pull request diffs against the base branch for structural issues.

Community
Advanced
treesus6treesus6
1

erne-code-review

Identify code quality issues and performance bottlenecks in React Native projects.

Community
Intermediate
NoobyGainsNoobyGains
78

quality-enforcement

Enforce code quality standards across pre-commit, pre-merge, and CI pipeline stages.

Community
Advanced
a29paula29paul
1

review

Detects SQL injection, LLM trust boundary violations, race conditions, and enum gaps in pull request diffs.

Community
Advanced