review

Analyze git diffs for SQL injection, race conditions, and shell injection risks.

11|2|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/ajsai47/holyclaude --skill review-ajsai47
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/ajsai47/holyclaude/tree/main/skills/team/review
Command: npx skills add https://github.com/ajsai47/holyclaude --skill review-ajsai47

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual code reviews miss structural issues like SQL injection, race conditions, and LLM trust boundary violations that automated tests don't catch. This Skill runs a systematic pre-landing review so critical bugs are caught before merge, not in production.

Core Features & Use Cases

  • Two-Pass Static Analysis: Scans diffs for SQL safety, shell injection, race conditions, enum completeness, and LLM output trust boundaries in a structured critical-then-informational workflow.
  • Specialist Subagents: Spawns parallel security, performance, testing, maintainability, and data migration specialists for deep-dive analysis on large diffs.
  • Scope Drift Detection: Compares the actual diff against TODOS.md and PR descriptions to catch scope creep and missing requirements before the review begins.
  • Use Case: You're about to merge a 300-line branch that touches payments. Run this Skill to automatically flag N+1 queries, missing parameterized SQL, and incomplete error handling before the code reaches production.

Quick Start

Use the review skill to analyze the current branch diff against the base branch and report any critical or informational issues found.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate static analysis for SQL injection and race conditions in a pull request?

Automated static analysis on git diffs identifies SQL injection, race conditions, and shell injection risks before code merges. It scans pull request changes in a structured critical-then-informational workflow to catch structural bugs missed by manual reviews.

What is the best way to catch scope drift and missing requirements before merging a branch?

Scope drift detection compares the actual git diff against TODOS.md and PR descriptions to catch scope creep. It flags missing requirements before the review begins, ensuring the code changes align strictly with the intended project plan.

Can I use parallel subagents for deep-dive security and performance auditing on large diffs?

Yes, specialist subagents can be spawned for parallel deep-dive analysis on large diffs. They independently audit security, performance, testing, maintainability, and data migration issues to provide comprehensive pre-merge validation.

Does pre-landing code review detect LLM trust boundary violations?

Pre-landing code review detects LLM trust boundary violations by performing two-pass static analysis on git diffs. It systematically scans for untrusted LLM output handling and other structural issues before the code reaches production.

How do I set up continuous integration pipelines requiring systematic code quality gates?

Continuous integration pipelines use automated static analysis to enforce systematic code quality gates. This process validates pull requests by checking for shell injection risks, enum completeness, and missing parameterized SQL before merge.

Why does manual code review miss structural issues like N+1 queries?

Manual code review misses structural issues like N+1 queries because they are difficult to spot visually. Automated static analysis scans the diff to systematically flag missing parameterized SQL and incomplete error handling.