review

Audit built code across correctness, architecture, security, and performance.

Updated May 24, 2026
One-click install
npx skills add https://github.com/RCSnyder/lights-out-swe-plugin --skill review-rcsnyder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/RCSnyder/lights-out-swe-plugin/tree/main/skills/review
Command: npx skills add https://github.com/RCSnyder/lights-out-swe-plugin --skill review-rcsnyder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Review helps prevent unsafe or low-quality changes from moving forward by auditing built code for correctness, architecture, security, readability, and performance before reconcile and verify.

Core Features & Use Cases

  • Multi-axis audit: Assesses correctness, readability/simplicity, architecture, security, and performance to catch issues tests may miss.
  • Traceability and discipline checks: Detects scope reduction, placeholder behavior, and broken AC-* traceability so requirements remain accountable.
  • Gate-controlled progression: Blocks the pipeline when Critical/Required findings remain and logs a structured review checkpoint.

Quick Start

Run the Lights Out SWE: Review review agent to audit the built code and automatically enforce the post-review PASS gate before proceeding to RECONCILE.

Frequently Asked Questions about review

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

FAQPage Schema
How do I audit code for security and performance before merging?

Auditing code for security and performance involves a structured review across correctness, architecture, and readability to catch issues tests miss before pipeline progression.

What is AC traceability in gated code review workflows?

AC traceability in code review ensures built artifacts map directly to acceptance criteria, detecting scope reduction and placeholder behavior so requirements remain accountable.

How do I block a CI pipeline when critical code review findings remain?

Blocking a CI pipeline when critical code review findings remain requires a gate-controlled progression mechanism that stops the workflow and logs a structured review checkpoint.

Does automated code review work for staged AI coding pipelines?

Automated code review works for staged AI coding pipelines by validating artifacts produced in prior phases, ensuring built software is safe to keep before reconcile and verify stages.

How to detect scope reduction and placeholder behavior in built code?

Detecting scope reduction and placeholder behavior requires traceability and discipline checks during code review to identify incomplete implementations and broken AC-* mappings.

What are the limitations of relying on tests for software safety?

Relying solely on tests for software safety misses architectural, security, and readability flaws, requiring a multi-axis audit to evaluate these dimensions and block unsafe changes.