br4zz4:review-request

Dispatches a code reviewer subagent to evaluate git diffs against requirements before merging.

Updated May 25, 2025
One-click install
npx skills add https://github.com/oporpino/commons --skill br4zz4-review-request-oporpino
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: br4zz4:review-request
Source: https://github.com/oporpino/commons/tree/main/ai/shared/skills/br4zz4%3Areview-request
Command: npx skills add https://github.com/oporpino/commons --skill br4zz4-review-request-oporpino

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often fail because the reviewer lacks context or the author skips review entirely for "simple" changes. This Skill structures the review request process so a fresh reviewer subagent evaluates the actual work product against the original requirements, catching correctness, test quality, and code quality issues before they reach main. ## Core Features & Use Cases - Structured Review Dispatch: Provides a complete prompt template for a reviewer subagent, including SHAs, requirements, and a severity-based output format. - Severity-Based Triage: Classifies findings as Critical, Important, or Minor with clear rules for how to act on each level before merging. - Use Case: After finishing a feature branch, run the Skill to get the base and head SHAs, gather the spec from .project/docs/specs/, and dispatch a reviewer subagent that returns a Ready to merge or Needs fixes assessment. ## Quick Start Ask the AI to request a code review for the current branch against origin/main using the review-request workflow before merging.

Frequently Asked Questions about br4zz4:review-request

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

FAQPage Schema
How do I request a code review before merging to main?▼

Get the base SHA from origin/main and the head SHA from your branch, gather the spec and plan documents, then dispatch a general-purpose subagent with the provided reviewer prompt template. The reviewer runs git diff between the SHAs and returns severity-classified findings.

What should a code review prompt include for an AI reviewer?▼

Include a one-paragraph summary of what was built, the requirements or spec path, the exact git diff command with base and head SHAs, and a defined output format. Specify review dimensions like correctness, test quality, and code quality.

When is a code review mandatory versus optional?▼

Review is mandatory before merging to main and after completing a major feature. It is optional but valuable when stuck on a problem, before refactoring as a baseline check, or after fixing a complex bug.

How should I handle code review feedback I disagree with?▼

Push back with technical reasoning and evidence rather than defensiveness. Do not implement suggestions that break functionality, violate YAGNI, or conflict with prior architectural decisions, but never ignore Critical findings.

What are the limitations of subagent-based code review?▼

The reviewer only sees the diff and provided context, not your session history or thought process. Review quality depends on supplying accurate requirements and correct SHAs, so incomplete context can produce incomplete findings.