review

Review git diffs against main with configurable depth levels.

Updated Sep 12, 2021
One-click install
npx skills add https://github.com/cerico/macfair --skill review-cerico
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/cerico/macfair/tree/main/files/claude/skills/review
Command: npx skills add https://github.com/cerico/macfair --skill review-cerico

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reviews of code changes can be inconsistently thorough, leading to blockers slipping into production. This Skill automates code-change reviews with a configurable depth, surfacing issues appropriate to the selected level.

Core Features & Use Cases

  • Depth-configurable checks: Level 1 (quick) through Level 4 (experimental) review modes to tailor thoroughness.
  • Diff-driven assessment: analyzes git diff main...HEAD to identify impacted files, areas, and risk vectors.
  • Output artifacts: provides a concise summary, a list of blockers, and an overall grade for the change.
  • Use Case: a feature branch can be quickly sanity checked at Level 1, or deeply evaluated at Level 3 for a critical release.

Quick Start

Run the review on the current branch with a chosen level (1-4). For example: /review 2

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate code review for a git diff before merging?

Automate code review by processing the git diff against the main branch and applying a structured checklist to return a summary, blockers, and a grade. This surfaces issues consistently without manual inspection.

What is the best way to run a quick sanity check on a feature branch?

Run a quick sanity check on a feature branch by executing a Level 1 review mode. This performs a rapid automated code-change assessment to catch obvious issues before deeper evaluation.

Can I adjust the thoroughness of automated code reviews on demand?

Yes, you can adjust review thoroughness on demand using depth-configurable levels from 1 to 4. This tailors the automated review from a quick sanity check to a deep analysis for critical releases.

How does automated code review identify risk vectors in a pull request?

Automated code review identifies risk vectors by analyzing the git diff main...HEAD output. It evaluates the impacted files and applies a structured checklist to assess potential problems.

What output artifacts are generated from an automated code review?

An automated code review generates a concise summary, a list of blockers, and an overall grade for the change. These artifacts help evaluate the quality and readiness of the code.