Can this skill be used for refactoring projects?

Yes, requesting a review before and after refactoring provides a valuable baseline check to ensure that logic remains sound while the structure improves.

How does the code-reviewer subagent analyze my work?

The subagent compares the code changes between two specific git SHAs against a provided plan or requirements document to ensure the implementation matches the intended design.

What should I do if the AI reviewer provides incorrect feedback?

The skill includes a protocol for pushing back. If the reviewer is wrong, provide technical reasoning or point to specific tests that prove the code works as intended.

When is the best time to request an automated review?

It is recommended to request a review after completing any task in a subagent-driven workflow, after finishing a major feature, or as a final check before merging to your main branch.

Does this replace human code reviews?

While it significantly speeds up the process and catches common errors, it is designed to complement human review by handling the initial verification of requirements and standard practices.

Automated Code Reviewer

Name: Automated Code Reviewer
Author: seanGSISG

byseanGSISG

0•

Herramientas de Colaboración

Facilitates automated code reviews by dispatching a specialized subagent to audit implementations against requirements before merging or proceeding with tasks.

The requesting-code-review skill streamlines the quality assurance process within Claude Code by automating the dispatch of a 'code-reviewer' subagent. It provides a structured framework for comparing current implementations against original plans or technical requirements using git diffs. By enforcing mandatory checkpoints after tasks and before merges, it helps developers identify critical bugs, architectural inconsistencies, and missing requirements early in the development lifecycle, preventing technical debt from cascading through a project.

Características Principales

01Requirement-to-implementation verification against project documentation

02Git-based diff analysis using BASE and HEAD SHA tracking

03Automated subagent dispatch for deep implementation audits

04Prioritized feedback loops categorized by Critical, Important, and Minor issues

05Structured workflow integration for subagent-driven development

060 GitHub stars

Casos de Uso

01Verifying individual task completion in subagent-driven development cycles

02Obtaining a fresh perspective and automated feedback when stuck on complex bug fixes

03Performing final audits of major features before merging into the main branch

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add seangsisg/crispy-claude requesting-code-review

For use in Claude.ai and ChatGPT

Download Skill