What should I do with the feedback provided by the subagent?

Fix Critical issues immediately, resolve Important issues before moving to the next task, and note Minor issues for later refinement.

How does the code-reviewer subagent know what to check?

The skill uses Git SHAs to define a range of commits and requires placeholders for the implementation description and the original plan requirements.

Can I disagree with the AI reviewer's feedback?

Yes. If the reviewer is incorrect, you should push back with technical reasoning, provide tests, or request clarification to improve the model's understanding.

Does this skill work with ad-hoc development?

Absolutely. It is highly effective for ad-hoc reviews before merges or as a baseline check before starting a major refactor.

When is it mandatory to request a code review?

Review is mandatory after each task in subagent-driven development, after completing major features, and before merging to the main branch.

GitHub Code Reviewer

Name: GitHub Code Reviewer
Author: tianyuanztm

bytianyuanztm

0•

Collaboration Tools

Automates the code review process by dispatching AI subagents to verify feature implementation and catch issues before merging.

The Requesting Code Review skill optimizes your development cycle by integrating a specialized code-reviewer subagent into your workflow. It allows developers to define specific commit ranges using Git SHAs and receive structured feedback on implementation quality, requirement adherence, and potential bugs. By enforcing a 'review early, review often' philosophy, this skill prevents technical debt from cascading, making it an essential tool for subagent-driven development and complex feature deployments.

Key Features

01Context-aware verification against project plans and requirements

020 GitHub stars

03Categorized feedback (Critical, Important, Minor) for prioritization

04Automated subagent dispatch for deep logic verification

05Seamless integration with subagent-driven development tasks

06Git SHA-based commit range analysis for targeted auditing

Use Cases

01Obtaining a fresh technical perspective when stuck on complex debugging

02Verifying task completion in multi-step subagent development pipelines

03Final audit of major features before merging into the main branch

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add tianyuanztm/myplan requesting-code-review

For use in Claude.ai and ChatGPT

Download Skill