code-review

Reviews branch changes for maintainability, abstraction quality, and structural simplification opportunities.

Updated May 28, 2026
One-click install
npx skills add https://github.com/changfengpro/agent-skills --skill code-review-changfengpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/changfengpro/agent-skills/tree/main/skills/code-review
Command: npx skills add https://github.com/changfengpro/agent-skills --skill code-review-changfengpro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often rubber-stamp working implementations that quietly degrade a codebase through file sprawl, ad-hoc conditionals, and leaky abstractions. This Skill enforces a strict, structure-focused review that pushes for dramatic simplification rather than accepting code that merely works. ## Core Features & Use Cases - Strict Maintainability Audit: Applies explicit non-negotiable rules covering file size limits (1000-line threshold), spaghetti branching, thin abstractions, and type-boundary cleanliness. - Structural Simplification Focus: Actively searches for "code judo" moves—restructurings that delete complexity entirely instead of rearranging it. - Prioritized Findings: Orders review output from structural regressions down to legibility concerns, with a clear approval bar and presumptive blockers. - Use Case: Before merging a large pull request, run this review to catch a file crossing 1000 lines, feature logic leaking into shared modules, or a missed opportunity to reframe the change so entire conditional branches disappear. ## Quick Start Run a strict code quality review of the current branch's changes and flag any structural regressions or missed simplification opportunities.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I run a strict code quality review on a pull request?

Invoke this review on the current branch's changes to audit maintainability, abstraction quality, and structural regressions. It applies explicit rules on file size, branching complexity, and layer placement, then returns prioritized findings with actionable restructuring suggestions.

What does a maintainability-focused code review check for?

It checks for files crossing 1000 lines, ad-hoc conditionals added to unrelated flows, thin wrapper abstractions, unnecessary casts or optionality, logic in the wrong layer, duplicated helpers, and non-atomic or overly sequential orchestration.

When should I use a strict structural review instead of a standard review?

Use it when a change risks long-term maintainability—large diffs, growing files, or new special-case branching. Standard reviews verify correctness; this review blocks merges that preserve incidental complexity when a simpler restructuring is visible.

What are the limitations of an automated maintainability review?

It evaluates structure and design quality, not runtime correctness, security vulnerabilities, or test coverage. Judgments about acceptable complexity still require author justification, and it may flag patterns that are intentional given domain constraints.

Why does a code review flag files over 1000 lines?

Files past 1000 lines are treated as a code-quality smell because they signal missing decomposition. The review asks whether helpers, subcomponents, or modules should be extracted first, waiving the rule only with a compelling structural justification.