KS
Killer-Skills

review — how to use review for code quality how to use review for code quality, what is review in software development, review alternative for code analysis, review vs code inspection, review install guide for AI agents, review setup for improved code quality

v1.0.0
GitHub

About this Skill

Ideal for Code Review Agents needing comprehensive content analysis and quality assurance capabilities. Review is a code analysis skill that evaluates individual files to identify areas for improvement and provides targeted suggestions.

Features

Reviews each individual file for quality improvements
Supports review of uncommitted files, PR diffs, and user-specified files or directories
Provides focused feedback on top 2-3 aspects that need improvement
Offers short, actionable suggestions for code refinement
Enables efficient code review and quality assurance

# Core Topics

gabrielelanaro gabrielelanaro
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
35
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add gabrielelanaro/wrongodb/review

Agent Capability Analysis

The review MCP Server by gabrielelanaro is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use review for code quality, what is review in software development, review alternative for code analysis.

Ideal Agent Persona

Ideal for Code Review Agents needing comprehensive content analysis and quality assurance capabilities.

Core Value

Empowers agents to review individual files, provide suggestions, and improve code quality using diff to main, uncommitted, or user-specified files and directories, focusing on top aspects that need to be addressed.

Capabilities Granted for review MCP Server

Reviewing code changes for quality assurance
Analyzing individual files for improvements
Providing suggestions for code optimization

! Prerequisites & Limits

  • Requires access to files or directories to be reviewed
  • Limited to reviewing individual files or small code changes
Project
SKILL.md
2.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Review

When to use this skill

Use this skill when you need to review changes and improve quality

How to use

Review EACH individual file that is likely in scope to be reviewed (either uncommitted or in the PR, diff to main, depending on context, or the user specified file or directory)

Really focus on the review on what the user intend to get out of it.

At the end select the top 2-3 aspects that need to be addressed and a short suggestion. The user doesn't want to read a whole essay on the PR. Concise-focused suggestions are best. Like a skilled code reviewer would do.

Provide links to the relevant parts of the code for each suggestion so I can quickly jump to the relevant parts.

Limit strictly to the following aspects and criteria:

Criteria

Single responsibility principle (SRP)

  • Does the current file contains a single isolated functionality or is it a mix? Consider splitting it into multiple files if it's not the case.

  • Does the current class contain a single isolated functionality or is it expanding into a god class? Think again on the overall purpose and evaluate how the responsibility can be split.

Dependency injection (DI)

  • Are we doing some weird initialization in the main constructor? Consider accepting dependencies directly by simplifying the main constructor and moving the initialization of its to a separate factory method. Or whether we need the factory method at all (maybe this is internally initialized class and we don't care)

Naming

  • Files: does each file has a clear name that reflects its purpose? Or does it look like a leftover or a hack?

Layout

  • Does the file belong to its location? Does the file belong to this module or specific directory? If not or it's weird consider renames, or repositioning the file in another place.

Simplicity

  • Are we having unnecessary indirection? If a function is just calling another function, consider inlining it.

Consistency

  • Are we duplicating logic that already exists elsewhere in the codebase? Search for similar patterns, helper methods, or services that we should be using instead.
  • Are there other places in the codebase with similar situations where this same logic/fix should be applied? We don't want inconsistency.
  • Check for opportunities to consolidate with existing utilities, concerns, or services.

Comments

  • Do comments explain the "why" and not the "what"? Comments should only be added in confusing parts and explain why this particular decision was made. If the code is clear, it should not need comments, so consider removing them.

Meaningful, tight interfaces

  • Are the interfaces defined meaningful and tight, are they a pleasure to use?
  • Are they too broad or too narrow?
  • Are they redundant?
  • Are they all used outside Are there too many publid methods? 3–7 public methods is a sweet spot.
  • Does it follow ISP, the interface segregation principle?

Related Skills

Looking for an alternative to review or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication