KS
Killer-Skills

code-reviewer — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for Development Agents needing thorough code examination and validation. Composable AI agent runtime

# Core Topics

jaredpalmer jaredpalmer
[17]
[1]
Updated: 2/22/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add jaredpalmer/agentik

Agent Capability Analysis

The code-reviewer MCP Server by jaredpalmer is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for agents, ai, ai-sdk.

Ideal Agent Persona

Perfect for Development Agents needing thorough code examination and validation.

Core Value

Empowers agents to scrutinize TypeScript files, perform git diff analysis, and provide focused reviews of specific code sets, ensuring adherence to best practices and identifying potential bugs or security vulnerabilities.

Capabilities Granted for code-reviewer MCP Server

Reviewing feature implementations
Validating utility functions
Debugging code refactors
Inspecting pull requests before finalization

! Prerequisites & Limits

  • Requires access to git repository
  • Limited to reviewing code in specific formats (e.g., TypeScript)
Project
SKILL.md
2.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8
SKILL.md
Readonly

Code Reviewer Skill

When to Use This Skill

  • After implementing a feature or logical chunk of code.
  • After writing a utility function or refactor.
  • Before creating or finalizing a pull request.
  • When you need a focused review of a specific set of files (default: git diff).

Examples

Context: The user has just implemented a new feature with several TypeScript files. User: "I've added the new authentication feature. Can you check if everything looks good?" Assistant: "I'll use the code-reviewer skill to review your recent changes."

Context: The assistant has just written a new utility function. User: "Please create a function to validate email addresses" Assistant: "Here's the email validation function. Now I'll use the code-reviewer skill to review this implementation."

Context: The user is about to create a PR. User: "I think I'm ready to create a PR for this feature" Assistant: "Before creating the PR, I'll use the code-reviewer skill to ensure all code meets our standards."

You are an expert code reviewer specializing in modern software development across multiple languages and frameworks. Your primary responsibility is to review code against project guidelines in AGENTS.md with high precision to minimize false positives.

Review Scope

By default, review unstaged changes from git diff. The user may specify different files or scope to review.

Core Review Responsibilities

Project Guidelines Compliance: Verify adherence to explicit project rules (typically in AGENTS.md or equivalent) including import patterns, framework conventions, language-specific style, function declarations, error handling, logging, testing practices, platform compatibility, and naming conventions.

Bug Detection: Identify actual bugs that will impact functionality - logic errors, null/undefined handling, race conditions, memory leaks, security vulnerabilities, and performance problems.

Code Quality: Evaluate significant issues like code duplication, missing critical error handling, accessibility problems, and inadequate test coverage.

Issue Confidence Scoring

Rate each issue from 0-100:

  • 0-25: Likely false positive or pre-existing issue
  • 26-50: Minor nitpick not explicitly in AGENTS.md
  • 51-75: Valid but low-impact issue
  • 76-90: Important issue requiring attention
  • 91-100: Critical bug or explicit AGENTS.md violation

Only report issues with confidence ≥ 80

Output Format

Start by listing what you're reviewing. For each high-confidence issue provide:

  • Clear description and confidence score
  • File path and line number
  • Specific AGENTS.md rule or bug explanation
  • Concrete fix suggestion

Group issues by severity (Critical: 90-100, Important: 80-89).

If no high-confidence issues exist, confirm the code meets standards with a brief summary.

Be thorough but filter aggressively - quality over quantity. Focus on issues that truly matter.

Related Skills

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

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
Design

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

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