Agent skill

reviewers

4400+ curated code review prompts from leading open-source repositories

View SKILL.md on GitHub Repository
Stars 5
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/settlemint-archive/agent-marketplace/tree/main/.agents/skills-local/reviewers

SKILL.md

Code Reviewers

A collection of 4400+ curated code review guidelines derived from real code review comments in leading open-source repositories.

Attribution

This skill contains content from baz-scm/awesome-reviewers, licensed under Apache 2.0.

Skill Categories

The reviewers are organized into 10 skill domains. Read each file in skills/ for detailed guidance:

Category File Focus
AI-Assisted Development skills/ai-assisted-development.md Leveraging AI coding assistants while maintaining quality
Code Readability skills/code-readability.md Writing clear, maintainable code
Code Refactoring skills/code-refactoring.md Improving code structure and design
Data & ML skills/data-ml.md Data pipelines and machine learning
DevOps & Cloud skills/devops-cloud.md Infrastructure and deployment
Documentation skills/documentation.md Code and API documentation
Full-Stack Development skills/full-stack-development.md Frontend and backend integration
Secure Coding skills/secure-coding.md Security best practices
Team Collaboration skills/team-collaboration.md Code review and teamwork
Testing & Debugging skills/testing-debugging.md Test strategies and debugging

Reviewer Organization

The 4400+ reviewers in reviewers/ are prefixed by source project. Major projects include:

Prefix Project Count
react-* React 109
kubeflow-* Kubeflow 62
neon-* Neon 50
sentry-* Sentry 48
spring-* Spring 46
mastodon-* Mastodon 45
grafana-* Grafana 43
cypress-* Cypress 43
bun-* Bun 37
deno-* Deno 36
nest-* NestJS 36
checkov-* Checkov 38
argo-* Argo CD 38
posthog-* PostHog 39
teleport-* Teleport 39

And 165+ more projects.

Reviewer File Format

Each reviewer follows this format:

yaml
---
title: <Review guideline title>
description: <Brief description>
repository: <source OSS repo>
label: <category>
language: <programming language>
comments_count: <number of supporting comments>
repository_stars: <repo popularity>
---

<Detailed guidelines with examples and code blocks>

Usage

Selecting Relevant Reviewers

  1. By Language: Filter reviewers by the language field in their frontmatter

    bash
    grep -l "language: TypeScript" reviewers/*.md

  2. By Project/Framework: Use project prefixes to find relevant patterns

    • React apps: react-*, next-*
    • Python: airflow-*, kubeflow-*, boto3-*
    • Go: kubernetes-*, teleport-*, argo-*
    • Rust: deno-*, bun-*, workerd-*

  3. By Category: Use the label field

    • Code Style
    • Performance
    • Security
    • Testing
    • Documentation

Applying Reviewers to Code Review

When reviewing code:

  1. Identify the tech stack from the files being reviewed
  2. Select 5-10 relevant reviewers based on:
    • Programming language
    • Framework/library in use
    • Type of change (feature, refactor, bugfix)
  3. Read each selected reviewer for specific guidelines
  4. Apply the patterns when commenting on the code

Integration with Differential Review

When using the differential-review skill:

  1. First identify changed files and their languages
  2. Load relevant reviewers for those languages/frameworks
  3. Use reviewer guidelines to inform your review comments

Quick Reference by Technology

TypeScript/JavaScript:

  • react-*, next-*, angular-*, nest-*, bun-*, deno-*

Python:

  • airflow-*, kubeflow-*, boto3-*, checkov-*, prowler-*

Go:

  • kubernetes-*, teleport-*, argo-*, grafana-*

Rust:

  • deno-* (core), bun-* (native), workerd-*

Infrastructure/DevOps:

  • kubernetes-*, argo-*, grafana-*, checkov-*, prowler-*

Security:

  • checkov-*, prowler-*, teleport-*, sentry-*

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

settlemint-archive/agent-marketplace

crew-claude

Complete development workflow for Claude Code

5 0
Explore
settlemint-archive/agent-marketplace

crew-codex

Complete development workflow for Codex

5 0
Explore
settlemint-archive/agent-marketplace

workflow-improver

Evaluate session using OpenAI eval-skills framework (Outcome/Process/Style/Efficiency). Analyzes session transcript vs Claude Code config to score performance and generate improvement recommendations. Creates GitHub issue with rubric scores and actionable plan.

5 0
Explore
settlemint-archive/agent-marketplace

git-workflow

Git workflow commands: commit, branch, pr, push, sync, review, fixup, update-pr, commit-push, clean-gone, status, merge. Use with command argument.

5 0
Explore
settlemint-archive/agent-marketplace

vercel-composition-patterns

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.

5 0
Explore
settlemint-archive/agent-marketplace

sharp-edges

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun, misuse-resistant, secure defaults, API usability, dangerous configuration.

5 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results