code-reviewer_skill

This skill reviews frontend and backend code for quality, tests, security, and performance to help you ship reliable software faster.

Makefile

0

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill shaul1991/shaul-agents-plugin --skill code-reviewer

SKILL.md8.1 KB

Overview

This skill is a Code Reviewer Agent that performs automated and manual reviews of frontend and backend code. It focuses on code quality, test coverage, security, and performance to catch issues early and improve maintainability. The agent produces actionable comments, checklist-driven review reports, and recommended automated checks.

How this skill works

The agent inspects pull requests and code diffs against a checklist covering readability, maintainability, tests, security, and performance. It runs or suggests automated tools (linters, type checks, test coverage, security scanners) and creates clear review comments: suggestions, questions, praises, issues, and nitpicks. It outputs a structured review summary and required/optional fixes for maintainers to act on.

When to use it

During pull request review for frontend or backend changes
When enforcing test coverage and quality gates before merge
To identify security or performance regressions early
As part of CI to run automated checks and produce human-readable findings
When onboarding new contributors to keep code standards consistent

Best practices

Use the provided checklist for every PR and adapt it to the project context
Prefer constructive comments: explain impact and propose concrete fixes
Run automated tools (ESLint, Prettier, type checks, coverage, security scans) in CI before manual review
Require at least one reviewer and a self-review from the author prior to assignment
Record review results and required fixes in a short, scannable review summary

Example use cases

Front-end PR: check component responsibilities, props typing, re-rendering, and accessibility issues
Back-end PR: validate API behavior, database queries, transaction handling, and N+1 problems
CI integration: fail CI when linting, type checks, or coverage thresholds are not met
Security sweep: verify input validation, auth/authorization checks, and sensitive data handling before release
Performance audit: flag heavy operations, memory leaks, and suggest caching or query optimization

FAQ

Use linters and formatters (ESLint, Prettier), TypeScript compiler checks, unit test coverage (Jest), and security scanners (npm audit, Snyk). Integrate these into CI for immediate feedback.

How are review priorities determined?

Issues are categorized as required (blocking), suggested (non-blocking improvements), or praise. Required items cover correctness, security, and failing tests; suggestions improve maintainability and performance.