code-reviewer

Analyzes pull requests and source code for risks, code smells, and SOLID violations across 14 languages.

2|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/BryanPinheiro77/FinanceBot-BackEnd --skill code-reviewer-bryanpinheiro77
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/BryanPinheiro77/FinanceBot-BackEnd/tree/main/.agents/skills/code-reviewer
Command: npx skills add https://github.com/BryanPinheiro77/FinanceBot-BackEnd --skill code-reviewer-bryanpinheiro77

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and assets (resource) components.

What problem does it solve? Manual code review is slow and inconsistent: reviewers miss hardcoded secrets, SQL injection patterns, swallowed exceptions, and structural smells like god classes or overly complex functions. This Skill automates PR risk assessment, code quality scoring, and review report generation so issues are caught deterministically before merge. ## Core Features & Use Cases - PR Analyzer: Diffs branches with git to score review complexity (1-10), categorize risks (critical/high/medium/low), prioritize file review order, and validate commit messages against conventional commit format. - Code Quality Checker: Scores code 0-100 with letter grades, detecting long functions, god classes, deep nesting, magic numbers, and language-specific smells for C#, Java, C, and more. - Review Report Generator: Combines both analyses into a markdown or JSON verdict (approve, request changes, block) with prioritized action items. - Use Case: Before merging a feature branch in a Java Spring project, run the PR analyzer to flag a hardcoded JDBC credential as critical, then generate a markdown review report to attach to the pull request. ## Quick Start Ask the AI to review the current pull request against the main branch and generate a code quality report for the changed files.

Frequently Asked Questions about code-reviewer

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

FAQPage Schema
How do I analyze a pull request for review complexity and risk?▼

Run pr_analyzer.py with the repository path and branch names, for example: python scripts/pr_analyzer.py . --base main --head feature-branch. It outputs a complexity score from 1-10, risk categorization by severity, and a prioritized file review order.

How to check code quality for code smells and SOLID violations?▼

Run code_quality_checker.py on a file or directory, optionally filtering with --language and --json flags. It scores code 0-100 with a letter grade and reports long functions, god classes, high complexity, magic numbers, and language-specific smells.

What programming languages does automated code review support?▼

The skill supports TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, Java, C, C++, Rust, Ruby, PHP, and Dart. Each language has a dedicated rules file, and C#, Java, and C have dedicated deterministic smell detectors in the scripts.

Does the code review tool require installing Python packages?▼

No, all three scripts are standard-library only and require no pip install. The PR analyzer does require the target directory to be a git repository since it uses git diff and git log commands.

Why does the PR analyzer report no changes detected?▼

This happens when there is no diff between the base and head refs, or when the path is not a git repository. Verify the base branch name exists locally and that you run the script from inside the repository root.

What are the limitations of regex-based code quality analysis?▼

Regex heuristics can produce false positives, such as flagging IDisposable-like names that are not actually disposable, and cannot perform full type or dataflow analysis. Language-specific detectors currently exist only for C#, Java, and C; other languages use universal checks.