code-reviewer
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
86
86%
Does it follow best practices?
Impact
84%
1.78xAverage score across 6 eval scenarios
Passed
No known issues
Evaluation results
100%
90%Authentication Service Security Review
PR security risk analysis with JSON output
JSON output format
100%
100%
Complexity score present
0%
100%
Risk severity categories
0%
100%
File review order
0%
100%
Hardcoded secret detected
0%
100%
SQL injection detected
0%
100%
TypeScript any type detected
0%
100%
Console statements detected
0%
100%
ESLint suppression detected
0%
100%
TODO/FIXME comments detected
0%
100%
95%
25%Order Processing Module Quality Assessment
Code quality structural smell detection
JSON output format
100%
100%
Total smells reported
0%
0%
Quality score present
50%
100%
God class detected
100%
100%
Long function detected
33%
100%
Too many parameters detected
100%
100%
High complexity detected
100%
100%
Magic numbers detected
0%
100%
God class threshold in message
100%
100%
Parameter count in smell message
100%
100%
100%
31%Reporting Pipeline PR — Formal Review Report
Full review report with verdict and pre-computed analyses
Markdown report created
100%
100%
PR analysis JSON created
60%
100%
Quality analysis JSON created
80%
100%
Verdict present
40%
100%
Score present
100%
100%
Verdict matches score
20%
100%
Action items section
100%
100%
Issue summary section
60%
100%
PR statistics incorporated
100%
100%
Review order present
40%
100%
24%
-16%Data Pipeline Quality Assessment
Language-scoped deep nesting and large file detection
Language flag used
0%
0%
JSON flag used
0%
100%
Output file created
100%
100%
Large file detected
0%
0%
Deep nesting detected
100%
0%
Missing error handling detected
0%
0%
Unused imports detected
100%
0%
Magic numbers detected
0%
100%
Nesting threshold in message
62%
0%
File line count in message
0%
0%
100%
56%Feature Branch Risk Review
Branch-specific PR analysis with commit validation
Base/head flags used
0%
100%
JSON flag used
0%
100%
Output file created
100%
100%
Complexity score present
0%
100%
Risk categories present
50%
100%
Hardcoded credentials detected
66%
100%
SQL injection detected
80%
100%
Commit message validation present
41%
100%
File review order present
0%
100%
Repository path used
100%
100%
88%
34%Notification Service Code Review
TypeScript async antipatterns and language standards review
Report generator used
0%
100%
No pre-computed flags
0%
0%
Markdown format flag used
0%
100%
Output file flag used
0%
100%
Markdown report created
100%
100%
Verdict present
0%
100%
Score present
100%
100%
Floating promise issue reported
100%
100%
TypeScript any type reported
100%
100%
Action items section
100%
100%
Review order present
100%
100%
- Repository
- alirezarezvani/claude-skills
- Commit
967fe01
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.