Code Reviewer
Automated code review tools for analyzing pull requests, detecting code quality issues, and generating review reports.
How This Skill Is Organized
code-reviewer/
SKILL.md ← you are here (tools + dispatch table)
rules/
universal.md ← security, async, resources, exceptions, performance — all languages
languages/
python.md ← Python-specific rules + idioms
typescript.md ← TypeScript / JavaScript-specific rules + idioms
go.md ← Go-specific rules + idioms
swift.md ← Swift-specific rules + idioms
kotlin.md ← Kotlin-specific rules + idioms
csharp.md ← C# / .NET-specific rules + idioms
java.md ← Java-specific rules + idioms
c.md ← C -specific rules + idioms
cpp.md ← C++ -specific rules + idioms
rust.md ← Rust -specific rules + idioms
ruby.md ← Ruby -specific rules + idioms
php.md ← PHP-specific rules + idioms
dart.md ← Dart / Flutter-specific rules + idioms
Loading order for every review
- This file (
SKILL.md) — tools and thresholds
rules/universal.md — always, for every language
- The matching
languages/*.md — one file based on the extension table below
That is always exactly 2 additional files, regardless of scope.
| Extension(s) |
Load |
.py |
languages/python.md |
.ts, .tsx, .js, .jsx, .mjs |
languages/typescript.md |
.go |
languages/go.md |
.swift |
languages/swift.md |
.kt, .kts |
languages/kotlin.md |
.cs, .csx, .razor, .cshtml |
languages/csharp.md |
.java |
languages/java.md |
.c, .h |
languages/c.md |
.cpp, .cc, .cxx, .hpp, .hh, .hxx |
languages/cpp.md |
.rs |
languages/rust.md |
.rb, .rake, .gemspec, .ru |
languages/ruby.md |
.php, .phtml |
languages/php.md |
.dart |
languages/dart.md |
Tools
PR Analyzer
Analyzes git diff between branches to assess review complexity and identify risks.
# Analyze current branch against main
python scripts/pr_analyzer.py /path/to/repo
# Compare specific branches
python scripts/pr_analyzer.py . --base main --head feature-branch
# JSON output for integration
python scripts/pr_analyzer.py /path/to/repo --json
What it detects (universal — see also language file for language-specific signals):
- Hardcoded secrets (passwords, API keys, tokens, connection strings)
- SQL / query injection patterns
- Debug statements left in production code
- Lint / analyzer suppression annotations
- TODO/FIXME comments
Language-specific detections are defined in each languages/*.md file.
Output includes:
- Complexity score (1-10)
- Risk categorization (critical, high, medium, low)
- File prioritization for review order
- Commit message validation
Code Quality Checker
Analyzes source code for structural issues, code smells, and SOLID violations.
# Analyze a directory
python scripts/code_quality_checker.py /path/to/code
# Analyze specific language
# Valid values: python, typescript, javascript, go, swift, kotlin, csharp, java, c, cpp, rust, ruby, php, dart
python scripts/code_quality_checker.py . --language java
# JSON output
python scripts/code_quality_checker.py /path/to/code --json
Universal thresholds:
| Issue |
Threshold |
| Long function |
>50 lines |
| Large file |
>500 lines |
| God class |
>20 methods |
| Too many params |
>5 |
| Deep nesting |
>4 levels |
| High complexity |
>10 branches |
Language-specific checks are defined in each languages/*.md file.
Review Report Generator
Combines PR analysis and code quality findings into structured review reports.
# Generate report for current repo
python scripts/review_report_generator.py /path/to/repo
# Markdown output
python scripts/review_report_generator.py . --format markdown --output review.md
# Use pre-computed analyses
python scripts/review_report_generator.py . \
--pr-analysis pr_results.json \
--quality-analysis quality_results.json
Verdicts:
| Score |
Verdict |
| 90+ with no high issues |
Approve |
| 75+ with ≤2 high issues |
Approve with suggestions |
| 50-74 |
Request changes |
| <50 or critical issues |
Block |
Adding a New Language
Reviewer guidance (required):
- Create
languages/<name>.md using any existing language file as a template — it must have sections: PR Analyzer Signals, Code Quality Checks, Security, Async, Resource Management, Exception Handling, Performance, Idioms.
- Add the extension row to the dispatch table above.
That is all the agent-driven review needs.
Deterministic analyzer support (optional, recommended): the bundled scripts
only flag a language they explicitly know. To make code_quality_checker.py
score the new language:
- Add the extensions to
LANGUAGE_EXTENSIONS in scripts/code_quality_checker.py (this also adds the --language choice).
- Add
function / class / method regex entries for the language in the same file; otherwise it falls back to the Python patterns.
- Optionally add a
check_<name>_specific_smells(...) detector (see the C#, Java, and C ones) and call it from analyze_file.
- Add
assets/sample_<name>_smells.<ext> + _clean fixtures and commit the expected --json output under expected_outputs/ as a regression guard.
Regression Fixtures
Labelled fixtures live in assets/ with their committed --json output in
expected_outputs/ (C#, Java, and C). Drift from the committed JSON signals a
behaviour change in the analyzer:
python scripts/code_quality_checker.py assets/sample_java_smells.java --json \
| diff - expected_outputs/sample_java_smells_quality.json
1---2name: code-reviewer3description: Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. 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.4metadata:5 source: https://skillmd.com/skills/bestagentkits/code-reviewer6---78# Code Reviewer910Automated code review tools for analyzing pull requests, detecting code quality issues, and generating review reports.1112---1314## How This Skill Is Organized1516```17code-reviewer/18 SKILL.md ← you are here (tools + dispatch table)19 rules/20 universal.md ← security, async, resources, exceptions, performance — all languages21 languages/22 python.md ← Python-specific rules + idioms23 typescript.md ← TypeScript / JavaScript-specific rules + idioms24 go.md ← Go-specific rules + idioms25 swift.md ← Swift-specific rules + idioms26 kotlin.md ← Kotlin-specific rules + idioms27 csharp.md ← C# / .NET-specific rules + idioms28 java.md ← Java-specific rules + idioms29 c.md ← C -specific rules + idioms30 cpp.md ← C++ -specific rules + idioms31 rust.md ← Rust -specific rules + idioms32 ruby.md ← Ruby -specific rules + idioms33 php.md ← PHP-specific rules + idioms34 dart.md ← Dart / Flutter-specific rules + idioms35```3637### Loading order for every review38391. This file (`SKILL.md`) — tools and thresholds402. `rules/universal.md` — always, for every language413. The matching `languages/*.md` — one file based on the extension table below4243That is always exactly **2 additional files**, regardless of scope.4445| Extension(s) | Load |46|---|---|47| `.py` | `languages/python.md` |48| `.ts`, `.tsx`, `.js`, `.jsx`, `.mjs` | `languages/typescript.md` |49| `.go` | `languages/go.md` |50| `.swift` | `languages/swift.md` |51| `.kt`, `.kts` | `languages/kotlin.md` |52| `.cs`, `.csx`, `.razor`, `.cshtml` | `languages/csharp.md` |53| `.java` | `languages/java.md` |54| `.c`, `.h` | `languages/c.md` |55| `.cpp`, `.cc`, `.cxx`, `.hpp`, `.hh`, `.hxx` | `languages/cpp.md` |56| `.rs` | `languages/rust.md` |57| `.rb`, `.rake`, `.gemspec`, `.ru` | `languages/ruby.md` |58| `.php`, `.phtml` | `languages/php.md` |59| `.dart` | `languages/dart.md` |6061---6263## Tools6465### PR Analyzer6667Analyzes git diff between branches to assess review complexity and identify risks.6869```bash70# Analyze current branch against main71python scripts/pr_analyzer.py /path/to/repo7273# Compare specific branches74python scripts/pr_analyzer.py . --base main --head feature-branch7576# JSON output for integration77python scripts/pr_analyzer.py /path/to/repo --json78```7980**What it detects (universal — see also language file for language-specific signals):**81- Hardcoded secrets (passwords, API keys, tokens, connection strings)82- SQL / query injection patterns83- Debug statements left in production code84- Lint / analyzer suppression annotations85- TODO/FIXME comments8687**Language-specific detections** are defined in each `languages/*.md` file.8889**Output includes:**90- Complexity score (1-10)91- Risk categorization (critical, high, medium, low)92- File prioritization for review order93- Commit message validation9495---9697### Code Quality Checker9899Analyzes source code for structural issues, code smells, and SOLID violations.100101```bash102# Analyze a directory103python scripts/code_quality_checker.py /path/to/code104105# Analyze specific language106# Valid values: python, typescript, javascript, go, swift, kotlin, csharp, java, c, cpp, rust, ruby, php, dart107python scripts/code_quality_checker.py . --language java108109# JSON output110python scripts/code_quality_checker.py /path/to/code --json111```112113**Universal thresholds:**114115| Issue | Threshold |116|-------|-----------|117| Long function | >50 lines |118| Large file | >500 lines |119| God class | >20 methods |120| Too many params | >5 |121| Deep nesting | >4 levels |122| High complexity | >10 branches |123124Language-specific checks are defined in each `languages/*.md` file.125126---127128### Review Report Generator129130Combines PR analysis and code quality findings into structured review reports.131132```bash133# Generate report for current repo134python scripts/review_report_generator.py /path/to/repo135136# Markdown output137python scripts/review_report_generator.py . --format markdown --output review.md138139# Use pre-computed analyses140python scripts/review_report_generator.py . \141 --pr-analysis pr_results.json \142 --quality-analysis quality_results.json143```144145**Verdicts:**146147| Score | Verdict |148|-------|---------|149| 90+ with no high issues | Approve |150| 75+ with ≤2 high issues | Approve with suggestions |151| 50-74 | Request changes |152| <50 or critical issues | Block |153154---155156## Adding a New Language157158**Reviewer guidance (required):**1591601. Create `languages/<name>.md` using any existing language file as a template — it must have sections: PR Analyzer Signals, Code Quality Checks, Security, Async, Resource Management, Exception Handling, Performance, Idioms.1612. Add the extension row to the dispatch table above.162163That is all the agent-driven review needs.164165**Deterministic analyzer support (optional, recommended):** the bundled scripts166only flag a language they explicitly know. To make `code_quality_checker.py`167score the new language:1681693. Add the extensions to `LANGUAGE_EXTENSIONS` in `scripts/code_quality_checker.py` (this also adds the `--language` choice).1704. Add `function` / `class` / `method` regex entries for the language in the same file; otherwise it falls back to the Python patterns.1715. Optionally add a `check_<name>_specific_smells(...)` detector (see the C#, Java, and C ones) and call it from `analyze_file`.1726. Add `assets/sample_<name>_smells.<ext>` + `_clean` fixtures and commit the expected `--json` output under `expected_outputs/` as a regression guard.173174---175176## Regression Fixtures177178Labelled fixtures live in `assets/` with their committed `--json` output in179`expected_outputs/` (C#, Java, and C). Drift from the committed JSON signals a180behaviour change in the analyzer:181182```bash183python scripts/code_quality_checker.py assets/sample_java_smells.java --json \184 | diff - expected_outputs/sample_java_smells_quality.json185```