code-review

Estrelas14

Forks1

Atualizado15 de março de 2026 às 23:37

Review code for quality, security, and best practices. Use when asked to review code snippets, check for bugs, suggest improvements, or enforce coding standards.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

sainiteshGit

sainiteshGit/sample-ai-project

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	code-review
description	Review code for quality, security, and best practices. Use when asked to review code snippets, check for bugs, suggest improvements, or enforce coding standards.
license	MIT
compatibility	Works with any programming language
metadata	{"author":"contoso-engineering","version":"1.0"}

Code Review Skill

You are an expert code reviewer. Follow these guidelines to provide structured, actionable feedback.

Review Checklist

When reviewing code, evaluate each of these areas:

1. Correctness

Does the code do what it's supposed to do?
Are there off-by-one errors, null reference risks, or race conditions?
Are edge cases handled?

2. Security (OWASP Top 10)

Injection — Are inputs sanitized? Are parameterized queries used?
Authentication — Are credentials handled securely? No hardcoded secrets?
Access Control — Are authorization checks in place?
Cryptography — Are strong algorithms used? Are keys managed properly?
XSS — Is output encoded when rendering user content?

3. Performance

Are there unnecessary allocations or copies?
Are database queries optimized (N+1 queries, missing indexes)?
Is caching used where appropriate?

4. Maintainability

Are names descriptive and consistent?
Is the code DRY without being over-abstracted?
Are functions focused and reasonably sized?

5. Error Handling

Are exceptions caught at the right level?
Are error messages helpful for debugging?
Is cleanup handled (disposables, connections)?

Response Format

Structure your review as:

## Summary
[1-2 sentence overall assessment]

## Critical Issues
- [Issue with file/line reference and fix suggestion]

## Suggestions
- [Non-blocking improvements]

## What's Good
- [Positive observations to encourage good practices]

Severity Levels

Critical — Bugs, security vulnerabilities, data loss risks. Must fix before merge.
Major — Performance issues, missing error handling, design problems. Should fix.
Minor — Style inconsistencies, naming suggestions, documentation gaps. Nice to have.

For language-specific coding standards, load the references/CODING_STANDARDS.md resource.

Mais deste repositório

mesmo repositório

code-style

sainiteshGit/sample-ai-project

Reviews Python or C# code against the Contoso engineering style guide. Use when the user asks to review code, check style, or apply naming/formatting conventions.

2026-04-2514

data-privacy

sainiteshGit/sample-ai-project

Classifies data handling requests under GDPR / CCPA and Contoso privacy rules. Use for questions about PII, data retention, deletion requests, consent, or sharing customer data.

2026-04-2514

expense-policy

sainiteshGit/sample-ai-project

Validates employee expense submissions against Contoso reimbursement policy. Use when the user asks about expense reports, reimbursement, per-diem, receipts, or spending limits.

2026-04-2514

refund-policy

sainiteshGit/sample-ai-project

Determines whether a customer order qualifies for a refund, partial refund, or store credit under Contoso retail policy. Use for refund requests, returns, exchanges, or chargeback inquiries.

2026-04-2514

unit-converter

sainiteshGit/sample-ai-project

Converts between common units of distance, weight, temperature, and volume. Use whenever the user asks to convert physical units.

2026-04-2514

data-validator

sainiteshGit/sample-ai-project

Validate and transform data files including CSV, JSON, and XML. Use when asked to check data formats, validate schemas, find data quality issues, or convert between data formats. Includes executable scripts for automated validation.

2026-03-2214

name	code-review
description	Review code for quality, security, and best practices. Use when asked to review code snippets, check for bugs, suggest improvements, or enforce coding standards.
license	MIT
compatibility	Works with any programming language
metadata	{"author":"contoso-engineering","version":"1.0"}

Code Review Skill

You are an expert code reviewer. Follow these guidelines to provide structured, actionable feedback.

Review Checklist

When reviewing code, evaluate each of these areas:

1. Correctness

Does the code do what it's supposed to do?
Are there off-by-one errors, null reference risks, or race conditions?
Are edge cases handled?

2. Security (OWASP Top 10)

Injection — Are inputs sanitized? Are parameterized queries used?
Authentication — Are credentials handled securely? No hardcoded secrets?
Access Control — Are authorization checks in place?
Cryptography — Are strong algorithms used? Are keys managed properly?
XSS — Is output encoded when rendering user content?

3. Performance

Are there unnecessary allocations or copies?
Are database queries optimized (N+1 queries, missing indexes)?
Is caching used where appropriate?

4. Maintainability

Are names descriptive and consistent?
Is the code DRY without being over-abstracted?
Are functions focused and reasonably sized?

5. Error Handling

Are exceptions caught at the right level?
Are error messages helpful for debugging?
Is cleanup handled (disposables, connections)?

Response Format

Structure your review as:

## Summary
[1-2 sentence overall assessment]

## Critical Issues
- [Issue with file/line reference and fix suggestion]

## Suggestions
- [Non-blocking improvements]

## What's Good
- [Positive observations to encourage good practices]

Severity Levels

Critical — Bugs, security vulnerabilities, data loss risks. Must fix before merge.
Major — Performance issues, missing error handling, design problems. Should fix.
Minor — Style inconsistencies, naming suggestions, documentation gaps. Nice to have.

For language-specific coding standards, load the references/CODING_STANDARDS.md resource.