Ejecuta cualquier Skill en Manus
con un clic
con un clic
Ejecuta cualquier Skill en Manus con un clic
Comenzarai-code-review
Automated code review with AI agents
Estrellas1
Forks0
Actualizado25 de mayo de 2026, 21:36
SKILL.md
readonlyMenú
Automated code review with AI agents
Modern AI-assisted development workflow
AI safety and responsible AI practices
Customizing Claude Code with CLAUDE.md
Using Claude Code CLI for autonomous development
Advanced Claude Code workflows and automation
Using Cursor IDE with advanced AI features
| name | ai-code-review |
| description | Automated code review with AI agents |
| category | ai |
| tags | ["code-review","ai","automation","quality","security"] |
| models | ["sonnet","opus"] |
| version | 1.0.0 |
| created | "2026-05-14T00:00:00.000Z" |
Automate code reviews with AI agents that catch bugs, security issues, and style violations.
# ai_review.py — AI-powered code review script
import subprocess
import json
from anthropic import Anthropic
client = Anthropic()
def get_pr_diff():
result = subprocess.run(
["git", "diff", "main...HEAD"],
capture_output=True, text=True
)
return result.stdout
def review_code(diff: str) -> dict:
response = client.messages.create(
model="claude-sonnet-4-20250514",
system="You are an expert code reviewer. Analyze diffs for:\n"
"1. Security vulnerabilities (XSS, SQLI, CSRF, injection)\n"
"2. Performance issues (N+1 queries, memory leaks)\n"
"3. Logic bugs (off-by-one, race conditions)\n"
"4. Type safety (missing null checks, any usage)\n"
"5. Code quality (dead code, complexity, duplication)\n"
"Rate each category: CRITICAL, WARNING, INFO",
messages=[{
"role": "user",
"content": f"Review this diff:\n```diff\n{diff}\n```"
}],
max_tokens=2000
)
return response.content[0].text
if __name__ == "__main__":
diff = get_pr_diff()
if diff:
print(review_code(diff))
AI code review complements (not replaces) human review. Best for catching common issues, suggesting improvements, and enforcing conventions. Integrate via CI pipeline or pre-commit hooks.