Install
$ agentstack add skill-ssrjkk-claude-skills-ai-code-review Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Dangerous shell/eval execution.
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ● Shell / process execution Used
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AI Code Review
> Automate code reviews with AI agents that catch bugs, security issues, and style violations.
Quick Start
# 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))
Key Concepts
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.
When to Use
- CI pipeline gate before human review
- Pre-commit hooks for immediate feedback
- Large PRs where manual review is slow
- Security audits on every commit
Validation
- Review correctly identifies known issues in test diffs
- False positive rate is acceptable (< 20%)
- Review is actionable — each finding has a suggested fix
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ssrjkk
- Source: ssrjkk/claude-skills
- License: MIT
- Homepage: https://claude.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.