- Home
- Skills
- Code Quality & Review
- Code Reviewer Pro — PR & Security Standards
More screenshots
Works with the AI Agents you already use
Code Reviewer Pro — PR & Security Standards
Deep severity-ranked code & PR reviews with security, performance checks and ready-to-apply fixes
$9
Code Reviewer Pro — PR & Security Standards
Example session with this skill installed
- Read your context and instructions
- Compiled the code reviewer pro
Review Summary
The component has several high-impact issues around performance, missing dependencies, and a serious security gap on the delete action. It is not production-ready in its current form.
Risk Level: High
Recommendation: Request Changes
Findings
Critical
Unauthenticated destructive action
Location: Delete button
Issue: The delete button fires a fetch to /api/delete/${user.id} with no authentication, CSRF protection, or confirmation. Any visitor can trigger deletions.
Evidence
<button onClick={() => fetch(/api/delete/${user.id})}>Delete
Fix
const handleDelete = async (id: string) => {
if (!confirm('Are you sure?')) return;
await fetch(/api/delete/${id}, {
method: 'DELETE',
headers: { Authorization: Bearer ${token} },
credentials: 'include'
});
};
High
Missing dependency in useEffect
Location: useEffect
Issue: The effect depends on both users and search but only lists search. When the parent passes a new users array the filtered list will be stale.
Evidence
useEffect(() => {
setFiltered(users.filter(u => u.name.toLowerCase().includes(search.toLowerCase())));
}, [search]);
Fix
useEffect(() => {
setFiltered(users.filter(u => u.name.toLowerCase().includes(search.toLowerCase())));
}, [users, search]);
Expensive filter on every keystroke without memoization
Location: useEffect + filter
Issue: Filtering the full list on every character typed will become expensive with larger datasets.
Fix: Prefer useMemo for the filtered result instead of effect + state, or debounce the search input.
Medium
Missing alt text and loading state on images
Location
Issue: Accessibility and layout-shift problems.
Fix: Add alt={user.name} and consider a placeholder or skeleton.
Low / Nits
Prefer type="search" on the input for better mobile keyboards.
Consider extracting the list item into its own memoized component.
Strengths
Clean functional component structure
Good use of controlled input for search
Simple and readable mapping logic
Suggested Next Steps
Add authentication + confirmation to the delete action (Critical).
Fix the useEffect dependency array and switch to useMemo for filtering.
Add basic accessibility attributes and consider virtualization if the list can grow large.
Connects securely to your tools. The creator never sees your data.
About this skill
Turn any AI agent into a senior staff engineer for code reviews.
This skill delivers production-grade reviews that focus on real risk — bugs, security holes, performance bottlenecks, and maintainability issues. Every finding is ranked by severity, backed by exact code evidence, and paired with a concrete fix.
What buyers get
- Severity-ordered findings (Critical → High → Medium → Low)
- Exact code quotes + ready-to-apply fixes
- Clear recommendation: Approve / Request Changes / Block
- Strengths section so good patterns get repeated
- Language-aware guidance for React/TypeScript, Python, Go and more
Best for
- Reviewing pull requests before merge
- Auditing components or services for production readiness
- Security-focused or performance-focused reviews
- Teams that want consistent, high-signal feedback instead of vague “looks good”
Works with any SKILL.md-compatible agent (Claude Code, Cursor, Codex CLI, VS Code Copilot, Gemini CLI, etc.). Just install and say “review this” or “review this PR”.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
- Works best when you provide the full code or a clear diff. Very large files or entire repositories may need to be reviewed in sections.
- Does not execute or run the code — it performs static analysis based on the text you paste.
- Language and framework guidance is strongest for JavaScript/TypeScript/React, Python, and Go. Other languages still receive a solid general review.
- Cannot access private repositories or external links unless you paste the relevant code.
- Style and architectural opinions are intentional and may differ from your team’s existing conventions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected