- Home
- Skills
- Code Quality & Review
- Auto Code Reviewer
Auto Code Reviewer
Three-pass automated code review that catches error handling gaps, structural issues, and naming problems — then auto-fixes everything before code reaches the user.
$5
Works with the AI Agents you already use
Auto Code Reviewer
Example session with this skill installed
Review this processUserBatch script. It's getting too long, has no error handling for the API calls, and I think it's making too many requests inside the loop. Clean it up.
- Read your context and instructions
- Compiled the auto code reviewer
Refactored processUserBatch:
- Extracted
fetchLabelsto look up labels once before the loop. - Wrapped Google API calls in try/catch with context-aware error messages.
- Reduced function from 52 to 24 lines by extracting
validateUserData. - Removed 3 unused imports and a commented-out block.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does Code Reviewer is an automated quality gate that runs on every piece of code your AI agent generates or modifies. It executes a rigorous three-pass review process, then auto-fixes every issue it finds before presenting the code to you. Pass 1 — Error Handling & Robustness Wraps API calls and file I/O in try/catch with descriptive error states. Adds null checks, validates inputs, and handles empty datasets gracefully. Ensures no unhandled promise rejections or silent failures. Pass 2 — Structure & Cleanliness Enforces a strict 30-line limit per function via automated refactoring. Extracts repeated logic into shared utilities, pre-fetches lookup data to eliminate N+1 query patterns, and removes dead code and unused imports. Pass 3 — Naming & Simplification Renames vague variables (data, temp, result) to intent-revealing names. Replaces complex conditionals with well-named booleans. Simplifies nested logic and extracts magic numbers into named constants. Why buy this? Unlike standard prompting, Code Reviewer doesn't just suggest improvements — it identifies issues and auto-fixes them. Every piece of code passes through all three review passes before you ever see it. Think of it as a senior engineer reviewing every line, built directly into your AI workflow.
- May struggle with highly fragmented codebases or proprietary DSLs.
- Cannot run actual code to verify logic; performs static structural analysis only.
- Strict 30-line limit may require manual overrides for complex UI layouts.
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 any payment.
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
1 use
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 7 months ago
Permissions
No special permissions declared or detected