skills.rest
novel-jp
novel-jpOFFICIAL
Explore all skills by this author →
GitHub

learn-ac-code-review

Review AI-generated code diffs for intent, tests, performance, security, and maintainability issues.

Updated Mar 12, 2026
Search Tags:#code review#maintainability#security review#test coverage#ai collaboration#performance analysis
One-click install
npx skills add https://github.com/novel-jp/projsight-plugin --skill learn-ac-code-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: learn-ac-code-review
Source: https://github.com/novel-jp/projsight-plugin/tree/main/skills/learn-ac-code-review
Command: npx skills add https://github.com/novel-jp/projsight-plugin --skill learn-ac-code-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill teaches you how to review AI-generated code with the same rigor as a professional code review, so you can catch hidden trade-offs, missing tests, performance regressions, security risks, and maintainability issues before they reach production.

Core Features & Use Cases

  • Intent Review: Ask why a specific implementation was chosen and uncover unspoken trade-offs or safer alternatives.
  • Test Coverage Review: Identify missing edge cases such as empty inputs, nonexistent paths, permission errors, symbolic links, and deeply nested data.
  • Performance and Security Review: Spot blocking synchronous I/O, unnecessary work, path traversal risks, TOCTOU issues, and inconsistent error handling.
  • Use Case: Review a generated file utility and systematically find at least one issue in each of the five review dimensions before discussing fixes.

Quick Start

Ask the AI to generate code for a small utility, then review the diff for intent, tests, performance, security, and maintainability issues.

Frequently Asked Questions about learn-ac-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review AI-generated code for hidden trade-offs and security risks?▼

Review AI-generated code by applying systematic diff analysis across intent, tests, performance, security, and maintainability to surface defects and hidden trade-offs before merge.

What security issues should I look for during an AI code review?▼

During an AI code review, look for path traversal risks, TOCTOU issues, inconsistent error handling, and permission errors to identify critical security vulnerabilities in the generated diff.

How do I find missing test coverage and edge cases in AI-generated utilities?▼

Find missing test coverage by validating edge cases like empty inputs, nonexistent paths, symbolic links, and deeply nested data through targeted questioning during the code review process.

What is the best way to analyze performance regressions in AI-generated code?▼

Analyze performance regressions by spotting blocking synchronous I/O and unnecessary work during the diff inspection, ensuring the AI-generated code meets performance requirements before shipping.

How do I systematically review a file utility generated by AI?▼

Systematically review a generated file utility by performing iterative inspection across five dimensions—intent, tests, performance, security, and style—to find and log at least one issue in each category.

Why does AI-generated code require an intent review before merging?▼

AI-generated code requires an intent review to ask why a specific implementation was chosen, uncovering unspoken trade-offs or safer alternatives that the AI may have omitted in the initial diff.

Related Skills

Explore More Software Engineering Skills→
KarlinskySKarlinskyS

requesting-code-review

Gather git change data and dispatch a reviewer subagent with a structured checklist.

Community
Intermediate
Keiji-MiyakeKeiji-Miyake

qa

Generate TEST_PLAN.md and automated tests from feature specs.

Community
Intermediate
raybargasraybargas

Global Coding Style

Detect and fix coding style violations across multi-language repositories.

Community
Basic
0x1337c0d30x1337c0d3
3

race-conditions

Identify and analyze race condition vulnerabilities in source code for TOCTOU and shared-state issues.

Community
Advanced