code-reviewer

Reviews session code changes for bugs, race conditions, and quality issues.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/apsulli/gsd-extended --skill code-reviewer-apsulli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/apsulli/gsd-extended/tree/main/.agent/skills/code-reviewer
Command: npx skills add https://github.com/apsulli/gsd-extended --skill code-reviewer-apsulli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Catching bugs, race conditions, and code quality issues before they reach production is hard, especially in fast-moving AI-assisted coding sessions where changes accumulate quickly. This Skill performs a focused review of only the code written or modified in the current session, producing a prioritized, actionable report. ## Core Features & Use Cases - Session-Scoped Review: Analyzes only files changed in the current session rather than the entire codebase, keeping feedback relevant and fast. - Bug and Race Condition Detection: Scans for React hook dependency issues, stale closures, memory leaks, Firestore check-then-act patterns, non-atomic updates, and async ordering hazards. - Prioritized Findings Report: Outputs a severity-ranked table (CRITICAL/HIGH/MEDIUM/LOW) with file and line references, explanations, and concrete suggested fixes. - Use Case: After a coding session that adds a new Firebase-backed dashboard feature, invoke the review to catch an unsubscribed onSnapshot listener and a non-atomic counter update before committing. ## Quick Start Ask the AI to review the code written in this session for bugs, race conditions, and quality issues.

Frequently Asked Questions about code-reviewer

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

FAQPage Schema
How do I review code changes from the current session?▼

Invoke the code review after your coding session and it will identify files created or modified during that session, then analyze only those changes for bugs, race conditions, and quality issues. It does not scan the entire codebase.

What bugs does a React code review typically catch?▼

Common findings include missing useEffect dependencies, stale closures, missing cleanup functions causing memory leaks, unhandled null props, and incorrect keys in mapped lists. Each issue is reported with file, line, and a suggested fix.

How are Firestore race conditions detected in code review?▼

The review flags read-modify-write sequences and check-then-act patterns that are not wrapped in transactions or atomic operations like increment(). It recommends atomic Firestore updates to prevent data corruption from concurrent writes.

Does this review the entire codebase or just recent changes?▼

It reviews only the code written or modified during the current session, plus related components that interact with those changes. Reviewing the entire codebase is explicitly out of scope.

What severity levels are used in the review report?▼

Findings are classified as CRITICAL (data corruption, security, crashes), HIGH (memory leaks, race conditions, major bugs), MEDIUM (quality issues that could cause bugs), and LOW (style or minor optimizations).