unity-review-quality — unity-review-quality install for AI agents unity-review-quality, oh-my-unity, community, unity-review-quality install for AI agents, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Code Review Agents specializing in Unity project analysis and optimization. unity-review-quality is a skill that analyzes Unity projects, providing a comprehensive report on architecture, performance, best practices, and tech debt, helping developers identify areas for improvement.

Features

Scans Unity projects read-only, analyzing .cs, .prefab, .unity, .asmdef, and .asset files
Grades architecture, performance, best practices, and tech debt on an A–F scale with evidence
Generates a comprehensive HTML report for detailed analysis
Checks Dependency Injection (DI) patterns for optimal architecture
Records file counts for .cs, .prefab, .unity, .asmdef, and .asset files

# Core Topics

cuozg cuozg
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The unity-review-quality skill by cuozg is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for unity-review-quality install for AI agents.

Ideal Agent Persona

Perfect for Code Review Agents specializing in Unity project analysis and optimization.

Core Value

Empowers agents to scan Unity projects read-only, grading architecture, performance, best practices, and tech debt on an A–F scale, generating comprehensive HTML reports with evidence, utilizing file formats like `.cs`, `.prefab`, `.unity`, `.asmdef`, and `.asset`.

Capabilities Granted for unity-review-quality

Onboarding to unfamiliar Unity codebases
Implementing pre-release quality gates for shipped titles
Conducting quarterly tech debt audits for live games

! Prerequisites & Limits

  • Requires read-only access to Unity project files
  • Limited to Unity projects only
  • Grading scale may require customization for specific project needs
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

unity-review-quality

Install unity-review-quality, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

unity-review-quality

Scan a Unity project read-only, grade architecture, performance, best practices, and tech debt on an A–F scale with evidence, and generate a comprehensive HTML report.

When to Use

  • Onboarding to an unfamiliar Unity codebase
  • Pre-release quality gate for a shipped title
  • Quarterly tech debt audit for a live game

Workflow

  1. Scope project — list all .cs, .prefab, .unity, .asmdef, .asset files; record counts
  2. Analyze architecture — check DI patterns, assembly structure, coupling, event systems, singleton count
  3. Analyze performance — scan for hot-path allocations, FindObjectOfType, per-frame GetComponent, excessive coroutines
  4. Evaluate best practices — null handling, serialization safety, test coverage presence, naming conventions
  5. Measure tech debt — TODO/FIXME count, dead code, magic numbers, file length outliers
  6. Grade each category — apply A–F rubric from references/quality-grading-rubric.md
  7. Generate HTML report — use structure from unity-standards/references/quality/html-report-format.md; embed evidence snippets

Rules

  • Read files only — never modify source code or assets
  • Assign one grade per category: Architecture, Performance, Best Practices, Tech Debt
  • Every grade must cite at least one evidence file path + line number
  • F grade requires 3+ CRITICAL violations in that category
  • A grade requires zero violations and positive evidence
  • Include a "Top 5 Priority Fixes" section ranked by severity × frequency
  • Do not average grades into an overall score — list each separately
  • Flag FindObjectOfType calls as performance violations (not architectural)
  • Flag missing .asmdef files in a project > 50 scripts as Architecture WARNING
  • Flag test coverage below 10% (by file count) as Best Practices WARNING
  • Save report to Documents/QualityAudit_{date}.html unless path overridden

Output Format

HTML report file at Documents/QualityAudit_{date}.html with A-F grades per category, evidence table, and prioritized fix list.

Reference Files

  • references/quality-grading-rubric.md — per-category A-F descriptions (loads unity-standards/references/quality/grading-criteria.md for scale + formula)

Load references on demand via read_skill_file("unity-review-quality", "references/{file}") and read_skill_file("unity-standards", "references/quality/grading-criteria.md").

Standards

Load unity-standards for audit criteria. Key references:

  • quality/grading-criteria.md — A-F scale definitions, evidence requirements
  • quality/architecture-audit.md — coupling, layering, assembly structure
  • quality/performance-audit.md — profiler markers, memory, frame budget
  • quality/best-practices-audit.md — Unity API usage, deprecated calls
  • quality/tech-debt-audit.md — TODO density, code duplication, complexity

Load via read_skill_file("unity-standards", "references/quality/<file>").

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is unity-review-quality?

Perfect for Code Review Agents specializing in Unity project analysis and optimization. unity-review-quality is a skill that analyzes Unity projects, providing a comprehensive report on architecture, performance, best practices, and tech debt, helping developers identify areas for improvement.

How do I install unity-review-quality?

Run the command: npx killer-skills add cuozg/oh-my-unity/unity-review-quality. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for unity-review-quality?

Key use cases include: Onboarding to unfamiliar Unity codebases, Implementing pre-release quality gates for shipped titles, Conducting quarterly tech debt audits for live games.

Which IDEs are compatible with unity-review-quality?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for unity-review-quality?

Requires read-only access to Unity project files. Limited to Unity projects only. Grading scale may require customization for specific project needs.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add cuozg/oh-my-unity/unity-review-quality. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use unity-review-quality immediately in the current project.

Related Skills

Looking for an alternative to unity-review-quality or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI