SkillAgentSearch skills...

everything-claude-unity

The ultimate Claude Code toolkit for Unity — 20 AI agents, 22 slash commands, 41 skills, and safety hooks for AI-assisted Unity game development. Drop-in, production-ready.

Install / Use

npx skills add XeldarAlz/everything-claude-unity

Installs into whichever agent you are using.

About this skill
📦

Other

Other agent config

Quality Score

81/100

Supported Platforms

Claude Code

Our assessment of everything-claude-unity

everything-claude-unity scores 81/100 on our quality scale, 744th of 965 AI & Machine Learning skills we index.

Its Other is 21 KB long, well organised into 60 sections with 19 code examples: a thorough specification that gives an agent plenty to work with.

It has 24 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
6/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-09-28 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 95/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

everything-claude-unity compared with similar skills

All 4 of these similar skills score higher than everything-claude-unity; compare them before choosing.

SkillScoreStarsUpdatedFormat
everything-claude-unity (this skill)by XeldarAlz81246mo agoOther
claude-memby thedotmack100100.5ktodayCLAUDE.md
Agent-Reachby Panniantong10097.1k6d agoCLAUDE.md
Understand-Anythingby Egonex-AI10086.2k1d agoCLAUDE.md
headroomby headroomlabs-ai10075.3ktodayCLAUDE.md

Frequently asked questions

How do I install everything-claude-unity?
Run npx skills add XeldarAlz/everything-claude-unity. The install tabs above show the steps for each supported agent.
Which AI agents does everything-claude-unity work with?
It is written for Claude Code, as a Other file. Other agents that read the same format can often use it too.
Is everything-claude-unity safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 95/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is everything-claude-unity still maintained?
The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

everything-claude-unity

License: MIT GitHub stars GitHub release Claude Code Unity PRs Welcome Discussions

English | 中文 | 日本語 | 한국어 | Español | Português | Deutsch | Français | Türkçe

The ultimate Claude Code toolkit for Unity game development.

A production-ready, plug-and-play system that gives Claude Code deep Unity expertise — from writing performant C# to building scenes, profiling performance, and triggering iOS/Android builds — all through natural language.

Built for solo indie mobile game developers. Drop it into any Unity project and it works.

Why this works?

  • Drop-in, zero-config — one install.sh and Claude Code knows Unity inside out
  • 20 specialized agents across haiku/sonnet/opus tiers with automatic complexity routing
  • 22 safety hooks that prevent scene/meta corruption, silent data loss, and GC spikes before they happen
  • MVS architecture built-in — VContainer + MessagePipe + UniTask patterns enforced by rules and templates
  • MCP-native — scene building, profiling, and iOS/Android builds triggered from chat
  • 60+ automated tests and reproducible benchmarks so the toolkit itself stays honest

What You Get

| Component | Count | Purpose | |-----------|-------|---------| | Agents | 20 | Specialized sub-agents across 3 model tiers (haiku/sonnet/opus) | | Commands | 22 | Slash commands like /unity-workflow, /unity-ralph, /unity-team, /unity-skillify | | Skills | 41 | Knowledge modules for Unity systems, gameplay patterns, and mobile genres | | Hooks | 22 | Safety net, quality gates, notifications, session persistence, auto-learning | | Rules | 5 | C# coding standards, performance rules, MVS architecture patterns | | Scripts | 8 | Validation tools for meta files, code quality, serialization, architecture | | Templates | 10 | C# templates for MVS pattern (Model, View, System, LifetimeScope, Message) | | Tests | 60+ | Automated test suite for hooks, state, cross-validation, templates, skills | | Benchmarks | 4 | Quality evaluation scenarios with structural comparison |


Highlights

/unity-workflow — Full Development Pipeline

A structured 4-phase pipeline for any feature: Clarify requirements, Plan the implementation, Execute with specialized agents, Verify with automated review + fix loop.

/unity-workflow "add a combo scoring system with multipliers and visual feedback"

/unity-prototype — One Prompt to Playable

Describe a mechanic, and Claude writes the C# scripts, builds the scene via MCP, sets up physics layers, configures the camera, and verifies it compiles.

/unity-prototype "2D platformer with wall jumping and dash"

/unity-ralph — Relentless Verify-Fix Loop

Runs the verify-fix loop persistently — refuses to stop until the project is clean or hits the safety limit. Up to 30 effective verification passes with stall detection.

/unity-ralph --max-iterations 10

/unity-team — Parallel Agent Orchestration

Spawn multiple agents simultaneously — coder + tester + reviewer working in parallel for faster development.

/unity-team --build "add health system with damage and healing"
/unity-team --security "audit the save system"
/unity-team --build --quick "add a basic score counter"

What's New in v1.3.0

  • Smart Model Routing — complexity heuristics auto-select haiku/sonnet/opus agents based on task signals
  • Persistent State — session data survives reboots in .claude/state/ with structured schema
  • Plan Critic — unity-critic agent challenges your plans before execution (built into /unity-workflow)
  • Security Auditing — unity-security-reviewer catches PlayerPrefs secrets, hardcoded keys, insecure saves
  • Benchmarking — measure agent quality with reproducible evaluation scenarios
  • Skillify — /unity-skillify auto-generates skills from your accumulated session learnings
  • Multi-channel Notifications — Discord, Slack, OS-native with event filtering and rate limiting
  • Hardened CI — cross-validation, tool restriction checks, template and skill quality gates

Verify-Fix Loop

The unity-verifier agent automatically reviews your code changes, fixes safe issues (missing [FormerlySerializedAs], uncached GetComponent, ?. on Unity objects), and re-verifies — up to 3 iterations until clean. Built into /unity-workflow and available as an optional step in /unity-feature and /unity-prototype.

Hook Profiles

Hooks are organized into three profiles. Set UNITY_HOOK_PROFILE to control which hooks run:

| Profile | What's Active | Best For | |---------|--------------|----------| | minimal | Safety hooks only (block scene/meta corruption, editor guards, pre-compact) | CI pipelines, experienced developers | | standard | Safety + quality warnings + session persistence + stop validation (default) | Daily development | | strict | Everything: GateGuard, cost tracking, auto-learning, build analysis | New projects, learning, auditing |

UNITY_HOOK_PROFILE=strict          # Enable all hooks including GateGuard
UNITY_HOOK_PROFILE=minimal         # Only critical safety hooks
DISABLE_UNITY_HOOKS=1              # Bypass all hooks entirely
UNITY_HOOK_MODE=warn               # Downgrade blocks to warnings
DISABLE_HOOK_BLOCK_SCENE_EDIT=1    # Disable a specific hook

Quick Start

Prerequisites

  • Claude Code installed
  • Unity 2021.3 LTS or later
  • unity-mcp (optional but recommended for full pipeline)

Install

# From your Unity project root:
git clone https://github.com/XeldarAlz/everything-claude-unity.git /tmp/ecu
/tmp/ecu/install.sh --project-dir .
rm -rf /tmp/ecu

Or manually:

git clone https://github.com/XeldarAlz/everything-claude-unity.git
cp -r everything-claude-unity/.claude your-unity-project/.claude
chmod +x your-unity-project/.claude/hooks/*.sh

Upgrade / Uninstall

# Upgrade to latest (preserves your customizations, creates backup)
./upgrade.sh --project-dir .

# Preview changes before upgrading
./upgrade.sh --project-dir . --dry-run

# Clean removal (with backup)
./uninstall.sh --project-dir .

Setup Unity MCP (Recommended)

The MCP bridge gives Claude direct control over the Unity Editor — scene building, profiling, builds, and more.

  1. In Unity: Window > Package Manager > + > Add package from git URL
  2. Paste: https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main
  3. Open Window > MCP for Unity and click Start Server
  4. Claude Code auto-connects via .claude/settings.json

First Run

cd your-unity-project
claude

# Verify installation:
/unity-doctor         # Check MCP, hooks, project structure

# Start working:
/unity-audit          # Full project health check
/unity-workflow       # Full pipeline: clarify → plan → execute → verify
/unity-prototype      # Rapid prototype a game mechanic

Agents

Code Agents

| Agent | Model | What It Does | |-------|-------|-------------| | unity-coder | opus | Implements features with Unity subsystem awareness, loads relevant skills | | unity-coder-lite | sonnet | Lightweight variant for simple additions (fields, methods, straightforward components) | | unity-fixer | opus | Diagnoses bugs using Unity-specific patterns (missing refs, execution order, coroutine lifecycle) | | unity-fixer-lite | sonnet | Quick fixes for obvious issues (typos, missing imports, simple errors) | | unity-reviewer | sonnet | Code review checking serialization safety, GC in hot paths, lifecycle ordering | | unity-shader-dev | opus | HLSL/ShaderGraph development optimized for mobile GPUs, live testing via MCP |

Orchestration Agents

| Agent | Model | What It Does | |-------|-------|-------------| | unity-verifier | opus | Verify-fix loop: reviews changes, auto-fixes safe issues, re-verifies (max 3 iterations) | | unity-prototyper | opus | End-to-end prototyping: writes code + builds scene + physics + camera |

MCP-Powered Agents

| Agent | Model | What It Does | Key MCP Tools | |-------|-------|-------------|---------------| | unity-scene-builder | opus | Builds scenes from descriptions | manage_scene, batch_execute | | unity-test-runner | sonnet | Writes + runs tests, reports results | run_tests, read_console | | unity-build-runner | sonnet | Configures and triggers builds | manage_build, manage_packages | | unity-optimizer | opus | Profiles and fixes performance issues | manage_profiler, manage_graphics |

Hybrid Agents

| Agent | Model | What It Does | |-------|-------|-------------| | unity-ui-builder | opus | Builds UI screens with code + visual setup via MCP | | unity-network-dev | opus | Implements multiplayer with Netcode/Mirror/Photon/Fish-Net | | unity-migrator | sonnet | Unity version and render pipeline migration |

Commands support --quick (routes to sonnet lite agent) and --thorough (routes to opus) flags. See docs/MODEL-ROUTING.md for the full routing table.


Commands

Full Pipeline

/unity-workflow <description>   Clarify → Plan → Execute → Verify (the recommended workflow)

Daily Workflow

/unity-feature <description>    Plan + implement a feature (--quick for simple tasks)
/unity-fix <bug or error>       Diagnose and fix a bug (--quick for obvious fixes)
/unity-prototype <mechanic>     One prompt to playable prototype
/unity-scene <description>      Build a scene via MCP
/unity-shader <description>     Create shaders with live preview
/unity-ui <screen description>  Build UI with visual setup
/unity-network <framework>      Set up multiplayer

Quality Gates

/unity-review [scope]           Code review (--thorough for deep analysis)
/unity-optimize                 Profile via MCP + fix bottlenecks
/unity-test                     Write + run tests via MCP
/unity-audit                    Full project health check
/unity-profile                  Deep profiling session

Orchestration

/unity-ralph [options]          Persistent verify-fix loop (refuses to stop until clean)
/unity-team <--preset|--custom> Parallel agents (coder + tester + reviewer simultaneously)
/unity-interview <topic>        Deep Socratic requirements interview before coding
/unity-learn [subcommand]       Session analytics: review, extract patterns, draft skills

Project Lifecycle

/unity-init                     Scan project + generate CLAUDE.md
/unity-build                    Configure + trigger builds
/unity-migrate                  Plan version/pipeline migration
/unity-doctor                   Diagnostic health check (MCP, hooks, project structure)

Hooks

22 hooks across 5 lifecycle events, organized by profile level.

Blocking Hooks — PreToolUse (minimal profile)

| Hook

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars24
CategoryAI
Updated5mo ago
Forks3

Languages

Shell

Trust signals

95/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 info