Hz New Project Creation logo

Hz New Project Creation

Organization
meta-quest
hz-new-project-creation

Scaffolds new Meta Quest and Horizon OS projects with recommended settings for Unity, Unreal, Android/Spatial SDK, or WebXR. Use when creating a new Quest app from scratch.

Overview

Publishermeta-quest
Repositoryagentic-tools
Skill namehz-new-project-creation
Stars
195
Forks
17
Bundled files
5
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by meta-quest on GitHub. Read the source before you install it.

Installation

Install the Hz New Project Creation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/meta-quest/agentic-tools.git /tmp/agentic-tools
mkdir -p .claude/skills
cp -r /tmp/agentic-tools/skills/hz-new-project-creation .claude/skills/hz-new-project-creation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hz New Project Creation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hz New Project Creation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hz New Project Creation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

New Project Creation Skill

Scaffold and configure new Meta Quest projects from scratch. This skill guides you through choosing the right platform and project type, then provides step-by-step setup instructions with recommended settings optimized for Quest hardware.

When to Use This Skill

Use this skill when you need to:

  • Create a brand-new project targeting Meta Quest (Quest 2, Quest 3, Quest 3S, Quest Pro)
  • Choose between Unity, Unreal Engine, Android/Spatial SDK, or WebXR
  • Configure a project with the correct render settings, SDK versions, and build targets for Quest
  • Set up a project template with recommended architecture and folder structure
  • Understand which platform best fits your application type

Prerequisites

Before creating any Meta Quest project, complete these steps regardless of platform:

  1. Create a Meta developer account -- Sign up at developer.meta.com and create an organization.
  2. Set up your Quest for development -- Enable developer mode in the Meta Horizon app on your phone under your headset's settings.
  3. Enable USB debugging -- Connect your Quest via USB-C, put on the headset, and accept the "Allow USB debugging" prompt.
  4. Use metavr via npx -- The metavr CLI is invoked on demand; no global install required:
    bash
    npx -y metavr --version
    Examples below use the bare metavr command for brevity; if it is not installed globally, replace metavr with npx -y metavr.

Verify your device connection before starting any project:

bash
metavr device list

Decision Tree

When a user wants to create a new Quest project, walk through these questions in order:

Step 1: What Platform?

Ask the user which development platform they prefer or are most experienced with:

  • Unity -- C# scripting, mature XR ecosystem, large asset store
  • Unreal Engine -- C++ and Blueprints, high-fidelity rendering, cinematic tools
  • Android / Spatial SDK -- Kotlin, native Android development, panel-based apps
  • Web / IWSDK / WebXR -- TypeScript, rapid prototyping, browser-based distribution

Step 2: What Type of Experience?

Ask what kind of application they are building:

TypeDescriptionBest Platforms
Fully Immersive VRComplete virtual environment, no passthroughUnity, Unreal
Mixed RealityBlend virtual content with real world via passthroughUnity, Unreal, Spatial SDK
2D Panel AppFlat UI panel floating in the user's spaceSpatial SDK, Unity
Hybrid (2D + 3D)Panels with optional 3D spatial contentSpatial SDK

Step 3: What Features?

Identify which Quest-specific features the project needs:

  • Hand tracking -- Controller-free interaction using hand and finger detection
  • Eye tracking -- Gaze-based interaction and foveated rendering (Quest Pro, Quest 3)
  • Passthrough -- Camera-based view of the real world with virtual overlays
  • Multiplayer -- Networked multi-user experiences
  • Spatial audio -- 3D positional audio with HRTF spatialization
  • Scene understanding -- Room mesh, plane detection, semantic labels
  • Spatial anchors -- Persistent world-locked content placement

Platform Comparison

PlatformBest ForLanguage3D EngineLearning CurveDistribution
UnityGames, complex 3D, social VRC#UnityModerateQuest Store, App Lab
Unreal EngineHigh-fidelity visuals, cinematicC++ / BlueprintUnrealSteepQuest Store, App Lab
Spatial SDKAndroid panel apps, hybrid appsKotlinCustom ECSModerateQuest Store, App Lab
IWSDK / WebXRWeb-based, quick prototypingTypeScriptThree.jsLowWeb, PWA, Store (via Bubblewrap)

Platform Selection Guidelines

  • Choose Unity when you need the broadest XR feature support, a large ecosystem of third-party assets, or your team already knows C#.
  • Choose Unreal when visual fidelity is the top priority, you need cinematic sequences, or your team is experienced with C++ or Blueprints.
  • Choose Spatial SDK when building panel-based Android apps, hybrid 2D+3D experiences, or leveraging existing Android/Kotlin expertise.
  • Choose IWSDK/WebXR when you want the fastest iteration cycle, browser-based distribution, or are prototyping an idea before committing to a native engine.

After Choosing a Platform

Once the user has selected a platform, refer to the corresponding reference guide for detailed, step-by-step project setup:

  • Unity (Quest / VR) -- MUST use the metavr_unity_setup MCP tool to create the project. Do NOT run Unity CLI directly. Do NOT walk the user through manual Package Manager / XR Plug-in Management steps. See Unity Project Setup. Manual fallback at unity-project-manual.md only when the MCP tool is unavailable. (Note: this guidance applies to Quest/VR Unity projects only — for non-VR Unity projects use Unity Hub as normal.)
  • Unreal Engine -- Unreal Project Setup
  • Android / Spatial SDK -- Android Project Setup
  • Web / IWSDK / WebXR -- Web Project Setup

Each reference covers:

  1. Required tool and SDK versions
  2. Project creation steps
  3. Recommended project settings for Quest
  4. Build and deployment workflow
  5. Testing and iteration workflow

Gotchas

These are common pitfalls when setting up new Quest projects.

  • Android API level mismatch -- Quest requires a minimum Android API level of 29 (Android 10) and a target API level of 32+. Setting the wrong API level is the most common reason builds fail to install on the device. Unity defaults may not match these requirements — always verify in Player Settings > Other Settings.
  • ARM64 only, no x86 -- Quest devices are ARM64 (aarch64). If your build pipeline targets x86 or includes x86 native libraries, the APK will install but crash immediately on launch. In Unity, ensure "Target Architectures" has only ARM64 checked. In Android Studio, verify your ABI filters.
  • Gradle version compatibility -- Meta's Android/Spatial SDK samples often pin specific Gradle and AGP (Android Gradle Plugin) versions. Using a newer Gradle version than the samples expect can cause obscure build failures. Match the versions from the sample project's gradle-wrapper.properties and build.gradle.
  • Unity version matters -- Not every Unity version is compatible with the latest Meta XR SDK. Check the Meta XR SDK release notes for the supported Unity version range. Using an unsupported Unity version causes cryptic C# compilation errors or missing XR subsystem errors at runtime.
  • Vulkan vs. OpenGL ES -- Quest 3 supports Vulkan and it is recommended for best performance. Quest 2 also supports Vulkan but some older Meta XR SDK features had Vulkan-only bugs. If you see rendering artifacts on Quest 2 with Vulkan, try OpenGL ES 3.0 as a fallback and file a bug.
  • Missing Android manifest permissions -- Quest-specific features (hand tracking, passthrough, scene understanding, eye tracking) require explicit manifest permissions. The app will silently fail to access these features without the correct permissions. They are not added automatically by the SDK.
  • Forgetting to set the package name before first build -- Changing the package name after the first install on a device can cause data loss or install failures. Set the correct com.company.appname package name before your first build and deploy.
  • Unreal Engine: OpenXR vs. OVRPlugin -- Unreal supports both the OpenXR backend and the legacy OVRPlugin backend for Quest. New projects should use OpenXR. Mixing plugins in the same project causes undefined behavior.

Common Post-Setup Tasks

After the project is created and configured on any platform, these tasks are typically needed:

Register the App on the Developer Dashboard

Create an application entry at developer.meta.com to obtain an App ID. This is required for platform features like entitlement checks, multiplayer, achievements, and store submission.

Set Up Version Control

Initialize a Git repository and configure .gitignore for the chosen platform:

bash
git init
# Use a platform-appropriate .gitignore (Unity, Unreal, Android, or Node.js)

First Build and Deploy

Build the project and install it on a connected Quest device:

bash
# After building, install the APK
metavr app install path/to/build.apk

# Launch the app
metavr app launch com.yourcompany.yourapp

# Monitor logs during first run
metavr log --tag yourapp

Performance Baseline

On first successful run, verify the application meets baseline performance targets:

  • Frame rate: 72 Hz minimum (90 Hz or 120 Hz preferred on Quest 3)
  • Frame timing: Consistent frame times without spikes
  • Thermal: No thermal throttling warnings during normal use

References

Skill References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hz New Project Creation AI skill do?

Scaffolds new Meta Quest and Horizon OS projects with recommended settings for Unity, Unreal, Android/Spatial SDK, or WebXR. Use when creating a new Quest app from scratch.

Why use Hz New Project Creation on TypingMind?

Because you install it once and use it with any model. Hz New Project Creation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hz New Project Creation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/meta-quest/agentic-tools/tree/main/skills/hz-new-project-creation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hz New Project Creation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hz New Project Creation?

As many as you like. As long as a model supports skills, you can use Hz New Project Creation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hz New Project Creation AI skill free?

Yes. It is published on GitHub by meta-quest under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇