Initialize Ai Navigation logo

Initialize Ai Navigation

OrganizationPopular
Unity-Technologies
initialize-ai-navigation

Sets up and configures Unity AI Navigation, including NavMesh surfaces, agents, obstacles, and links. Use when the user asks about navigation meshes, pathfinding, patrol routes, or obstacle avoidance.

Overview

PublisherUnity-Technologies
Repositoryskills
Skill nameinitialize-ai-navigation
Stars
1K
Forks
61
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by Unity-Technologies on GitHub. Read the source before you install it.

Installation

Install the Initialize Ai Navigation 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.
    https://github.com/Unity-Technologies/skills/tree/main/skills/initialize-ai-navigation
  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/Unity-Technologies/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/initialize-ai-navigation .claude/skills/initialize-ai-navigation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Initialize Ai Navigation 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 Initialize Ai Navigation 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 Initialize Ai Navigation 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.

Determine what the user needs and guide them through navigation setup. See navigation-system.md for expanded component details, API notes, code recipes, and troubleshooting.

Passing C# to eval

eval compiles a statement block, not a file. Two consequences, both of which cause a compile error rather than a warning:

  • No using directives. The compiler reads using UnityEngine; as a resource-disposal statement and rejects it (CS0210).
  • Types must be fully qualified. A bare AssetDatabase or Volume does not resolve (CS0246 / CS0103), and a bare Object is ambiguous with object (CS0104).

Where a snippet below is written as a file — with usings, for readability, or because it is meant to be saved into the project — qualify the types before passing it to eval.

Routing Logic

User SaysInterpretation
"add navigation" / "set up nav"Full setup: NavMeshSurface + bake + NavMeshAgent
"make this character navigate"Add NavMeshAgent, ensure NavMesh exists
"add pathfinding"NavMeshAgent + movement script
"agent won't move" / "path not found"Troubleshoot — see Troubleshooting Decision Tree in reference
"avoid obstacles"NavMeshObstacle with carving or avoidance
"connect two areas" / "jump across"NavMeshLink between areas
"patrol between points"NavMeshAgent + patrol script
"click to move"NavMeshAgent + raycast click-to-move script
"animate the character while navigating"Couple Animator with NavMeshAgent
"different agent sizes"Configure agent types in Navigation window
"areas and costs" / "restrict areas"NavMesh area types, modifiers, and agent area masks

Workflow

0. Package Installation Check

Before doing anything else, verify that com.unity.ai.navigation is installed. If it's missing, add it to Packages/manifest.json under dependencies — Unity resolves it when the Editor next regains focus, and this needs no Editor connection:

json
"com.unity.ai.navigation": "<current 2.x version>"

Don't invent the version string. Read the current one from the Unity registry — https://packages.unity.com/com.unity.ai.navigation lists every published version — or copy the version an adjacent Unity package in this manifest already uses. A version that doesn't exist makes Unity fail resolution silently, so a wrong guess looks like nothing happened.

Proceed only once it's confirmed installed. If you have a live Editor to run C# in, see navigation-system.md for the Client.Add equivalent.

1. Pre-Flight: Assess Current Navigation Setup

Before making changes, inspect what already exists:

  1. Find the existing navigation components. With a connected Editor, query the live scene for NavMeshSurface, NavMeshAgent, NavMeshObstacle, NavMeshLink and NavMeshModifier — see the unity-cli skill for driving a running Editor. Without one, search the scene and prefab files for those component names.
  2. Check configured agent types via Window > AI > Navigation > Agents tab.
  3. Summarize ALL detected navigation components before proposing changes.

2. Gather Missing Information

Before creating components, ensure the user has specified: walkable surfaces, agent type/size, agent behavior, obstacles, links, and area/cost requirements. Ask if anything is unclear. See the Information Gathering Checklist in the reference for full details.

3. Planning & Execution

Follow this general order. See the Component Setup Guide in the reference for detailed step-by-step instructions per component:

  1. NavMesh Surface — create the walkable mesh (bake it)
  2. NavMesh Agent — add pathfinding characters
  3. NavMesh Obstacle — add dynamic obstacles
  4. NavMesh Link — connect disconnected NavMesh areas
  5. NavMesh Modifier / Modifier Volume — fine-tune area types
  6. Scripts — movement, patrol, click-to-move, animation coupling (see Common Recipes in reference)

4. Validation

After setup, confirm:

  • NavMesh is baked and visible (blue overlay)
  • NavMeshSurface agent type matches NavMeshAgent agent type
  • Agents have a valid path to their destination
  • Obstacles carve or obstruct correctly
  • Links have both ends connected and Activated is enabled
  • Area masks allow the intended movement
  • No conflicting components (see Mixing Components Guide in reference)
  • If using Rigidbody with NavMeshAgent, Is Kinematic is enabled

5. Final Confirmation

Summarize what was created or changed:

  • NavMesh Surfaces: which GameObject, agent type, geometry mode, bake status
  • NavMesh Agent(s): which GameObject, speed, stopping distance, area mask
  • NavMesh Obstacle(s): which GameObject, shape, carve on/off
  • NavMesh Link(s): start/end, bidirectional, area type
  • Scripts: which scripts attached to which GameObjects
  • Any manual steps required (adjust waypoints, re-bake after scene changes, etc.)

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 Initialize Ai Navigation AI skill do?

Sets up and configures Unity AI Navigation, including NavMesh surfaces, agents, obstacles, and links. Use when the user asks about navigation meshes, pathfinding, patrol routes, or obstacle avoidance.

Why use Initialize Ai Navigation on TypingMind?

Because you install it once and use it with any model. Initialize Ai Navigation 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 Initialize Ai Navigation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Unity-Technologies/skills/tree/main/skills/initialize-ai-navigation. 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 Initialize Ai Navigation?

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 Initialize Ai Navigation?

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

Is the Initialize Ai Navigation AI skill free?

It is published on GitHub by Unity-Technologies. Check the repository for licensing terms. 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 👇