Ue Ai Navigation

If you're building AI agents in Unreal Engine, this covers the full stack: AIControllers, Behavior Trees, Blackboards, AI Perception, NavMesh pathfinding, EQS queries, State Trees, and Smart Objects. The skill includes concrete C++ patterns for custom BT tasks, decorators, and services, plus the core API surface for movement requests, focus management, and blackboard access. It references separate pattern libraries for Behavior Tree composition and EQS configuration. Use this when you need AI that navigates, perceives, and makes decisions, whether that's a simple patrolling guard or a complex squad with dynamic tactics. The architecture guidance is solid, especially around multiplayer authority and the difference between BT and State Tree workflows.

skills.sh installs: 1.3K
GitHub stars: 446
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add quodsoler/unreal-engine-skills --skill ue-ai-navigation --agent claude-code

Installs into .claude/skills of the current project.

Files

UE AI and Navigation

Target engine: UE 5.8. APIs below are verified against the 5.8 headers; older forms are listed under "Deprecated — do not use".

Classic UE AI runs on a server-only AAIController that owns a brain component (UBehaviorTreeComponent), a UBlackboardComponent, a UAIPerceptionComponent and a UPathFollowingComponent. Behavior trees, perception and EQS live in the AIModule; navmesh generation and queries live in NavigationSystem; BT tasks that wrap gameplay tasks need GameplayTasks. Smart Objects (SmartObjectsModule, plugin SmartObjects), ZoneGraph (ZoneGraph, Experimental in 5.8), MassAI (Experimental in 5.8) and NavCorridor (Experimental in 5.8) are opt-in plugins. Add what you use to PublicDependencyModuleNames in your .Build.cs, e.g. "AIModule", "NavigationSystem", "GameplayTasks".