navmesh
Navigation mesh generation and pathfinding skill for game AI. Enables creation and configuration of navigation meshes, pathfinding queries, dynamic obstacles, and navigation agent setup across Unity, Unreal, and Godot engines.
What this skill does
# Navigation Mesh Skill
Comprehensive navigation mesh generation and pathfinding implementation for game AI systems across multiple engines.
## Overview
This skill provides capabilities for creating, configuring, and utilizing navigation meshes for AI pathfinding. It covers navmesh generation, agent configuration, dynamic obstacles, off-mesh links, and runtime navigation queries.
## Capabilities
### NavMesh Generation
- Configure navmesh build settings
- Define walkable areas and surfaces
- Set up area types with costs
- Generate runtime navmeshes
### Agent Configuration
- Configure agent radius and height
- Set movement parameters
- Define avoidance priorities
- Configure step height and slopes
### Pathfinding
- Query paths between points
- Handle partial paths
- Implement path smoothing
- Support hierarchical pathfinding
### Dynamic Navigation
- Handle dynamic obstacles
- Implement navmesh carving
- Update navmesh at runtime
- Handle moving platforms
### Off-Mesh Links
- Create jump links
- Configure drop connections
- Handle ladders and teleports
- Set up one-way paths
## Prerequisites
### Unity
```csharp
// Built-in: Package Manager > AI Navigation
// Install: com.unity.ai.navigation
```
### Unreal Engine
```cpp
// Enable NavigationSystem module in Build.cs
PublicDependencyModuleNames.AddRange(new string[] {
"NavigationSystem",
"AIModule"
});
```
### Godot
```
# Enable NavigationServer2D/3D in project settings
# Use NavigationRegion2D/3D and NavigationAgent2D/3D nodes
```
## Usage Patterns
### Unity Navigation Setup
```csharp
// NavMeshAgent configuration
using UnityEngine;
using UnityEngine.AI;
public class AINavigation : MonoBehaviour
{
[Header("Navigation Settings")]
[SerializeField] private float moveSpeed = 3.5f;
[SerializeField] private float angularSpeed = 120f;
[SerializeField] private float stoppingDistance = 0.5f;
private NavMeshAgent _agent;
private Transform _target;
private void Awake()
{
_agent = GetComponent<NavMeshAgent>();
ConfigureAgent();
}
private void ConfigureAgent()
{
_agent.speed = moveSpeed;
_agent.angularSpeed = angularSpeed;
_agent.stoppingDistance = stoppingDistance;
_agent.autoBraking = true;
}
public void SetDestination(Vector3 destination)
{
if (NavMesh.SamplePosition(destination, out NavMeshHit hit, 2f, NavMesh.AllAreas))
{
_agent.SetDestination(hit.position);
}
}
public void SetTarget(Transform target)
{
_target = target;
}
private void Update()
{
if (_target != null)
{
SetDestination(_target.position);
}
}
public bool HasReachedDestination()
{
if (!_agent.pathPending)
{
if (_agent.remainingDistance <= _agent.stoppingDistance)
{
if (!_agent.hasPath || _agent.velocity.sqrMagnitude == 0f)
{
return true;
}
}
}
return false;
}
public bool IsPathValid()
{
return _agent.hasPath && _agent.pathStatus == NavMeshPathStatus.PathComplete;
}
}
// Dynamic NavMesh Obstacle
using UnityEngine;
using UnityEngine.AI;
public class DynamicObstacle : MonoBehaviour
{
private NavMeshObstacle _obstacle;
private void Awake()
{
_obstacle = GetComponent<NavMeshObstacle>();
_obstacle.carving = true;
_obstacle.carvingMoveThreshold = 0.1f;
_obstacle.carvingTimeToStationary = 0.5f;
}
public void EnableCarving(bool enable)
{
_obstacle.carving = enable;
}
}
// Off-Mesh Link Setup
using UnityEngine;
using UnityEngine.AI;
public class JumpLink : MonoBehaviour
{
[SerializeField] private Transform startPoint;
[SerializeField] private Transform endPoint;
[SerializeField] private bool bidirectional = false;
private OffMeshLink _link;
private void Awake()
{
_link = gameObject.AddComponent<OffMeshLink>();
_link.startTransform = startPoint;
_link.endTransform = endPoint;
_link.biDirectional = bidirectional;
_link.autoUpdatePositions = true;
}
}
// NavMesh Surface Runtime Baking
using UnityEngine;
using Unity.AI.Navigation;
public class RuntimeNavMesh : MonoBehaviour
{
private NavMeshSurface _surface;
private void Awake()
{
_surface = GetComponent<NavMeshSurface>();
}
public void RebuildNavMesh()
{
_surface.BuildNavMesh();
}
public void UpdateNavMesh()
{
_surface.UpdateNavMesh(_surface.navMeshData);
}
}
```
### Unreal Engine Navigation Setup
```cpp
// AINavigationComponent.h
#pragma once
#include "CoreMinimal.h"
#include "Components/ActorComponent.h"
#include "NavigationSystem.h"
#include "AINavigationComponent.generated.h"
UCLASS(ClassGroup=(Custom), meta=(BlueprintSpawnableComponent))
class MYGAME_API UAINavigationComponent : public UActorComponent
{
GENERATED_BODY()
public:
UAINavigationComponent();
UFUNCTION(BlueprintCallable, Category = "Navigation")
bool MoveToLocation(FVector Destination);
UFUNCTION(BlueprintCallable, Category = "Navigation")
bool MoveToActor(AActor* TargetActor);
UFUNCTION(BlueprintCallable, Category = "Navigation")
void StopMovement();
UFUNCTION(BlueprintCallable, Category = "Navigation")
bool HasReachedDestination() const;
UFUNCTION(BlueprintCallable, Category = "Navigation")
FVector GetRandomReachablePoint(float Radius) const;
protected:
virtual void BeginPlay() override;
UPROPERTY(EditAnywhere, BlueprintReadWrite, Category = "Navigation")
float AcceptanceRadius = 50.0f;
UPROPERTY(EditAnywhere, BlueprintReadWrite, Category = "Navigation")
bool bStopOnOverlap = true;
UPROPERTY(EditAnywhere, BlueprintReadWrite, Category = "Navigation")
bool bUsePathfinding = true;
private:
class AAIController* AIController;
class UNavigationSystemV1* NavSystem;
};
// AINavigationComponent.cpp
#include "AINavigationComponent.h"
#include "AIController.h"
#include "NavigationSystem.h"
#include "NavFilters/NavigationQueryFilter.h"
UAINavigationComponent::UAINavigationComponent()
{
PrimaryComponentTick.bCanEverTick = false;
}
void UAINavigationComponent::BeginPlay()
{
Super::BeginPlay();
APawn* Pawn = Cast<APawn>(GetOwner());
if (Pawn)
{
AIController = Cast<AAIController>(Pawn->GetController());
}
NavSystem = FNavigationSystem::GetCurrent<UNavigationSystemV1>(GetWorld());
}
bool UAINavigationComponent::MoveToLocation(FVector Destination)
{
if (!AIController) return false;
FAIMoveRequest MoveRequest;
MoveRequest.SetGoalLocation(Destination);
MoveRequest.SetAcceptanceRadius(AcceptanceRadius);
MoveRequest.SetStopOnOverlap(bStopOnOverlap);
MoveRequest.SetUsePathfinding(bUsePathfinding);
FNavPathSharedPtr Path;
AIController->MoveTo(MoveRequest, &Path);
return Path.IsValid();
}
bool UAINavigationComponent::MoveToActor(AActor* TargetActor)
{
if (!AIController || !TargetActor) return false;
FAIMoveRequest MoveRequest;
MoveRequest.SetGoalActor(TargetActor);
MoveRequest.SetAcceptanceRadius(AcceptanceRadius);
MoveRequest.SetStopOnOverlap(bStopOnOverlap);
MoveRequest.SetUsePathfinding(bUsePathfinding);
FNavPathSharedPtr Path;
AIController->MoveTo(MoveRequest, &Path);
return Path.IsValid();
}
void UAINavigationComponent::StopMovement()
{
if (AIController)
{
AIController->StopMovement();
}
}
bool UAINavigationComponent::HasReachedDestination() const
{
if (!AIController) return false;
return AIController->GetMoveStatus() == EPathFollowingStatus::Idle;
}
FVector UAINavigationComponent::GetRandomReachablePoint(float Radius) const
{
FNavLocation RandomPoint;
if (NavSystem && NavSystem->GetRandomReacRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.