unreal-engine-developer
Expert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level design, asset management, gameplay programming, and visual development.
What this skill does
# Unreal Engine Developer & Technical Artist
## Overview
This skill enables complete game development in Unreal Engine 5 through agentic coding. It provides expertise in:
- **MCP Integration** - Control Unreal Editor via Model Context Protocol
- **Python Automation** - Editor scripting and pipeline automation
- **Blueprint Development** - Visual scripting and node graph manipulation
- **C++ Programming** - Engine extension and gameplay systems
- **Technical Art** - Materials, shaders, VFX, and procedural content
- **Level Design** - World building, lighting, and environment art
## MCP Server Setup
### Option 1: runreal/unreal-mcp (Recommended - No Plugin Required)
Uses Unreal's built-in Python Remote Execution. Supports full Unreal Python API.
**Prerequisites:**
- Unreal Engine 5.4+
- Node.js with npx
**Unreal Editor Setup:**
1. Edit → Plugins → Enable "Python Editor Script Plugin"
2. Edit → Project Settings → Search "Python" → Enable "Remote Execution"
3. Restart Editor
**MCP Client Config:**
```json
{
"mcpServers": {
"unreal": {
"command": "npx",
"args": ["-y", "@runreal/unreal-mcp"]
}
}
}
```
**Available Tools:**
| Tool | Description |
|------|-------------|
| `editor_run_python` | Execute any Python within Unreal Editor |
| `editor_list_assets` | List all Unreal assets |
| `editor_export_asset` | Export asset to text |
| `editor_get_asset_info` | Get asset info including LOD levels |
| `editor_search_assets` | Search assets by name/path/class |
| `editor_get_world_outliner` | Get all actors with properties |
| `editor_create_object` | Create new actor in world |
| `editor_update_object` | Update existing actor |
| `editor_delete_object` | Delete actor from world |
| `editor_console_command` | Run console command |
| `editor_take_screenshot` | Capture viewport screenshot |
| `editor_move_camera` | Position viewport camera |
### Option 2: chongdashu/unreal-mcp (Plugin-Based)
Provides deeper Blueprint and node graph control via C++ plugin.
**Prerequisites:**
- Unreal Engine 5.5+
- Python 3.12+
- uv package manager
**Installation:**
1. Copy `MCPGameProject/Plugins/UnrealMCP` to your project's Plugins folder
2. Generate Visual Studio project files
3. Build project with plugin
**MCP Client Config:**
```json
{
"mcpServers": {
"unrealMCP": {
"command": "uv",
"args": [
"--directory",
"<path/to/Python>",
"run",
"unreal_mcp_server.py"
]
}
}
}
```
**Additional Capabilities:**
- Create Blueprint classes with custom components
- Add and configure components (mesh, camera, light)
- Manipulate Blueprint node graphs
- Add event nodes (BeginPlay, Tick)
- Create function call nodes and connect them
- Add variables with types and defaults
---
## Python Scripting Reference
### Enable Python in Unreal
1. Edit → Plugins → Enable "Python Editor Script Plugin"
2. Edit → Plugins → Enable "Editor Scripting Utilities"
3. Restart Editor
Unreal embeds Python 3.11.8 - no separate installation needed.
### Core API Patterns
```python
import unreal
# Asset Registry
asset_registry = unreal.AssetRegistryHelpers.get_asset_registry()
assets = asset_registry.get_assets_by_path('/Game/MyFolder', recursive=True)
# Editor Utility
editor_util = unreal.EditorUtilityLibrary()
selected_assets = editor_util.get_selected_assets()
# Actor Operations
world = unreal.EditorLevelLibrary.get_editor_world()
actors = unreal.EditorLevelLibrary.get_all_level_actors()
# Spawn Actor
location = unreal.Vector(0, 0, 100)
rotation = unreal.Rotator(0, 0, 0)
actor = unreal.EditorLevelLibrary.spawn_actor_from_class(
unreal.StaticMeshActor, location, rotation
)
# Set Properties
actor.set_actor_label('MyActor')
actor.set_actor_location(unreal.Vector(100, 200, 300), False, False)
actor.set_actor_rotation(unreal.Rotator(0, 45, 0), False)
# Static Mesh Component
mesh_component = actor.static_mesh_component
mesh_component.set_static_mesh(
unreal.load_asset('/Game/Meshes/MyMesh')
)
# Material Assignment
material = unreal.load_asset('/Game/Materials/MyMaterial')
mesh_component.set_material(0, material)
```
### Asset Management
```python
# Create Asset
factory = unreal.MaterialFactoryNew()
asset_tools = unreal.AssetToolsHelpers.get_asset_tools()
new_material = asset_tools.create_asset(
'M_NewMaterial',
'/Game/Materials',
unreal.Material,
factory
)
# Import Asset
import_task = unreal.AssetImportTask()
import_task.filename = 'C:/path/to/texture.png'
import_task.destination_path = '/Game/Textures'
import_task.automated = True
import_task.save = True
unreal.AssetToolsHelpers.get_asset_tools().import_asset_tasks([import_task])
# Generate LODs for Static Mesh
mesh = unreal.load_asset('/Game/Meshes/MyMesh')
options = unreal.EditorStaticMeshLibrary.generate_lod(mesh, 3)
# Save All
unreal.EditorAssetLibrary.save_loaded_assets([new_material])
```
### Level Operations
```python
# Load Level
unreal.EditorLevelLibrary.load_level('/Game/Maps/MyLevel')
# Save Current Level
unreal.EditorLevelLibrary.save_current_level()
# Get Level Actors by Class
lights = unreal.EditorFilterLibrary.by_class(
unreal.EditorLevelLibrary.get_all_level_actors(),
unreal.PointLight
)
# Duplicate Actors
duplicates = unreal.EditorLevelLibrary.duplicate_actors(
[actor1, actor2],
to_level_duplicate=False
)
# Delete Actors
unreal.EditorLevelLibrary.destroy_actors([actor])
```
### Blueprint Creation via Python
```python
# Create Blueprint
factory = unreal.BlueprintFactory()
factory.set_editor_property('parent_class', unreal.Actor)
asset_tools = unreal.AssetToolsHelpers.get_asset_tools()
blueprint = asset_tools.create_asset(
'BP_MyActor',
'/Game/Blueprints',
unreal.Blueprint,
factory
)
# Add Component
unreal.BlueprintEditorLibrary.add_component(
blueprint,
unreal.StaticMeshComponent
)
# Compile Blueprint
unreal.BlueprintEditorLibrary.compile_blueprint(blueprint)
# Spawn Blueprint Actor
bp_class = unreal.load_class(None, '/Game/Blueprints/BP_MyActor.BP_MyActor_C')
actor = unreal.EditorLevelLibrary.spawn_actor_from_class(
bp_class, unreal.Vector(0,0,0), unreal.Rotator(0,0,0)
)
```
---
## Editor Utility Widgets
Create custom Editor tools with Python + Blueprints:
```python
# Execute Python from Editor Utility Widget
# Use "Execute Python Command" node in Blueprint
# Example: Batch rename selected assets
import unreal
assets = unreal.EditorUtilityLibrary.get_selected_assets()
for asset in assets:
old_name = asset.get_name()
new_name = 'SM_' + old_name # Add prefix
unreal.EditorAssetLibrary.rename_asset(
asset.get_path_name(),
asset.get_path_name().replace(old_name, new_name)
)
```
---
## Coordinate System & Units
| Axis | Direction | Notes |
|------|-----------|-------|
| X | Forward (Red) | Positive = Forward |
| Y | Right (Green) | Positive = Right |
| Z | Up (Blue) | Positive = Up |
**Units:** 1 Unreal Unit = 1 centimeter
**Rotation:** Pitch (Y), Yaw (Z), Roll (X) in degrees
---
## Common Workflows
### 1. Procedural Level Generation
```python
import unreal
import random
def spawn_grid(mesh_path, rows, cols, spacing):
mesh = unreal.load_asset(mesh_path)
for x in range(rows):
for y in range(cols):
loc = unreal.Vector(x * spacing, y * spacing, 0)
actor = unreal.EditorLevelLibrary.spawn_actor_from_class(
unreal.StaticMeshActor, loc, unreal.Rotator(0,0,0)
)
actor.static_mesh_component.set_static_mesh(mesh)
# Random rotation
actor.set_actor_rotation(
unreal.Rotator(0, random.uniform(0, 360), 0), False
)
```
### 2. Batch Material Assignment
```python
import unreal
def assign_material_to_selection(material_path):
material = unreal.load_asset(material_path)
actors = unreal.EditorLevelLibrary.get_selected_level_actors()
for actor in actors:
components = actor.get_componenRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.