Unreal

Use when the user asks about Unreal Engine 5, UE5 C++, Blueprints, UObject and Actor lifecycle, Gameplay Ability System, Nanite, Lumen, Chaos physics or Unreal replication. Produces Unreal project architecture and C++/Blueprint guidance. Not for Unity (use unity) or custom engine rendering (use render-graph).

45 stars 6 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill unreal
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/game/unreal ~/.claude/skills/unreal

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Unreal Engine Deep Engineering Guide

## Purpose
Unreal Engine is a C++ game engine with a powerful actor-component framework (UObject/AActor), Blueprint visual scripting, the Chaos physics system, and the modern rendering stack built on RenderGraph, Nanite virtualized geometry, and Lumen GI.

## Agent Protocol

### Trigger
"unreal", "unreal engine 5", "UE5", "blueprint", "UObject", "gameplay ability system", "nanite", "lumen", "unreal replication".

### Input Context
- UE version (5.x)
- C++ / Blueprint split
- Target platforms and performance targets

### Output Artifact
C++/Blueprint guidance, config or a profiling plan. No file unless requested.

### Response Format
```
UE: {5.x}
Change: {what and why}
Code: {snippet}
Verify: {Unreal Insights / stat commands}
```

## 1. Engine Architecture

```
Unreal Engine 5
  Modules (UObject-based reflection)
    Core, Engine, Renderer, RHI (D3D12/Vulkan/Metal), Niagara, Chaos
  Engine loop -> UEngine::Tick -> UWorld::Tick -> Actor::Tick
  GWorld: The current UWorld (loaded levels)
```

- `UObject` base: GC (garbage collector), reflection (UFUNCTION/UPROPERTY), serialization.
- `AActor`: spawnable entity; placement via `UWorld::SpawnActor<T>()`.
- `UActorComponent`: reusable behavior attached to actors.

### 1.1 The Game Framework

| Class | Role |
|-------|------|
| `UGameInstance` | Per-process, survives level loads, global save data |
| `UWorld` | The active level + subsystems (GameMode, GameState) |
Read the full skill on GitHub

Details

Skill name
unreal
Path
skills/game/unreal/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Unreal skill do?

Use when the user asks about Unreal Engine 5, UE5 C++, Blueprints, UObject and Actor lifecycle, Gameplay Ability System, Nanite, Lumen, Chaos physics or Unreal replication. Produces Unreal project architecture and C++/Blueprint guidance. Not for Unity (use unity) or custom engine rendering (use render-graph).

How do I install the Unreal skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill unreal. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Unreal popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Build Overview

49

marcoemrich/agentic_coding_lab

Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.

Research & Science

Physics Engine

45

j4flmao/agent-skills

Use when the user asks about a physics engine, collision detection, broad phase, narrow phase, GJK, EPA, constraint solvers, rigid bodies, CCD, character controllers or Jolt/PhysX internals. Produces rigid-body physics design and solver code. Not for engine-specific physics settings (use unity, unreal or godot).

Research & Science

Run Rq

49

marcoemrich/agentic_coding_lab

Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start the Docker batch in the background, monitor progress, run aggregation, and propose findings updates. Trigger when the user says "RQ-N voranbringen", "run-rq", "fill RQ-N", "run RQ-N", "Forschungsfrage N starten", or names a specific RQ-N directory in research/.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.