driving-unreallisted

Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot, taking viewport or off-screen renders, auditing or compiling blueprints, or doing asset hygiene (find/move/rename/delete/fix-up redirectors). Teaches which tools to chain, in what order, the verification checkpoints, and the UE 5.x traps that silently no-op or corrupt state. Routes through the MCP server named "unreal-ai-connection" (tools are exposed as mcp__unreal-ai-connection__<tool>; confirm with list_tools). Trigger phrases: "Unreal", "Unreal Engine", "UE5", "UE 5.7", "build a level", "populate the level", "spawn an actor", "place actors", "apply a material", "material instance", "set up a sequencer shot", "cinematic", "screenshot the viewport", "render the scene", "photo to Unreal", "compil
NAJEMWEHBE/unreal-ai-connection · ★ 6 · AI & Automation · score 75

Install: claude install-skill NAJEMWEHBE/unreal-ai-connection

# Driving Unreal Engine via the unreal-ai-connection MCP tools This skill is the know-how layer for the `unreal-ai-connection` plugin. The plugin exposes ~105 UE editor-automation tools; this file tells you **how to operate them** — the chaining order, the verification checkpoints, and the failure modes. Deep step-by-step recipes and the full UE-quirk table live in [`reference.md`](reference.md); read it when executing a specific workflow. Tools are called as `mcp__unreal-ai-connection__<name>`. Below, names are written bare for brevity. ## Before you touch any tool 1. **Confirm the bridge is live.** The UE plugin binds `127.0.0.1:18888`. A cold editor launch takes ~2 minutes to bind; warm is seconds. Call `list_tools` first — if it returns the catalog, you are connected. Do not assume a tool exists; the live `list_tools` output is the source of truth. 2. **Establish a clean baseline.** For anything that places actors, plan an idempotent re-run: prefix your actor labels (e.g. `Test_*`) and start the workflow by deleting that prefix via `find_actors_by_class` + `delete_actor`, so repeated attempts don't pile up duplicates. ## Cross-cutting operating patterns (apply to every workflow) These rules matter more than any single recipe. Internalize them. - **Actor targeting is hybrid.** Actor-targeting tools accept either a display label or an FName. Label is tried first. If a label is ambiguous you get an `ambiguous_actor` error listing candidate FNames — ret