Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state…
Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images. Use before building any place, material, vehicle, sky or lighting condition, and again when judging your own screenshots.
Set up player input in Unreal Engine 5 with Enhanced Input: Input Actions, Input Mapping Contexts, modifiers and triggers, adding the mapping context, and binding actions by ETriggerEvent. Use when wiring movement/look/jump input, creating IA/IMC assets, binding in C++ or Blueprints, or when the user mentions Enhanced…
Use when creating, modifying, retargeting, rigging, constraining, or validating skeletal animation through UE-MCP. Covers native UE 5.8 IK Rig and Retargeter authoring, the Control Rig begin/read/apply/bake loop, generic contact locks, per-rig anatomical and mirrored-axis discovery, quaternion keying, deterministic…
Use when authoring or modifying Unreal Blueprint assets through ue-mcp. Covers the read-then-write discipline, node/pin wiring, component (SCS) hierarchy, variables, interfaces, compilation, and the difference between pin defaults and linked inputs. Pulls in any time the user asks to create, edit, or inspect a…
Use when writing or modifying native C++ UCLASSes in an Unreal project via ue-mcp. Covers createcppclass → writecppfile → livecodingcompile loop, when to use build vs Live Coding, and the addmoduledependency workflow. Pulls in any time the user asks to write a new native class, add a UPROPERTY, or implement a…
Field manual for driving Unreal Engine 5.7 / 5.8 through MCP. Engine-level gotchas, silent-fail edges, crash patterns, and the call sequences that actually work — applicable regardless of which MCP server you're using (Epic's official ModelContextProtocol plugin, custom servers, or anything else). Auto-trigger when…
Houdini 仿真工作流指南:Pyro/RBD/FLIP/Vellum 的标准搭建流程。 Use when AI needs to: (1) set up simulations, (2) configure DOPs, (3) build Pyro/RBD/FLIP/Vellum setups. Houdini only (runpython).
A guided tool for creating custom tools in the ArtClaw system, which connects an AI assistant with digital-content applications. It can package an existing skill, generate a script, or combine tools, then preview and save the result.
Fix silent tool registration failures in UEMCP when Python function parameters use modern union syntax (str | None) instead of Optional[str]. Use when: (1) MCP tools silently lose optional parameters in their JSON schema, (2) new ops module parameters all show as required when they should be optional, (3) manifest…
VERA ships a mobile and performance doctor: a small set of read-only tools that audit the project for things that hurt — or outright break — a mobile build. Use it proactively whenever the user is about to package for mobile, complains about device crashes, or worries about GPU/shader cost.
You are working inside PCW, Ezequiel's Unreal Engine project (an Aztec-themed action game, with cyberpunk experiments). Treat the facts below as ground truth so you don't rediscover them every session. When you learn something new and durable, remember it (the Memory plugin) so this knowledge keeps growing.
VERA can set the cinematic mood of the level currently open in the Unreal editor in a single command — perfect right before taking a showcase screenshot or recording a demo of a game. Pick a mood, capture the beauty shot, then restore the level.
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…
Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.
Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
Read and filter Unreal Engine log output from disk for any UE project. Auto-detects the project from the nearest .uproject, merges entries across all concurrently-active log files (editor session, standalone clients), and surfaces only recently-active sessions by default. Use when diagnosing a silent failure after a…
Author Unreal Engine AngelScript tests using the Hazelight FUnitTest / FIntegrationTest framework. Use when adding regression coverage for .as gameplay code, scaffolding a new Test function, deciding between a unit test and an integration test (which requires a /Content/Testing/.umap) — or deciding whether a test even…
Author Hazelight AngelScript (.as) gameplay code for Unreal Engine 5.x projects using the Hazelight UnrealEngine-Angelscript fork. AngelScript looks like UE C++ but differs in load-bearing ways — no #include, no GENERATEDBODY, default keyword for sub-object config, float is 64-bit, RPCs are reliable by default, no…