Ue Niagara Custom Modules logo

Ue Niagara Custom Modules

Community
kevinpbuckley
ue-niagara-custom-modules

Build Niagara scratch-pad modules and emitter interactions in Unreal Engine 5.8. Use for custom particle attributes, attribute readers, collision-driven secondary effects, texture sampling, or reusable rain and waterfall behaviors.

Overview

Publisherkevinpbuckley
Repositoryunreal-engine-skills
Skill nameue-niagara-custom-modules
Stars
89
Forks
9
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kevinpbuckley on GitHub. Read the source before you install it.

Installation

Install the Ue Niagara Custom Modules AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kevinpbuckley/unreal-engine-skills/tree/master/skills/core/ue-niagara-custom-modules
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kevinpbuckley/unreal-engine-skills.git /tmp/unreal-engine-skills
mkdir -p .claude/skills
cp -r /tmp/unreal-engine-skills/skills/core/ue-niagara-custom-modules .claude/skills/ue-niagara-custom-modules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ue Niagara Custom Modules in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ue Niagara Custom Modules on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ue Niagara Custom Modules is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Niagara custom modules

Use ue-niagara-vfx for the system/emitter model. Add a custom module when a built-in module cannot express the required behavior clearly, or when a repeated graph deserves one consistent interface. A scratch-pad module is useful for local exploration; promote stable, shared behavior to a reusable Niagara module only when more than one effect needs it.

Stage and parameter map

Choose the stage by when the value must change: emitter setup for emitter-level state, Particle Spawn for each new particle, Particle Update for per-frame motion, and an event handler for event-driven secondary particles. Inputs should state units and meaning; outputs should write the intended namespace and attribute. Inspect upstream and downstream writes to the same attribute. Niagara stack order matters: a later module can replace position, velocity, size, or color and make an earlier calculation appear broken.

Keep a custom graph narrow. For example, a follower module can read leader-particle position through a Particle Attribute Reader, combine it with a per-particle offset, and write the follower position. Define the leader emitter binding and behavior when no valid leader exists. Ensure both emitters use compatible simulation targets and that the data is available at the stage where it is read. Do not assume an emitter name, particle ID, or event stream is valid merely because the graph compiles.

Event-driven secondary effects

For rain splashes or other contact effects, a collision event can spawn a smaller secondary emitter at the contact position. Confirm the selected event handler, source emitter, persistent-ID requirements where applicable, and CPU/GPU support in the current UE version and emitter setup. Bound events per frame and particles per event; dense rain should not create an unbounded splash system. Use collision position and normal to orient a splash or ripple, then let size and opacity decay independently. If GPU simulation or platform constraints make events unsuitable, use an alternate visual method rather than depending on an unsupported event path.

For a waterfall, separate large-scale flowing shape from falling droplets, foam, splashes, and optional caustic or refraction details only where each contributes to the intended view. A moving UV material may carry most of the flow at lower particle cost. Collision-driven accents belong near contact surfaces; their spawn rate should reflect visible water contact, not the entire waterfall area.

Texture sampling is another data source, not a required asset pipeline. Map particle position or authored UV into the texture's coordinate space, sample the intended channel, and decide whether it drives spawn density, color, size, or motion. Verify UV origin, wrapping, filtering, and missing-texture behavior. Prefer a simple analytic mask when it serves the same purpose.

Verification

Test the module at zero and high spawn rates, with missing inputs and changing emitter transforms. Watch both the written attributes and the rendered result. If particles stop moving after adding a mesh-following or location module, look for a later position or velocity write before retuning forces.

References & source material

  • UE 5.8 source: Engine/Plugins/FX/Niagara/Source/Niagara/Classes/NiagaraScript.h (UNiagaraScript).
  • UE 5.8 source: Engine/Plugins/FX/Niagara/Source/Niagara/Classes/NiagaraDataInterfaceParticleRead.h (UNiagaraDataInterfaceParticleRead).
  • UE 5.8 source: Engine/Plugins/FX/Niagara/Source/Niagara/Classes/NiagaraDataInterfaceTexture.h (UNiagaraDataInterfaceTexture).

Frequently asked questions

What does the Ue Niagara Custom Modules AI skill do?

Build Niagara scratch-pad modules and emitter interactions in Unreal Engine 5.8. Use for custom particle attributes, attribute readers, collision-driven secondary effects, texture sampling, or reusable rain and waterfall behaviors.

Why use Ue Niagara Custom Modules on TypingMind?

Because you install it once and use it with any model. Ue Niagara Custom Modules is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ue Niagara Custom Modules in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/unreal-engine-skills/tree/master/skills/core/ue-niagara-custom-modules. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ue Niagara Custom Modules?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ue Niagara Custom Modules?

As many as you like. As long as a model supports skills, you can use Ue Niagara Custom Modules with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ue Niagara Custom Modules AI skill free?

It is published on GitHub by kevinpbuckley. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇