Niagara Emitters logo

Niagara Emitters

Community
kevinpbuckley
niagara-emitters

Niagara emitter color/curve authoring (tint, hue-shift, ColorFromCurve keys), rapid-iteration parameter tuning, and Custom-HLSL scratch-pad authoring (NiagaraEmitterService + NiagaraScratchPadService). Module/renderer CRUD is owned by the engine NiagaraToolsets. Use when the user asks to recolor or hue-shift particles, edit color curves, tune emitter params, or build a scratch-pad/Custom HLSL module. For system-level lifecycle, load niagara-systems.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill nameniagara-emitters
Stars
735
Forks
161
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Niagara Emitters 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/VibeUE/tree/master/Content/Skills/niagara-emitters
  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/VibeUE.git /tmp/VibeUE
mkdir -p .claude/skills
cp -r /tmp/VibeUE/Content/Skills/niagara-emitters .claude/skills/niagara-emitters
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Niagara Emitters 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 Niagara Emitters 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 Niagara Emitters 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.

🧠 Brains complement: IF an unreal-engine-skills-manager tool (external MCP) exists in this session, call it with {action: "load", skill: "niagara-vfx"} for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.

Niagara Emitters Skill

Architecture (read first): VibeUE extends Unreal's native MCP endpoint. Emitter module and renderer CRUD (add/remove/enable/reorder modules, add/remove renderers, set module/renderer inputs, search module scripts) are owned by the engine NiagaraToolsets.* toolsets, called through call_tool. VibeUE's NiagaraEmitterService was trimmed to the color/curve authoring the engine doesn't provide, plus a rapid-iteration-parameter reader.

VibeUE NiagaraEmitterService (this skill) keeps ONLY color/curve authoring + a param reader:

  • set_color_tint — add/set a ScaleColor tint (handles ColorFromCurve automatically)
  • get_color_curve_keys / set_color_curve_keys — read/replace ColorFromCurve keyframes
  • shift_color_hue — hue-rotate a ColorFromCurve while preserving detail (best for recolors)
  • get_rapid_iteration_parameters — read an emitter's rapid-iteration params

NiagaraScratchPadService authors scratch-pad module graphs:

  • Create empty scratch modules on any stage
  • Drop Map Get / Map Set / Op / Custom HLSL nodes
  • Add typed pins, connect pins, declare module inputs/outputs
  • Apply + recompile in one call

For module / renderer CRUD → engine NiagaraToolsets.* via call_tool (discover with list_toolsets / describe_toolset). For system-level operations (create system, add emitters, user params, compile) → engine NiagaraToolsets.* and the niagara-systems skill. Rapid-iteration param writes (set_rapid_iteration_param*) live on NiagaraService (niagara-systems skill).

Loading skills: skills load through the engine's AgentSkillToolset (ListSkills/GetSkills) — there is no vibeue-skills-manager tool. Run VibeUE services with execute_python_code (unreal.<Service>.<method>()); reach engine toolsets with call_tool.


⚠️ CRITICAL: Script Stages

Niagara modules exist in different script stages:

  • EmitterSpawn - Runs once when emitter spawns
  • EmitterUpdate - Runs every frame for emitter
  • ParticleSpawn - Runs once when each particle spawns
  • ParticleUpdate - Runs every frame for each particle

⚠️ Adding modules/renderers is an engine NiagaraToolsets operation — stage still matters

Adding modules and renderers moved to the engine toolsets. Discover the exact tool + schema with describe_toolset and invoke via call_tool:

python
# describe_toolset("NiagaraToolsets.NiagaraToolset_System")   # (find the add-module / add-renderer tools)
# call_tool(toolset_name="NiagaraToolsets.NiagaraToolset_System",
#           tool_name="<add module tool>", arguments={ ... })

Whatever the engine tool's signature, which stage a module goes in still matters — this is the #1 cause of a system that "compiles" but is invalid:

ModuleCorrect stage
InitializeParticleParticleSpawn
SpawnRate, SpawnBurstInstantaneous, EmitterStateEmitterUpdate
ParticleState, SolveForcesAndVelocity, ScaleColor, color/size/velocity update modulesParticleUpdate

SpawnRate is an emitter module — putting it in ParticleUpdate makes the system invalid, and a compile reports only the generic "System is invalid after compilation" with no pointer to the culprit. If a compile is "invalid" after you added modules, first suspect a mis-staged module (list the emitter's modules via the engine toolset and check each module's stage). Stage strings are ParticleSpawn / ParticleUpdate / EmitterSpawn / EmitterUpdate.

For building an emitter entirely from a scratch-pad / Custom HLSL module (which IS a VibeUE operation), see scratch-pad.md.

⚠️ IMPORTANT: Parameters Exist in MULTIPLE Stages

Color.Scale Color, Velocity, Size, and other parameters often exist in BOTH ParticleSpawn AND ParticleUpdate stages!

When changing these parameters, you MUST update BOTH stages:

IMPORTANT: Use full parameter names from list_rapid_iteration_params (e.g., Constants.emitter.Color.Scale Color)

python
# ❌ WRONG - Only sets ParticleUpdate, color may not work correctly
unreal.NiagaraService.set_rapid_iteration_param_by_stage(
    path, emitter, "ParticleUpdate", f"Constants.{emitter}.Color.Scale Color", "(0.0, 3.0, 0.0)"
)

# ✅ CORRECT - Use set_rapid_iteration_param to set ALL matching stages at once
unreal.NiagaraService.set_rapid_iteration_param(
    path, emitter, f"Constants.{emitter}.Color.Scale Color", "(0.0, 3.0, 0.0)"
)

# ✅ OR explicitly set BOTH stages
unreal.NiagaraService.set_rapid_iteration_param_by_stage(
    path, emitter, "ParticleSpawn", f"Constants.{emitter}.Color.Scale Color", "(0.0, 3.0, 0.0)"
)
unreal.NiagaraService.set_rapid_iteration_param_by_stage(
    path, emitter, "ParticleUpdate", f"Constants.{emitter}.Color.Scale Color", "(0.0, 3.0, 0.0)"
)

Why? ParticleSpawn sets initial color, ParticleUpdate multiplies it. If you only set one, the other uses its default value and the result won't be what you expect.


Task Index

TaskSub-doc / where
Recolor an emitter (hue shift / tint / scale)color.md (VibeUE)
Manage ColorFromCurve modules / curve keyscolor.md (VibeUE)
Read rapid-iteration paramsreference.md (VibeUE)
Set rapid-iteration params (all stages)reference.md → NiagaraService (niagara-systems)
Add modules / renderers to an emitterengine NiagaraToolsets.* via call_tool (see reference.md)
Build an emitter from scratch / Custom-HLSL scratch modulescratch-pad.md (VibeUE)

Sub-docs

  • color.md — all color editing: ColorFromCurve detection, choosing the right method (shift_color_hue vs tint vs scale), curve keys, per-stage color, managing ColorFromCurve.
  • reference.md — VibeUE color/curve + rapid-iteration-param readers, plus where module/renderer CRUD lives (engine NiagaraToolsets) and common property names.
  • scratch-pad.md — building emitters from scratch and Custom-HLSL Scratch-Pad authoring.

Verification

Compile and save after changes (compile via the engine NiagaraToolsets tool; unreal.EditorAssetLibrary.save_asset(path) to persist). For color edits, re-read the curve keys (get_color_curve_keys) or rapid-iteration params to confirm the change landed in every stage where the param exists.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Niagara Emitters AI skill do?

Niagara emitter color/curve authoring (tint, hue-shift, ColorFromCurve keys), rapid-iteration parameter tuning, and Custom-HLSL scratch-pad authoring (NiagaraEmitterService + NiagaraScratchPadService). Module/renderer CRUD is owned by the engine NiagaraToolsets. Use when the user asks to recolor or hue-shift particles, edit color curves, tune emitter params, or build a scratch-pad/Custom HLSL module. For system-level lifecycle, load niagara-systems.

Why use Niagara Emitters on TypingMind?

Because you install it once and use it with any model. Niagara Emitters 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 Niagara Emitters in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/niagara-emitters. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Niagara Emitters?

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 Niagara Emitters?

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

Is the Niagara Emitters AI skill free?

Yes. It is published on GitHub by kevinpbuckley under the MIT license. 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 👇