Enum Struct logo

Enum Struct

Community
kevinpbuckley
enum-struct

Create, modify, and introspect UserDefinedEnums and UserDefinedStructs (EnumStructService). Use when the user asks to create a Blueprint enum or struct, add enum values or struct members, or inspect an enum/struct's fields. Useful for defining a DataTable row struct.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill nameenum-struct
Stars
735
Forks
161
Bundled files
1
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.

  • 1 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 Enum Struct 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/enum-struct
  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/enum-struct .claude/skills/enum-struct
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Enum Struct 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 Enum Struct 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 Enum Struct 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.

Enum and Struct Skill

Critical Rules

Read-Only Native Types

Native C++ enums and structs are read-only. Only UserDefinedEnums and UserDefinedStructs can be modified:

python
import unreal

# Search for user-defined enums only (editable)
enums = unreal.EnumStructService.search_enums("Weapon", True)  # bUserDefinedOnly=True

# Check if an enum is user-defined before modifying
# (returns a single EnumInfo or None — NOT a (success, info) tuple)
info = unreal.EnumStructService.get_enum_info("EMyEnum")
if info and info.is_user_defined:          # field is is_user_defined, NOT b_is_user_defined
    unreal.EnumStructService.add_enum_value("EMyEnum", "NewValue")

🚨 Pass the EXACT asset name you want — prefixing is dumb

create_enum / create_struct only prepend E/F when the name doesn't already start with that letter; they never insert underscores or reformat. So:

  • want E_TestState → pass "E_TestState" (passing "TestState" creates ETestState)
  • want EWeaponType → "WeaponType" or "EWeaponType" both work

Creation fails with an empty string if the asset already exists — delete it first (delete_enum / delete_struct), there is no overwrite.

🚨 Enum values: you are always working with DISPLAY names

UserDefinedEnum entries have immutable internal names (NewEnumerator0..N). Every EnumStructService method speaks display names: the name you pass to add_enum_value becomes the display name, get_enum_values returns display names, and rename_enum_value / remove_enum_value accept display names (rename changes the display name only). For internal+display pairs use get_enum_info(...).values (each entry has name = internal, display_name, value, index).


Workflows

Create UserDefinedEnum

python
import unreal

# Create a new enum — pass the exact final name (here E prefix gets prepended)
enum_path = unreal.EnumStructService.create_enum("/Game/Data/Enums", "WeaponType")
print(f"Created: {enum_path}")  # /Game/Data/Enums/EWeaponType.EWeaponType
if not enum_path:
    # creation failed — most likely the asset already exists; delete_enum first
    ...

# Add values
unreal.EnumStructService.add_enum_value(enum_path, "Sword", "Melee Sword")
unreal.EnumStructService.add_enum_value(enum_path, "Bow", "Ranged Bow")
unreal.EnumStructService.add_enum_value(enum_path, "Staff", "Magic Staff")

# Verify
values = unreal.EnumStructService.get_enum_values(enum_path)
print(f"Values: {values}")  # ['Sword', 'Bow', 'Staff']

Create UserDefinedStruct

python
import unreal

# Create a new struct (F prefix added automatically)
struct_path = unreal.EnumStructService.create_struct("/Game/Data/Structs", "WeaponData")
print(f"Created: {struct_path}")

# Add properties
unreal.EnumStructService.add_struct_property(struct_path, "WeaponName", "FString", "Unnamed")
unreal.EnumStructService.add_struct_property(struct_path, "Damage", "float", "10.0")
unreal.EnumStructService.add_struct_property(struct_path, "AttackSpeed", "float", "1.0")
unreal.EnumStructService.add_struct_property(struct_path, "WeaponType", "EWeaponType")  # Use our enum

# Add array property
unreal.EnumStructService.add_struct_property(struct_path, "SpecialEffects", "FName", "", "Array")

# Verify — get_struct_info returns a single StructInfo (or None), NOT a (success, info) tuple
info = unreal.EnumStructService.get_struct_info(struct_path)
if info:
    print(f"Properties: {info.property_count}")
    for prop in info.properties:
        print(f"  {prop.name}: {prop.type} (default: {prop.default_value}, guid: {prop.guid})")

Notes:

  • prop.name is the authored name ("Damage") and all mutation methods (rename_struct_property, set_struct_property_default, remove_struct_property, change_struct_property_type) accept authored names. GUIDs live per property (StructPropertyInfo.guid) — StructInfo itself has no guid field.
  • New structs are seeded with a placeholder bool (MemberVar_0); the first add_struct_property call removes it automatically. If you ever see a stray MemberVar_* bool in an older struct, drop it with remove_struct_property(path, "MemberVar_0").

Discover Enums and Structs

python
import unreal

# Search all enums containing "Weapon"
enums = unreal.EnumStructService.search_enums("Weapon")
for e in enums:
    print(f"{e.name} ({e.value_count} values) - UserDefined: {e.is_user_defined}")

# Search user-defined structs only
structs = unreal.EnumStructService.search_structs("Data", True)  # bUserDefinedOnly=True
for s in structs:
    print(f"{s.name} ({s.property_count} properties)")

# Get detailed enum info — returns a single EnumInfo (or None), NOT a (success, info) tuple
enum_info = unreal.EnumStructService.get_enum_info("EWeaponType")
if enum_info:
    for v in enum_info.values:
        print(f"  {v.name} = {v.value} ({v.display_name})")

Modify Existing Enum

python
import unreal

enum_path = "/Game/Data/Enums/EWeaponType.EWeaponType"

# Rename a value
unreal.EnumStructService.rename_enum_value(enum_path, "Sword", "LongSword")

# Change display name
unreal.EnumStructService.set_enum_value_display_name(enum_path, "Bow", "Composite Bow")

# Remove a value
unreal.EnumStructService.remove_enum_value(enum_path, "Staff")

# Add new value
unreal.EnumStructService.add_enum_value(enum_path, "Crossbow", "Heavy Crossbow")

Modify Existing Struct

python
import unreal

struct_path = "/Game/Data/Structs/FWeaponData.FWeaponData"

# Rename a property
unreal.EnumStructService.rename_struct_property(struct_path, "Damage", "BaseDamage")

# Change property type — ⚠️ this RESETS the default value to the new type's zero;
# re-set the default afterwards if you need one
unreal.EnumStructService.change_struct_property_type(struct_path, "BaseDamage", "int32")

# Set default value
unreal.EnumStructService.set_struct_property_default(struct_path, "BaseDamage", "15")

# Remove a property
unreal.EnumStructService.remove_struct_property(struct_path, "SpecialEffects")

# Add new property
unreal.EnumStructService.add_struct_property(struct_path, "CriticalMultiplier", "float", "2.0")

Use Struct in a DataTable

After creating a UserDefinedStruct, it becomes available as a DataTable row type. The struct must contain at least one property before it can be used as a row type.

python
import unreal

# Create the row struct with EnumStructService
struct_path = unreal.EnumStructService.create_struct("/Game/Data", "ItemRow")
unreal.EnumStructService.add_struct_property(struct_path, "ItemName", "FString")
unreal.EnumStructService.add_struct_property(struct_path, "Value", "int32", "0")
unreal.EnumStructService.add_struct_property(struct_path, "Icon", "UTexture2D")

DataTable creation itself is no longer a VibeUE service — it is owned by the engine's native asset toolset. Create the DataTable with the engine AssetTools toolset via call_tool (pass the FItemRow struct as the row structure); run describe_toolset on AssetTools for the exact action name and parameters. You can also create one in raw Python via unreal.AssetToolsHelpers + unreal.DataTableFactory if you prefer execute_python_code.


Available Property Types

When adding struct properties, use these type strings:

Basic Types

  • bool, int32, int64, float, double
  • FString, FName, FText, uint8, byte

Common Structs

  • FVector, FVector2D, FRotator, FTransform
  • FColor, FLinearColor
  • FGameplayTag, FGameplayTagContainer

Object References

  • AActor, APawn, ACharacter
  • UTexture2D, UMaterial, UStaticMesh
  • USoundBase, UAnimSequence

Containers

Use the ContainerType parameter:

python
# Array of strings
unreal.EnumStructService.add_struct_property(path, "Tags", "FString", "", "Array")

# Set of names
unreal.EnumStructService.add_struct_property(path, "UniqueNames", "FName", "", "Set")

# Map of string to int
unreal.EnumStructService.add_struct_property(path, "Scores", "int32", "", "Map")

Troubleshooting

"Enum not found" Error

  • Check if using full path vs just name
  • Use search_enums() to find the correct path
  • Ensure the asset is saved

"Cannot modify native enum/struct"

  • Only UserDefinedEnum/UserDefinedStruct assets can be modified
  • Native C++ types from engine/plugins are read-only
  • Check is_user_defined property before modifying

Property Type Not Recognized

  • Use BlueprintService.search_variable_types() to find valid type names
  • Ensure enum/struct types exist before referencing them

Sample scripts (run via execute_python_code)

  • scripts/create_enum_struct.txt — create a UserDefinedEnum (+values) and a UserDefinedStruct.

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 Enum Struct AI skill do?

Create, modify, and introspect UserDefinedEnums and UserDefinedStructs (EnumStructService). Use when the user asks to create a Blueprint enum or struct, add enum values or struct members, or inspect an enum/struct's fields. Useful for defining a DataTable row struct.

Why use Enum Struct on TypingMind?

Because you install it once and use it with any model. Enum Struct 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 Enum Struct in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/enum-struct. 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 Enum Struct?

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 Enum Struct?

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

Is the Enum Struct 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 👇