Gas logo

Gas

Community
kevinpbuckley
gas

Author and PIE-verify Gameplay Ability System content — abilities, attribute sets, gameplay effects, gameplay events, costs/cooldowns, cues — by composing Epic's GASToolsets/GameplayTagsToolset with Blueprint/Object tools and Python. Use when the user asks to add abilities, attributes, damage/buff effects, cooldowns, gameplay cues, or to inspect a live ASC.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill namegas
Stars
735
Forks
161
Bundled files
Instructions only
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.

  • 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 Gas 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/gas
  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/gas .claude/skills/gas
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gas 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 Gas 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 Gas 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: "gameplay-ability-system"} for UE domain knowledge (ASC setup, attribute/effect/ability APIs, networking) — treat it as the rubric for any review / "best practices" question. If no such tool is available, skip this line entirely and proceed with this skill alone — do NOT attempt the call.

Gameplay Ability System Skill

Compose, do not duplicate. Everything GAS needs already exists across Epic's engine toolsets, the generic Blueprint/Object tools, and Python. VibeUE adds no GAS wrapper service; this skill is the routing map plus the live-verified gotchas.

Ownership matrix — who does what

OperationOwner
Inspect a live ASC (PIE): attributes, active tags, active effects, granted abilitiesEpic GASToolsets.AbilitySystemInspectorToolset → GetAttributeValues / GetActiveTags / GetActiveEffects / GetGrantedAbilities. Input is {"actor": {"refPath": "<actor path>"}} — works on PIE actors, no selection needed
Discover attribute set classes / attributesEpic GASToolsets.AttributeSetToolset → FindAttributeSetClasses / ListAttributes
Gameplay Cue notify assets + cue tagsEpic GASToolsets.GameplayCueToolset (list/get/create/execute-on-selected)
Tag CRUD (add/remove/rename/list single tags)Epic GameplayTagsToolset — see the gameplay-tags skill
Bulk tag registration, hierarchy queries, existence checksunreal.GameplayTagService (VibeUE delta — see gameplay-tags)
Create GameplayAbility / GameplayEffect / AttributeSet Blueprint subclasses, CDO configEpic BlueprintTools + ObjectTools (or native Python BlueprintFactory with the right ParentClass)
Ability / cue Blueprint graphsEpic BlueprintTools + unreal.BlueprintService.build_graph (see blueprint-graphs)
GameplayEffect legacy tag containers (Asset/Target Tags)unreal.BlueprintService.set_property — maps them onto the UE 5.3+ GE Components (VibeUE #539/#541)
Runtime PIE testingEditorToolset.EditorAppToolset StartPIE/StopPIE + Python on live actors (below)
Native C++ attribute sets / effects / abilitiesCoding-agent handoff — C++ patterns below are for that agent, not for editor tools

Python exposure facts (live-verified, UE 5.8)

  • UAbilitySystemBlueprintLibrary is exposed as unreal.AbilitySystemLibrary (the "BlueprintLibrary" name does not exist in Python). asc = unreal.AbilitySystemLibrary.get_ability_system_component(actor).
  • FGameplayTag cannot be constructed from raw Python: unreal.GameplayTag(tag_name=...) is rejected, TagName is read-only via set_editor_property, and GameplayTagLibrary.make_literal_gameplay_tag takes an FGameplayTag (circular). Use VibeUE's escape hatch: unreal.GameplayTagService.request_tag("A.B.C") returns the real registered tag VALUE (invalid tag for unknown names — check with GameplayTagLibrary.is_gameplay_tag_valid), and request_tag_container([...]) batches into a container. That unlocks every tag-typed API: asc.has_matching_gameplay_tag, send_gameplay_event_to_actor, assign_tag_set_by_caller_magnitude, tag-keyed TMap authoring, and tag queries. For pure READS the Epic inspector GetActiveTags also returns tag names as strings without needing tag values.
  • asc.get_owned_gameplay_tags() is NOT exposed. Use the inspector.
  • ASC BlueprintCallables that take a class work fine: asc.try_activate_ability_by_class(unreal.MyGA_Class) — this is the reliable Python path to drive abilities in PIE (it bypasses any component-level gates, which makes tests deterministic).
  • Multiple activations inside ONE execute_python_code call happen in the same frame — no timers tick and no GE durations expire between them. Exploit this to hit caps/lockouts deterministically instead of sleeping wall-clock time.

PIE verification recipe (one round-trip per step)

python
import unreal, json
world = unreal.get_editor_subsystem(unreal.UnrealEditorSubsystem).get_game_world()
pawn = unreal.GameplayStatics.get_player_pawn(world, 0)
ref = json.dumps({"actor": {"refPath": pawn.get_path_name()}})
for tool in ["GetAttributeValues", "GetActiveTags", "GetActiveEffects", "GetGrantedAbilities"]:
    r = unreal.ToolsetRegistry.execute_tool("GASToolsets.AbilitySystemInspectorToolset", tool, ref)
    print(tool, r.get_value_as_json_string())
# drive an ability and re-inspect IN THE SAME CALL for deterministic assertions
asc = unreal.AbilitySystemLibrary.get_ability_system_component(pawn)
asc.try_activate_ability_by_class(unreal.MyGA_Fire)

Damage through the classic funnel also exercises GE pipelines when the project routes TakeDamage into effects: unreal.GameplayStatics.apply_damage(actor, 25.0, None, None, None).

C++ authoring gotchas (for the coding-agent handoff)

  • Never call UGameplayEffect::FindOrAddComponent/AddComponent in a GE constructor — they NewObject with an empty name, which fatal-asserts at CDO construction and kills the editor on module load. In constructors use CreateDefaultSubobject<UTargetTagsGameplayEffectComponent>(TEXT("TargetTags")), call SetAndApplyTargetTagChanges(...), then GEComponents.Add(...) (protected — do it inside the class).
  • SetByCaller cost/cooldown GEs: CommitAbility alone applies a 0-magnitude spec and logs a warning. Override ApplyCost/ApplyCooldown, build the spec with MakeOutgoingGameplayEffectSpec, SetSetByCallerMagnitude(tag, value), then ApplyGameplayEffectSpecToOwner.
  • AbilityTags is deprecated in 5.5+ — call SetAssetTags(container) in the constructor.
  • NonInstanced instancing is deprecated — default to InstancedPerActor.
  • UAbilitySystemGlobals::Get().InitGlobalData() must run once at startup (GameInstance::Init / AssetManager) or target data and montage prediction fail silently.
  • Set [/Script/GameplayAbilities.AbilitySystemGlobals] +GameplayCueNotifyPaths=/Game/GameplayCues in DefaultGame.ini, or the cue manager scans all of /Game/ (startup warning + cost).

Verification rules

After authoring: compile (unreal.BlueprintEditorLibrary.compile_blueprint), then prove behavior in PIE with the inspector — a successful tool call is not evidence. Attribute deltas, active-tag presence, and effect duration/stack readouts are the evidence to report.

Frequently asked questions

What does the Gas AI skill do?

Author and PIE-verify Gameplay Ability System content — abilities, attribute sets, gameplay effects, gameplay events, costs/cooldowns, cues — by composing Epic's GASToolsets/GameplayTagsToolset with Blueprint/Object tools and Python. Use when the user asks to add abilities, attributes, damage/buff effects, cooldowns, gameplay cues, or to inspect a live ASC.

Why use Gas on TypingMind?

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

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

Which AI models can use Gas?

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 Gas?

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

Is the Gas 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 👇