Inventory System logo

Inventory System

Community
jame581
inventory-system

Use when building inventory systems — Resource-based items, slot management, stacking, and UI binding

Overview

Publisherjame581
RepositoryGodotPrompter
Skill nameinventory-system
Stars
808
Forks
47
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

    Published by jame581 on GitHub. Read the source before you install it.

Installation

Install the Inventory System 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/jame581/GodotPrompter/tree/master/skills/inventory-system
  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/jame581/GodotPrompter.git /tmp/GodotPrompter
mkdir -p .claude/skills
cp -r /tmp/GodotPrompter/skills/inventory-system .claude/skills/inventory-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Inventory System 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 Inventory System 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 Inventory System 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.

Inventory Systems in Godot 4.3+

All examples target Godot 4.3+ with no deprecated APIs. This skill carries the decisions; the implementations live in references/ (GDScript first, then C#) — load the one you need.

Related skills: resource-pattern for custom Resource data containers, save-load for inventory serialization, event-bus for inventory change notifications, hud-system for inventory UI display, popochiu for adventure-game inventory.


1. Architecture Overview

┌─────────────────────────────────────────────────────────┐
│                        UI Layer                         │
│   InventoryUI (Control)                                 │
│     └─ GridContainer                                    │
│           └─ SlotUI × N (Button)                        │
│                 └─ TextureRect (icon) + Label (qty)     │
│                                                         │
│   Connects to: inventory_changed signal                 │
│   Drag-and-drop via _get_drag_data / _drop_data         │
└───────────────────────┬─────────────────────────────────┘
                        │ reads / mutates
┌───────────────────────▼─────────────────────────────────┐
│                    Inventory (Node)                      │
│   slots: Array[InventorySlot]                           │
│   add_item(item, qty) → leftover: int                   │
│   remove_item(item, qty)                                │
│   has_item(item, qty) → bool                            │
│   get_item_count(item) → int                            │
│                                                         │
│   signals: inventory_changed                            │
│             item_added(item, quantity)                  │
│             item_removed(item, quantity)                │
└───────────────────────┬─────────────────────────────────┘
                        │ references
┌───────────────────────▼─────────────────────────────────┐
│                   Data Layer (Resources)                 │
│   ItemData (Resource)                                   │
│     id, name, description, icon, max_stack_size,        │
│     item_type enum                                      │
│                                                         │
│   InventorySlot (inner class / Resource)                │
│     item: ItemData, quantity: int                       │
└─────────────────────────────────────────────────────────┘

2. The Decisions That Matter

Three choices shape every inventory. Make them explicitly and state which you picked — the rest is mechanical.

DecisionTakeWhy
Item identity: Resource vs. Dictionary / JSONResource in .tres@export slots accept typed items, the Inspector edits them, and shared instances compare by reference
Slot container: Resource vs. RefCountedRefCountedSlots are runtime state, not authored assets. A Resource invites saving slots to disk and reloading stale item copies
add_item return: bool vs. leftover countleftover intPartial adds are the common case (stack caps, full bag). A bool forces the caller to re-query what actually fit

If your game needs something else — a weight-based bag with no slots, a grid inventory with shaped items, an infinite stack list — say so before building. The fixed slot array this skill describes is the wrong skeleton for all three.

Non-obvious specifics

  • Fill existing stacks before empty slots — two passes, in that order. A single naive pass scatters one item type across several slots and reports the bag full while space remains.
  • Emit inventory_changed once per operation, after both passes complete — not once per slot touched. Per-slot emission re-renders the whole UI N times for one add_item.
  • Items compare by reference. Godot caches loaded resources, so load() on the same .tres returns the same instance and slot.item == item is correct and cheap. If you duplicate() items at runtime, that breaks — key off ItemData.id instead.
  • Clear item to null when quantity reaches 0, or is_empty() lies and the slot is never reusable.
  • Prevent stacking with data, not branches — set max_stack_size = 1 on EQUIPMENT and KEY_ITEM items rather than special-casing them in add_item.
  • C#: mark ItemData [GlobalClass] or the Inspector will not offer it as a type when creating .tres files.

Inventory API contract

MemberReturnsContract
add_item(item, quantity)intLeftover that did not fit; 0 means everything was added
remove_item(item, quantity)—Removes up to quantity; silent when fewer are held
has_item(item, quantity)boolConvenience over get_item_count
get_item_count(item)intSummed across every slot
inventory_changedsignalFired once per mutating operation — drives all UI
item_added(item, quantity)signalCarries the amount actually added
item_removed(item, quantity)signalCarries the amount actually removed

Full ItemData, Inventory, and InventorySlot implementations in GDScript and C#: references/core-classes.md


3. Equipment Extension

Add equipment slots (HEAD, CHEST, WEAPON, etc.) by extending the Inventory class with a typed slot map. Stat aggregation runs by summing ItemData.stats across equipped items; signal equipment_changed when slots change.

See references/equipment.md for the full GDScript and C# Equipment class with EquipmentSlotType enum, equip / unequip API, and stat aggregation.


4. UI Binding

Slot-grid UI: a GridContainer of Panel slot widgets, each rendering one InventorySlot. Drag-and-drop uses _get_drag_data / _drop_data / _can_drop_data on the slot widget. The Inventory emits inventory_changed; the UI re-renders affected slots.

See references/ui-binding.md for the full GDScript and C# slot widget (drag/drop, hover preview), inventory grid layout, and tooltip wiring.


5. Serialization

Persist Inventory + Equipment as a Dictionary keyed by item resource path (since ItemData lives at res://items/<name>.tres). Reload by load(path) and reconstructing the slot list. Version field gates migration on load.

See references/serialization.md for the GDScript and C# save/load implementation with version field and ConfigFile / JSON variants.



Implementation Checklist

  • ItemData extends Resource with a stable id string set in the Inspector
  • ItemData files live under res://items/ and are committed to version control
  • Inventory.add_item() returns leftover count; callers handle a full inventory
  • inventory_changed signal drives all UI updates — UI never polls per-frame
  • InventorySlot.remove_from_stack() clears item to null when quantity reaches 0
  • Equipment slots keyed by SlotType enum, not by string, to catch typos at compile time
  • Equipment.get_total_stat() is called when stats are needed, not cached unless profiling demands it
  • Serialization stores id + quantity only — never full ItemData objects or resource paths
  • ItemRegistry loads items at startup; all deserialization goes through it
  • Drag-and-drop swaps slot contents directly then emits inventory_changed once
  • max_stack_size = 1 on EQUIPMENT and KEY_ITEM types to prevent stacking
  • All push_error() messages include the class name and method for easy tracing

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 Inventory System AI skill do?

Use when building inventory systems — Resource-based items, slot management, stacking, and UI binding

Why use Inventory System on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jame581/GodotPrompter/tree/master/skills/inventory-system. 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 Inventory System?

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 Inventory System?

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

Is the Inventory System AI skill free?

Yes. It is published on GitHub by jame581 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 👇