Dialogue System logo

Dialogue System

Community
jame581
dialogue-system

Use when implementing dialogue — data structures for branching dialogue, conditions, and UI presentation

Overview

Publisherjame581
RepositoryGodotPrompter
Skill namedialogue-system
Stars
808
Forks
47
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 jame581 on GitHub. Read the source before you install it.

Installation

Install the Dialogue 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/dialogue-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/dialogue-system .claude/skills/dialogue-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dialogue 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 Dialogue 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 Dialogue 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.

Dialogue Systems in Godot 4.3+

All examples target Godot 4.3+ with no deprecated APIs. GDScript is shown first, then C#.

Related skills: resource-pattern for dialogue data as Resources, godot-ui for Control node layout, state-machine for dialogue flow management, save-load for dialogue state persistence, dialogue-manager for a full-featured dialogue addon, popochiu for adventure games.


1. Architecture Overview

┌─────────────────────────────────────────────────────────┐
│                        UI Layer                         │
│   DialogueUI (Control)                                  │
│     ├─ Label (speaker_name)                             │
│     ├─ TextureRect (portrait)                           │
│     ├─ RichTextLabel (dialogue_text, typewriter effect) │
│     └─ VBoxContainer (choice_container)                 │
│           └─ Button × N (choice buttons)                │
│                                                         │
│   Connects to: line_displayed, choice_presented signals │
└───────────────────────┬─────────────────────────────────┘
                        │ drives UI via signals
┌───────────────────────▼─────────────────────────────────┐
│              DialogueManager (Autoload / Node)           │
│   start_dialogue(dialogue_data)                         │
│   advance()  → next line or end                         │
│   choose(choice_index)                                  │
│   current_line: DialogueLine (read-only)                │
│                                                         │
│   signals: dialogue_started                             │
│             line_displayed(line)                        │
│             choice_presented(choices)                   │
│             dialogue_ended                              │
└───────────────────────┬─────────────────────────────────┘
                        │ reads
┌───────────────────────▼─────────────────────────────────┐
│                   Data Layer (Resources)                 │
│   DialogueData (Resource)                               │
│     lines: Dictionary  ← id → DialogueLine              │
│     start_line_id: String                               │
│                                                         │
│   DialogueLine (Resource)                               │
│     speaker, text, choices, next_line_id, condition     │
└─────────────────────────────────────────────────────────┘

2. DialogueLine Resource

DialogueLine holds all data for a single beat of dialogue. Choices is an Array[Dictionary] so each entry can carry a text, next_line_id, and optional condition without a separate class.

GDScript

gdscript
# dialogue_line.gd
class_name DialogueLine
extends Resource

## Display name shown in the UI speaker box.
@export var speaker: String = ""

## The body text. Supports BBCode and variable placeholders: {player_name}.
@export_multiline var text: String = ""

## When non-empty, overrides next_line_id. Each Dictionary must have:
##   "text"        : String   — label on the choice button
##   "next_line_id": String   — line to jump to when chosen
##   "condition"   : String   — (optional) expression; omit or "" to always show
@export var choices: Array = []

## ID of the next DialogueLine. Ignored when choices is non-empty.
@export var next_line_id: String = ""

## Optional condition expression evaluated before displaying this line.
## If the expression returns false the manager skips to next_line_id.
## Example: "GameState.has_item('key')"
@export var condition: String = ""

C#

csharp
// DialogueLine.cs
using Godot;
using Godot.Collections;

[GlobalClass]
public partial class DialogueLine : Resource
{
    /// <summary>Display name shown in the speaker box.</summary>
    [Export] public string Speaker     { get; set; } = "";

    /// <summary>Body text. Supports BBCode and {variable} placeholders.</summary>
    [Export(PropertyHint.MultilineText)]
    public string Text                 { get; set; } = "";

    /// <summary>
    /// When non-empty, overrides NextLineId. Each Dictionary entry must contain:
    ///   "text"         : string  — choice button label
    ///   "next_line_id" : string  — line to jump to
    ///   "condition"    : string  — (optional) expression; omit or "" to always show
    /// </summary>
    [Export] public Array Choices      { get; set; } = new();

    /// <summary>ID of the next DialogueLine. Ignored when Choices is non-empty.</summary>
    [Export] public string NextLineId  { get; set; } = "";

    /// <summary>
    /// Optional condition expression. Evaluated before displaying this line.
    /// Example: "GameState.HasItem(\"key\")"
    /// </summary>
    [Export] public string Condition   { get; set; } = "";
}

3. DialogueData Resource

DialogueData is a container Resource that holds a dictionary of all lines, keyed by their string ID. Creating it as a .tres file lets you assign it to NPCs in the Inspector.

GDScript

gdscript
# dialogue_data.gd
class_name DialogueData
extends Resource

## Dictionary mapping line ID strings to DialogueLine resources.
## Example: { "intro": <DialogueLine>, "ask_quest": <DialogueLine> }
@export var lines: Dictionary = {}

## ID of the first line to display when dialogue starts.
@export var start_line_id: String = ""


## Convenience accessor — returns null for unknown IDs.
func get_line(id: String) -> DialogueLine:
    return lines.get(id, null)

C#

csharp
// DialogueData.cs
using Godot;
using Godot.Collections;

[GlobalClass]
public partial class DialogueData : Resource
{
    /// <summary>Maps line ID strings to DialogueLine resources.</summary>
    [Export] public Dictionary Lines        { get; set; } = new();

    /// <summary>ID of the first line to display when dialogue starts.</summary>
    [Export] public string StartLineId      { get; set; } = "";

    /// <summary>Returns the DialogueLine for id, or null if not found.</summary>
    public DialogueLine GetLine(string id)
    {
        if (Lines.ContainsKey(id))
            return Lines[id].As<DialogueLine>();
        return null;
    }
}

Populate lines in the Inspector by adding Dictionary entries with string keys and DialogueLine resource values, or load them programmatically from JSON (see section 7).


4. DialogueManager

A singleton autoload owns the active DialogueData and tracks current line ID. start(data) sets the data and emits the first line; advance(choice_index) moves forward. Wires three signals: line_changed(line), choices_presented(choices), dialogue_ended().

See references/dialogue-manager.md for the full GDScript and C# manager (line traversal, choice handling, condition evaluation hooks, signals).


5. Branching and Conditions

Choices live on DialogueLine.choices (an Array of Dictionary). Each choice has text, next_line_id, optional condition. Conditions are GDScript expressions evaluated via the Expression class — passed a context object with project state (e.g. GameState).

See references/branching-and-conditions.md for the full choice-handling and condition-evaluator implementations (GDScript + C#), plus security notes on Expression input.


6. Dialogue UI

A CanvasLayer with a RichTextLabel for the line body (BBCode-enabled), a Label for speaker name, and a VBoxContainer for choice buttons. Typewriter effect via RichTextLabel.visible_characters driven by a Tween. UI subscribes to DialogueManager signals.

See references/ui-presentation.md for the scene-tree fragment, typewriter recipe, choice-button spawning, and full GDScript + C# wiring.


7. External Formats

Load dialogue from JSON for designer-friendly editing — map JSON keys to DialogueLine properties at load time. Or integrate the Dialogic addon for a node-graph editor (community standard).

See references/external-formats.md for the JSON loader recipe and Dialogic integration notes.


8. Variable Interpolation

Dialogue text supports {player_name}-style placeholders. Resolve via a small templater: text.format(vars) (GDScript) or string.Format with named-tag preprocessing (C#).

See references/variable-interpolation.md for the GDScript and C# interpolation helpers.


9. Implementation Checklist

  • DialogueLine and DialogueData extend Resource and carry [GlobalClass] (C#) for Inspector integration
  • DialogueManager is registered as an Autoload so all scenes share a single instance
  • start_dialogue() asserts that dialogue_data is non-null before accessing it
  • advance() guards against being called when choices are pending
  • choose() operates on the filtered visible-choices list, not the raw choices array
  • Condition strings reference only stable autoload method names — avoid referencing scene-local nodes
  • _evaluate_condition() passes a known base instance (GameState) to Expression.execute() to resolve method calls
  • Typewriter timer uses visible_characters, not frame-by-frame string slicing, for BBCode compatibility
  • Pressing ui_accept mid-typewriter reveals full text; a second press advances the line
  • Choice buttons are freed (queue_free) before creating new ones — never accumulate stale children
  • JSON loader validates file open and parse steps separately, emitting clear error messages for each failure
  • Variable interpolation is centralised in one _interpolate() helper, not scattered across signal handlers
  • next_line_id = "" signals end-of-dialogue — no magic sentinel strings beyond the empty string
  • All push_error() messages include class name and method for easy log 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 Dialogue System AI skill do?

Use when implementing dialogue — data structures for branching dialogue, conditions, and UI presentation

Why use Dialogue System on TypingMind?

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

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

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

Is the Dialogue 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 👇