Godot Dialogue System logo

Godot Dialogue System

Community
thedivergentai
godot-dialogue-system

Expert patterns for branching dialogue systems including dialogue graphs (Resource-based), character portraits, player choices, conditional dialogue (flags/quests), typewriter effects, localization support, and voice acting integration. Use for narrative games, RPGs, or visual novels. Trigger keywords: DialogueLine, DialogueChoice, DialogueGraph, dialogue_manager, typewriter_effect, branching_dialogue, dialogue_flags, localization, voice_acting.

Overview

Publisherthedivergentai
RepositoryGD-Agentic-Skills
Skill namegodot-dialogue-system
Stars
727
Forks
43
Bundled files
17
LicenseLGPL-3.0
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.

  • 17 bundled files

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

  • Open source

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

Installation

Install the Godot 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.
  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/thedivergentai/GD-Agentic-Skills.git /tmp/GD-Agentic-Skills
mkdir -p .claude/skills
cp -r /tmp/GD-Agentic-Skills/skills/godot-dialogue-system .claude/skills/godot-dialogue-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot 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 Godot 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 Godot 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 System

Data-driven dialogue routing — not beginner typewriter tutorials.

NEVER Do in Dialogue Systems

  • NEVER hardcode dialogue text in GDScript — Store lines in Resources / JSON / CSV so localization works.
  • NEVER show choices the player has not unlocked — Hide (or intentionally gray) gated options.
  • NEVER use unvalidated loose strings for node transitions — Typos in next_node_id soft-lock mid-convo; assert / registry IDs.
  • NEVER force a typewriter without skip — Click/confirm must finish the line immediately.
  • NEVER drive reveal with per-character Timer / OS.delay_msec() — Use visible_ratio / visible_characters + Tween (see typebox_effect.gd).
  • NEVER store dialogue cursor state only in the UI node — Scene changes drop the player; keep progress in the manager Autoload / session object.
  • NEVER get_node() from NPCs into Dialogue UI — Start via manager signals (start_dialogue(res)).
  • NEVER invent regex for BBCode — Prefer RichTextLabel BBCode / custom effects.
  • NEVER save/load inside a dialogue node Resource — Nodes are data; persistence belongs to SaveSystem.
  • NEVER hardcode portrait paths in code — Assign textures on node Resources or a portrait database.

Decision Tree: Authoring Engine

Authoring needEngineMANDATORY scriptsDo NOT Load
Designer-friendly .tres graphs in-repoResource Autoload graphdialogue_resource.gddialogue_manager_singleton.gddialogue_ui_controller.gdtypebox_effect.gddialogue_engine.gd JSON path
External writers / spreadsheet → JSONJSON graph enginedialogue_engine.gd (+ optional dialogue_manager.gd) → UI + typeboxResource Autoload stack
Visual node editor in-projectGraphEdit authoringKeep runtime on Resource or JSON export; GraphEdit is editor-only toolingShipping GraphEdit as the runtime walker
Conditions / quest gatesEitherbranching_condition_validator.gdEmbedding flag checks in UI buttons
Portraits / expressionsEitherdialogue_portrait_manager.gd
Localization keysEitherlocalized_dialogue_resource.gdHardcoded language if trees
Quest / gameplay hooks from linesEitherdialogue_event_bridge.gdSide effects inside UI controller

Default golden path: Resource Autoload → UI controller → typebox_effect. Pick one runtime engine; do not run Resource manager and JSON engine in parallel.

Available Scripts (single catalog)

Runtime (golden path)

Supporting

Alternate engines (load only if decision tree says so)

Typewriter Contract (skip-safe)

Use typebox_effect.gd: set full text, tween visible_ratio (or RichTextLabel visible_characters) from 0→1. On skip input: kill tween and snap visibility to complete. Do not spawn a Timer per character.

Elite Deltas

MANDATORY for GraphEdit tooling, TTS/lipsync, analytics, and moved inline manager/UI tutorials: elite-dialogue-patterns.md. Do NOT Load for Resource Autoload golden path only.

Reference

Progressive disclosure: open Official Documentation links only when researching a specific API; load Related Skills when routing to a peer domain — do not preload the whole lattice.

Official Documentation

  • Resources — Why dialogue graphs belong in Resource / .tres data instead of hardcoded strings in scripts.
  • BBCode in RichTextLabel — Native markup for speaker emphasis, custom tags, and effects without rolling your own parser.
  • RichTextLabelvisible_characters / image helpers and BBCode APIs the dialogue UI should drive for typewriter and portraits.
  • Internationalizing gamestr() / TranslationServer workflow so line text stays key-based across locales.
  • Localization using spreadsheets — CSV translation tables that map cleanly onto dialogue text_key fields.
  • Importing translations — How Godot imports CSV/PO so localized dialogue resources resolve at runtime.
  • Using signals — Emit line/choice/end events upward so UI, quests, and audio never hard-reference the manager internals.
  • Singletons (Autoload) — Register a DialogueManager that survives scene changes and owns traversal state.
  • Tween — Drive visible_ratio / character reveal timing without blocking the main thread.
  • Text-to-speechDisplayServer TTS callbacks for placeholder VO and lipsync-adjacent timing.
  • GraphEdit — Editor surface for authoring branching dialogue graphs when .tres lists become unwieldy.
  • JSON — Parse external dialogue graph files when designers prefer JSON over Resources.

Related Skills

Prerequisites
  • godot-project-foundations — Autoload registration, input for advance/skip, and project layout dialogue UI scenes plug into.
  • godot-gdscript-mastery — Typed Resources, signals, await, and Callables required before branching engines and UI bridges.
  • godot-resource-data-patterns — Canonical patterns for DialogueLine / graph Resources, exports, and avoiding duplicated mutable state.
  • godot-autoload-architecture — Singleton ownership and boot order for a global DialogueManager that must outlive scene swaps.
Complements
  • godot-signal-architecture — Signal-up / call-down contracts for line_displayed, choice selection, and narrative event bridges.
  • godot-ui-rich-text — RichTextLabel BBCode, custom effects, and image embedding beyond the basics used in typewriter UIs.
  • godot-ui-containers — Layout choice buttons and dialogue panels without fighting Control sizing and focus.
  • godot-tweening — Skip-safe Tweens for character reveal, portrait entry, and panel transitions.
  • godot-audio-systems — Voice-line players, bus ducking during dialogue, and subtitle sync with spoken audio.
  • godot-quest-system — Quest flags and objectives that gate conditional choices and fire from dialogue event bridges.
  • godot-save-load-systems — Persist dialogue flags / seen-node state outside UI nodes so progress survives reloads.
Downstream / consumers
  • godot-genre-visual-novel — Full VN presentation loops consume this skill’s graph traversal, portraits, and choice UI patterns.
  • godot-inventory-system — Dialogue effects often grant/require items; keep grant logic in inventory, not inside line Resources.
  • godot-monte-carlo-balancer — Simulate skill-check / branching choice trees when narrative gates or reward paths need balance passes.
Master
  • godot-master — Library router and mirrored module entry; open when discovering which Domain Skill owns narrative, UI, or quest concerns.

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 Godot Dialogue System AI skill do?

Expert patterns for branching dialogue systems including dialogue graphs (Resource-based), character portraits, player choices, conditional dialogue (flags/quests), typewriter effects, localization support, and voice acting integration. Use for narrative games, RPGs, or visual novels. Trigger keywords: DialogueLine, DialogueChoice, DialogueGraph, dialogue_manager, typewriter_effect, branching_dialogue, dialogue_flags, localization, voice_acting.

Why use Godot Dialogue System on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thedivergentai/GD-Agentic-Skills/tree/main/skills/godot-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 Godot 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 Godot Dialogue System?

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

Is the Godot Dialogue System AI skill free?

Yes. It is published on GitHub by thedivergentai under the LGPL-3.0 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 👇