Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

godot-dialogue-system戈多对话系统

Agent Skill

godot-dialogue-system 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,545

周安装

105

GitHub Stars

138

下载量

832
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:godot-dialogue-system(戈多对话系统)
来源仓库:https://github.com/thedivergentai/gd-agentic-skills
仓库路径:skills/godot-dialogue-system
安装命令:
npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-dialogue-system
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-dialogue-system

简介

godot-dialogue-system 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装并使用该技能。
  • 安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Dialogue System

Expert guidance for building flexible, data-driven dialogue systems.

Available Scripts

dialogue_resource.gd

Data-driven conversation tree container using Resources for modular, branching narrative paths.

dialogue_node_data.gd

Serialized data structure for a single line of dialogue, including speaker metadata and portraits.

dialogue_option_data.gd

Interactive player choice definition with branching logic and scriptable availability conditions.

dialogue_manager_singleton.gd

Centralized AutoLoad orchestrator for traversing dialogue trees and broadcasting state signals.

dialogue_ui_controller.gd

Reactive UI bridge that maps dialogue data to visual labels and dynamic choice buttons.

typebox_effect.gd

Polished "Character-by-character" text reveal effect using Godot's built-in Tweens.

dialogue_event_bridge.gd

Bridge node for triggering external game events (e.g. starting a quest) from conversation nodes.

branching_condition_validator.gd

Expert logic for evaluating player stats or global flags to toggle dialogue choices.

localized_dialogue_resource.gd

Advanced strategy for supporting multi-language conversation text via translation keys.

dialogue_portrait_manager.gd

Visual controller for managing character expressions and entry animations during dialogue.

NEVER Do in Dialogue Systems

  • NEVER hardcode dialogue text directly in your GDScript files — This makes translation impossible. Store text in Resources or external JSON/CSV files [12].
  • NEVER display choices that the player hasn't met the criteria for — Hidden choices should stay hidden unless they are "grayed out" intentionally to show a missed path [13].
  • NEVER use loose strings for node transitions without validation — Typos in next_node_id will crash the dialogue mid-convo. Use assert() or a central ID registry [14].
  • NEVER force a typewriter effect without a "Skip" option — Forcing players to read at a fixed speed leads to frustration. Always allow clicking to finish the line [15].
  • NEVER store the current dialogue state inside a UI node — If the UI is closed or the scene changes, the player loses their place. Use an AutoLoad DialogueManager [16].
  • NEVER use get_node() to find dialogue UI from the NPC script — Use signals like DialogueManager.start_dialogue(res) to maintain a decoupled architecture.
  • NEVER use complex regex for simple text tags — Godot's RichTextLabel supports BBCode tags natively. Use [b], [i], and [url] for formatting.
  • NEVER perform save/load operations inside a dialogue node — Conversation nodes should be pure data. Delegate persistence to a dedicated SaveSystem.
  • NEVER block the main thread for text reveal timing — Never use OS.delay_msec(). Use create_timer() or Tween to maintain smooth 60fps performance.
  • NEVER hardcode portrait paths — Assign textures directly to the DialogueNode resource in the inspector or use a central PortraitDatabase.

Available Scripts

MANDATORY: Read the appropriate script before implementing the corresponding pattern.

dialogue_engine.gd

Graph-based dialogue with BBCode signal tags. Parses [trigger:event_id] tags from text, fires signals, and loads external JSON dialogue graphs.

dialogue_manager.gd

Data-driven dialogue engine with branching, variable storage, and conditional choices.


Dialogue Data

# dialogue_line.gd
class_name DialogueLine
extends Resource

@export var speaker: String
@export_multiline var text: String
@export var portrait: Texture2D
@export var choices: Array[DialogueChoice] = []
@export var conditions: Array[String] = []  # Quest flags, etc.
@export var next_line_id: String = ""
# dialogue_choice.gd
class_name DialogueChoice
extends Resource

@export var choice_text: String
@export var next_line_id: String
@export var conditions: Array[String] = []
@export var effects: Array[String] = []  # Set flags, give items

Dialogue Manager

# dialogue_manager.gd (AutoLoad)
extends Node

signal dialogue_started
signal dialogue_ended
signal line_displayed(line: DialogueLine)
signal choice_selected(choice: DialogueChoice)

var dialogues: Dictionary = {}
var flags: Dictionary = {}

func load_dialogue(path: String) -> void:
    var data := load(path)
    dialogues[path] = data

func start_dialogue(dialogue_id: String, start_line: String = "start") -> void:
    dialogue_started.emit()
    display_line(dialogue_id, start_line)

func display_line(dialogue_id: String, line_id: String) -> void:
    var line: DialogueLine = dialogues[dialogue_id].lines[line_id]

    # Check conditions
    if not check_conditions(line.conditions):
        # Skip to next
        if line.next_line_id:
            display_line(dialogue_id, line.next_line_id)
        else:
            end_dialogue()
        return

    line_displayed.emit(line)

    # Auto-advance or wait for player
    if line.choices.is_empty() and line.next_line_id:
        # Wait for player to click
        await get_tree().create_timer(0.1).timeout
    elif line.choices.is_empty():
        end_dialogue()

func select_choice(dialogue_id: String, choice: DialogueChoice) -> void:
    choice_selected.emit(choice)

    # Apply effects
    for effect in choice.effects:
        apply_effect(effect)

    # Continue to next line
    if choice.next_line_id:
        display_line(dialogue_id, choice.next_line_id)
    else:
        end_dialogue()

func end_dialogue() -> void:
    dialogue_ended.emit()

func check_conditions(conditions: Array[String]) -> bool:
    for condition in conditions:
        if not flags.get(condition, false):
            return false
    return true

func apply_effect(effect: String) -> void:
    # Parse effect string, e.g., "set_flag:met_npc"
    var parts := effect.split(":")
    match parts[0]:
        "set_flag":
            flags[parts[1]] = true
        "give_item":
            # Integration with inventory
            pass

Dialogue UI

# dialogue_ui.gd
extends Control

@onready var speaker_label := $Panel/Speaker
@onready var text_label := $Panel/Text
@onready var portrait := $Panel/Portrait
@onready var choices_container := $Panel/Choices

var current_dialogue: String
var current_line: DialogueLine

func _ready() -> void:
    DialogueManager.line_displayed.connect(_on_line_displayed)
    DialogueManager.dialogue_ended.connect(_on_dialogue_ended)
    visible = false

func _on_line_displayed(line: DialogueLine) -> void:
    visible = true
    current_line = line

    speaker_label.text = line.speaker
    portrait.texture = line.portrait

    # Typewriter effect
    text_label.text = ""
    for char in line.text:
        text_label.text += char
        await get_tree().create_timer(0.03).timeout

    # Show choices
    if line.choices.is_empty():
        # Wait for input to continue
        pass
    else:
        show_choices(line.choices)

func show_choices(choices: Array[DialogueChoice]) -> void:
    # Clear existing
    for child in choices_container.get_children():
        child.queue_free()

    # Add choice buttons
    for choice in choices:
        if not DialogueManager.check_conditions(choice.conditions):
            continue

        var button := Button.new()
        button.text = choice.choice_text
        button.pressed.connect(func(): _on_choice_selected(choice))
        choices_container.add_child(button)

func _on_choice_selected(choice: DialogueChoice) -> void:
    DialogueManager.select_choice(current_dialogue, choice)

func _on_dialogue_ended() -> void:
    visible = false

NPC Interaction

# npc.gd
extends CharacterBody2D

@export var dialogue_path: String = "res://dialogues/npc_1.tres"
@export var start_line: String = "start"

func interact() -> void:
    DialogueManager.start_dialogue(dialogue_path, start_line)

Dialogue Graph (Resource)

# dialogue_graph.gd
class_name DialogueGraph
extends Resource

@export var lines: Dictionary = {}  # line_id → DialogueLine

func _init() -> void:
    # Example structure
    lines["start"] = create_line("Hero", "Hello!")
    lines["response"] = create_line("NPC", "Greetings, traveler!")

func create_line(speaker: String, text: String) -> DialogueLine:
    var line := DialogueLine.new()
    line.speaker = speaker
    line.text = text
    return line

Localization

# Use Godot's built-in CSV import
# dialogue_en.csv:
# dialogue_id,speaker,text
# npc_1_start,Hero,"Hello!"
# npc_1_response,NPC,"Greetings!"

func get_localized_line(line_id: String) -> String:
    return tr(line_id)

Advanced: Voice Acting

@onready var voice_player := $AudioStreamPlayer

func play_voice_line(line_id: String) -> void:
    var audio := load("res://voice/" + line_id + ".mp3")
    if audio:
        voice_player.stream = audio
        voice_player.play()

Best Practices

  1. Resource-Based - Store dialogues as resources
  2. Flag System - Track player choices
  3. Typewriter Effect - Adds polish
  4. Skip Button - Let players skip

Reference

  • Related: godot-signal-architecture, godot-save-load-systems, godot-ui-rich-text

Related

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.9%
按下载量换算274

Claude

30.33%
按下载量换算252

Cursor

19.94%
按下载量换算166

Gemini CLI

8.54%
按下载量换算71

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills