Token导航 LogoToken导航

Agent Skill · 研究检索

godot-genre-roguelike(戈多类型 roguelike)

godot-genre-roguelike 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。

godot-genre-roguelike 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 32,235。

总安装 2,561周安装 110GitHub Stars 137下载 898核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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-genre-roguelike(戈多类型 roguelike)
来源仓库:https://github.com/thedivergentai/gd-agentic-skills
仓库路径:skills/godot-genre-roguelike
安装命令:
npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-genre-roguelike
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-genre-roguelike

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

godot-genre-roguelike 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。适用于游戏开发中的戈多类型 roguelike 项目研究,可结合具体需求筛选技术方案、资源或实现思路。

通过 npx skills add 命令从指定 GitHub 仓库安装,需确认宿主环境支持及权限配置。安装前建议核实仓库维护状态,避免使用已弃用或存在安全隐患的技能版本。注意该技能可能涉及联网查询或文件操作,请评估其对系统的影响后再部署。

来源仓库内路径:skills/godot-genre-roguelike

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

godot-genre-roguelike 怎么安装?

在终端执行 npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-genre-rog…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

godot-genre-roguelike 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

godot-genre-roguelike 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-genre-roguelike 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

godot-genre-roguelike 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

godot-genre-roguelike 用的人多吗?

公开数据是累计安装 2,561 次,近一周安装 110 次,下载 898 次,GitHub 137 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

godot-genre-roguelike 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
godot-genre-roguelike

戈多类型 roguelike · 本页

2,561137执行命令未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Genre: Roguelike

Expert blueprint for roguelikes balancing challenge, progression, and replayability.

NEVER Do (Expert Anti-Patterns)

Generation & RNG

  • NEVER make runs dependent on pure RNG; strictly provide mitigation (rerolls, shops, pity timers) to ensure every run is winnable.
  • NEVER use unseeded RNG for world generation; strictly initialize isolated RandomNumberGenerator with a predictable seed for daily runs/debugging.
  • NEVER rely on @GlobalScope.randi() for critical logic; strictly use local RNG instances to prevent global state pollution.
  • NEVER use Array.pick_random() for critical content drops; strictly use a Shuffle Bag to prevent statistically unfair streaks.
  • NEVER generate massive dungeons on the main thread; strictly use WorkerThreadPool.add_task() or add_group_task() to distribute generation across cores and prevent frame freezes.
  • NEVER interact with the SceneTree from a background thread; strictly generate dungeon data in a thread-safe Array/PackedByteArray before parsing on the main thread.

Data & State

  • NEVER allow Save Scumming; strictly delete mid-run save files immediately upon loading to enforce permadeath.
  • NEVER allow Run State to leak into Meta State; strictly use separate singletons or Resources for RunManager and MetaManager.
  • NEVER scale meta-progression to be overpowered (+100% damage); strictly keep upgrades subtle (+5-15%) to maintain skill-based play.
  • NEVER forget to call duplicate(true) on base stat Resources; failing to deep-duplicate causes all entities to share a single health instance.
  • NEVER save run states to .tscn files; strictly serialize to JSON or binary in user:// to prevent bloat.
  • NEVER rely on the SceneTree as the source of truth for grid logic; strictly maintain grid data in a separate Dictionary or Array.

Grid & Performance

  • NEVER forget to handle Navigation re-baking; strictly rebake NavigationRegion2D AFTER procedural tiles are placed.
  • NEVER use AStar2D for tile grids; strictly use AStarGrid2D with jumping_enabled = true (Jump Point Search) for O(1) queries and high-performance pathing across open areas.
  • NEVER forget to call update() on AStarGrid2D after modifying states; strictly ensures pathfinding queries aren't stale.
  • NEVER use floats (Vector2) for discrete grid coordinates; strictly use Vector2i to prevent precision drift.
  • NEVER use Manhattan heuristics for 8-way movement; strictly use HEURISTIC_CHEBYSHEV or HEURISTIC_OCTILE.
  • NEVER iterate over every cell coordinate (0 to W,H) in GDScript; strictly use get_used_cells() for optimized tile access.
  • NEVER clear procedural levels using free(); strictly use queue_free() to avoid mid-frame segmentation faults.
  • NEVER broadcast mass state changes to a grid immediately; strictly use call_deferred() or call_group_flags to avoid frame spikes during turn transitions.
  • NEVER use heavy TileMapLayer nodes for high-resolution Fog of War; strictly use a GPU Shader Mask via ColorRect and an ImageTexture updated via RenderingServer.texture_2d_update().

🛠 Expert Components (scripts/)

Original Expert Patterns

Modular Components

Core Loop

  1. Preparation: Select character, equip meta-upgrades (see meta_progression_resource.gd).
  2. The Run: complete procedural levels (dungeon_generator_walker.gd), acquire temporary power-ups.
  3. The Challenge: Survive increasingly difficult encounters using A* pathfinding (astar_grid_handler.gd).
  4. Death/Victory: Run ends, resources calculated.
  5. Meta-Progression: Spend resources on permanent unlocks (meta_progression_resource.gd).
  6. Repeat: Start a new run with new capabilities.

Skill Chain

PhaseSkillsPurpose
1. Architecturestate-machines, autoloadsManaging Run State vs Meta State
2. World Gengodot-procedural-generation, tilemap, noiseCreating unique levels every run
3. Combatgodot-combat-system, enemy-aiFast-paced, high-stakes encounters
4. Progressionloot-tables, godot-inventory-systemManaging run-specific items/relics
5. Persistencesave-system, resourcesSaving meta-progress between runs

Architecture Overview

Roguelikes require a strict separation between Run State (temporary) and Meta State (persistent).

1. Run Manager (AutoLoad)

Handles the lifespan of a single run. Resets completely on death.

# run_manager.gd
extends Node

signal run_started
signal run_ended(victory: bool)
signal floor_changed(new_floor: int)

var current_seed: int
var current_floor: int = 1
var player_stats: Dictionary = {}
var inventory: Array[Resource] = []
var rng: RandomNumberGenerator

func start_run(seed_val: int = -1) -> void:
    rng = RandomNumberGenerator.new()
    if seed_val == -1:
        rng.randomize()
        current_seed = rng.seed
    else:
        current_seed = seed_val
        rng.seed = current_seed

    current_floor = 1
    _reset_run_state()
    run_started.emit()

func _reset_run_state() -> void:
    player_stats = { "hp": 100, "gold": 0 }
    inventory.clear()

func next_floor() -> void:
    current_floor += 1
    floor_changed.emit(current_floor)

func end_run(victory: bool) -> void:
    run_ended.emit(victory)
    # Trigger meta-progression save here

2. Meta-Progression (Resource)

Stores permanent unlocks.

# meta_progression.gd
class_name MetaProgression
extends Resource

@export var total_runs: int = 0
@export var unlocked_weapons: Array[String] = ["sword_basic"]
@export var currency: int = 0
@export var skill_tree_nodes: Dictionary = {} # node_id: level

func save() -> void:
    ResourceSaver.save(self, "user://meta_progression.tres")

static func load_or_create() -> MetaProgression:
    if ResourceLoader.exists("user://meta_progression.tres"):
        return ResourceLoader.load("user://meta_progression.tres")
    return MetaProgression.new()

Key Mechanics implementation

Procedural Dungeon Generation

  • Drunkard's Walk (Walker): Ideal for organic, cave-like or connected room layouts.
  • Binary Space Partitioning (BSP): Best for rectangular, connected room-and-hallway dungeons.
  • Wave Function Collapse (WFC): For highly detailed, rule-based tile environments and modular room assembly.
# dungeon_generator.gd
extends Node

@export var map_width: int = 50
@export var map_height: int = 50
@export var max_walkers: int = 5
@export var max_steps: int = 500

func generate_dungeon(tilemap: TileMapLayer, rng: RandomNumberGenerator) -> void:
    tilemap.clear()
    var walkers: Array[Vector2i] = [Vector2i(map_width/2, map_height/2)]
    var floor_tiles: Array[Vector2i] = []

    for step in max_steps:
        var new_walkers: Array[Vector2i] = []
        for walker in walkers:
            floor_tiles.append(walker)
            # 25% chance to destroy walker, 25% to spawn new one
            if rng.randf() < 0.25 and walkers.size() > 1:
                continue # Destroy
            if rng.randf() < 0.25 and walkers.size() < max_walkers:
                new_walkers.append(walker) # Spawn

            # Move walker
            var direction = [Vector2i.UP, Vector2i.DOWN, Vector2i.LEFT, Vector2i.RIGHT].pick_random()
            new_walkers.append(walker + direction)

        walkers = new_walkers

    # Set tiles
    for pos in floor_tiles:
        tilemap.set_cell(pos, 0, Vector2i(0,0)) # Assuming source_id 0 is floor

    # Post-process: Add walls, spawn points, etc.

Item/Relic System (Resource-based)

Relics modify stats or add behavior.

# relic.gd
class_name Relic
extends Resource

@export var id: String
@export var name: String
@export var icon: Texture2D
@export_multiline var description: String

# Hook system for complex interactions
func on_pickup(player: Node) -> void:
    pass

func on_damage_dealt(player: Node, target: Node, damage: int) -> int:
    return damage # Return modified damage

func on_kill(player: Node, target: Node) -> void:
    pass
# example_relic_vampirism.gd
extends Relic

func on_kill(player: Node, target: Node) -> void:
    player.heal(5)
    print("Vampirism triggered!")

Common Pitfalls

  1. RNG Dependency: Don't make runs entirely dependent on luck. Good roguelikes allow skill to mitigate bad RNG.
  2. Meta-progression Imbalance: If meta-upgrades are too strong, the game becomes a "grind to win" rather than "learn to win".
  3. Lack of Variety: Procedural generation is only as good as the content it arranges. You need *a lot* of content (rooms, enemies, items) to keep it fresh.
  4. Save Scumming: Players will try to quit to avoid death. Save the state only on floor transition or quit, and delete the save on load (optional, but standard for strict roguelikes).

Godot-Specific Tips

  • Seeded Runs: Always initialize RandomNumberGenerator with a seed. This allows players to share specific run layouts.
  • ResourceSaver: Use ResourceSaver for meta-progression, but be careful with cyclical references in deeply nested resources.
  • Scenes as Rooms: Build your "rooms" as separate scenes (Room1.tscn, Room2.tscn) and instance them into the generated layout for handcrafted quality within procedural layouts.
  • Navigation: Rebake NavigationRegion2D at runtime after generating the dungeon layout if using 2D navigation.

Advanced Techniques

  • Synergy System: Tag items (fire, projectile, companion) and check for tag combinations to create emergent power-ups.
  • Director AI: An invisible "Director" system that tracks player health/stress and adjusts spawn rates dynamically (like *Left 4 Dead*).

Reference

平台分布

Codex

35.47%
按下载量换算319

Claude

29.23%
按下载量换算262

Cursor

19.31%
按下载量换算173

Gemini CLI

8.77%
按下载量换算79

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/thedivergentai/gd-agentic-skills --skill godot-genre-roguelike 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills