godot-mcp: Skill for Claude Code

.claude/skills/godot-skills/sub-skills/godot-gameplay-developer/SKILL.md

godot-gameplay-developer is a skill for Claude Code from hhhh124hhhh/godot-mcp. It costs 36 tokens per session (3,293 once invoked), scanned A, original, MIT.

A Godot 4.x game-development guide for building gameplay in Godot, a tool for making video games. It covers player movement, physics, game rules, and basic game AI using GDScript.

In plain words
What is it for?
Use it to build character controls, jumping and abilities, physical interactions, patrol or chase behavior, navigation, scoring, levels, and win conditions in Godot 4.x.
Why use it?
It helps turn gameplay ideas into the main systems needed for a working game.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is hhhh124hhhh/godot-mcp's own configuration. It tells Claude Code how to work on godot-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything godot-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hhhh124hhhh/godot-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hhhh124hhhh/godot-mcp/main/.claude/skills/godot-skills/sub-skills/godot-gameplay-developer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hhhh124hhhh/godot-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for godot-gameplay-developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer/github.svg)](https://agentmods.dev/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer)
Your own site
<a href="https://agentmods.dev/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer"><img src="https://agentmods.dev/badge/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for godot-gameplay-developer

Your own site · 80×15
<a href="https://agentmods.dev/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer"><img src="https://agentmods.dev/badge/skills/hhhh124hhhh/godot-mcp/godot-gameplay-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,293 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.03293
Opus 5 $0.00018 $0.01647
Sonnet 5 $0.00007 $0.00659
Haiku 4.5 $0.00004 $0.00329

Measured 11d ago against content hash d2ea056fa0e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

godot-gameplay-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/godot-skills/sub-skills/godot-gameplay-developer/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot 游戏玩法开发专家技能

重要提示: 本技能的所有代码示例均基于 Godot 4.5 最佳实践,使用 GDScript 语法。 确保在 Godot 4.x 环境中使用,避免与 Godot 3.x 语法混淆。

技能概述

godot-gameplay-developer 是专门用于开发 Godot 游戏核心玩法的智能化技能,能够根据用户的自然语言描述自动实现角色控制、物理交互、游戏规则、AI 行为等核心游戏机制。

核心功能

🎮 角色控制系统

  • 移动控制:2D/3D角色移动、跳跃、攀爬、游泳等
  • 状态管理:角色状态机(站立、行走、跑步、跳跃、攻击等)
  • 技能系统:角色技能、连招、特殊能力实现
  • 动画集成:与AnimationTree/AnimationPlayer的无缝集成

⚛️ 物理系统集成

  • 刚体物理:CharacterBody2D/3D、RigidBody2D/3D控制
  • 碰撞检测:精确的碰撞检测和响应系统
  • 物理交互:推拉、投掷、破坏等物理交互
  • 环境物理:流体、风力、重力等环境效果

🧠 AI 智能系统

  • 基础AI:巡逻、追踪、逃跑等基础行为
  • 决策系统:基于状态机的AI决策逻辑
  • 路径寻找:A*寻路和导航系统
  • 群体行为:编队、群体协作等高级AI

📊 游戏规则引擎

  • 胜利条件:多样化的游戏胜利条件设置
  • 计分系统:分数、等级、成就系统
  • 游戏流程:回合制、实时制等游戏节奏控制
  • 平衡系统:难度调节、数值平衡

使用方法

角色控制开发

用户: "我想要一个能跳跃、冲刺和二段跳的角色"
系统: 自动实现:
- CharacterBody2D基础控制
- 跳跃物理和二段跳逻辑
- 冲刺技能和冷却系统
- 相应的动画状态机
- 粒子特效集成

物理交互实现

用户: "创建一个可以推箱子、拉杠杆的物理谜题"
系统: 智能生成:
- 可推动箱子的物理体
- 杠杆机关机制
- 压力板触发器
- 物理约束和连接
- 谜题完成检测逻辑

AI行为开发

用户: "设计一个会巡逻、发现玩家后会追击的守卫AI"
系统: 完整实现:
- 守卫巡逻路径系统
- 视野检测机制
- 追击和丢失目标逻辑
- 警报和协作系统
- AI状态机管理

游戏规则实现

用户: "做一个三消游戏,包含连击系统和特殊道具"
系统: 全面开发:
- 三消匹配算法
- 连击计数和奖励系统
- 特殊道具和清除效果
- 分数和等级系统
- 游戏结束条件

工作流程

1. 需求解析

# 分析用户描述
- 提取核心玩法机制
- 识别技术实现要点
- 评估复杂度和依赖关系

2. 架构设计

# 设计实现架构
- 选择合适的节点类型
- 设计组件通信机制
- 规划数据流向

3. 代码实现

# 自动生成代码
- 实现核心逻辑
- 集成物理系统
- 配置动画状态
- 添加错误处理

4. 测试验证

# 功能测试
- 基础功能验证
- 边界情况测试
- 性能优化建议

MCP 工具集成

节点操作工具

  • create_node - 创建游戏对象节点
  • add_child_node - 添加子节点
  • configure_node - 配置节点属性
  • delete_node - 删除节点

脚本开发工具

  • create_script - 创建脚本文件
  • edit_script - 编辑脚本内容
  • attach_script - 附加脚本到节点
  • get_script_content - 获取脚本内容

场景管理工具

  • create_scene - 创建新场景
  • save_scene - 保存场景
  • load_scene - 加载场景
  • instance_scene - 实例化场景

调试测试工具

  • play_scene - 运行场景测试
  • get_node_properties - 获取节点属性
  • set_node_property - 设置节点属性
  • call_node_method - 调用节点方法

核心算法库

移动控制算法

# 平滑移动算法
func smooth_movement(delta: float) -> void:
    var target_velocity = input_direction * move_speed
    velocity = velocity.lerp(target_velocity, acceleration * delta)
    move_and_slide()

# 跳跃物理算法
func handle_jump() -> void:
    if is_on_floor() and Input.is_action_just_pressed("jump"):
        velocity.y = jump_velocity
        if can_double_jump and jumps_remaining > 0:
            jumps_remaining -= 1

Read the full file on GitHub · 408 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 408 lines · 36 tokens per session scan A d2ea056fa0e6

Subscribe to this mod's changes

godot-gameplay-developer is a skill published in the GitHub repository hhhh124hhhh/godot-mcp (42 stars, last pushed 9mo ago), licensed MIT. It adds 36 tokens to every session and 3,293 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories