Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/misonl/ling/game-developmentnpx skills add MisonL/Ling --skill game-developmentgit clone --depth 1 https://github.com/MisonL/LingWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.01482 |
| Opus 5 | $0.00010 | $0.00741 |
| Sonnet 5 | $0.00004 | $0.00296 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
game-development 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
游戏开发
编排类技能：提供核心原则，并引导至专业子技能。
何时使用此技能
当你在进行游戏开发项目时使用。本技能讲解游戏开发的核心原则，并根据上下文指引到合适的子技能。
子技能路由
平台选择
| 如果目标平台是... | 使用子技能 |
|---|---|
| Web 浏览器（HTML5, WebGL） | game-development/web-games |
| 移动端（iOS, Android） | game-development/mobile-games |
| PC（Steam, 桌面） | game-development/pc-games |
| VR/AR 头显 | game-development/vr-ar |
维度选择
| 如果游戏是... | 使用子技能 |
|---|---|
| 2D（sprites, tilemaps） | game-development/2d-games |
| 3D（meshes, shaders） | game-development/3d-games |
专业领域
| 如果你需要... | 使用子技能 |
|---|---|
| GDD、平衡性、玩家心理 | game-development/game-design |
| 多人联机、网络同步 | game-development/multiplayer |
| 视觉风格、素材管线、动画 | game-development/game-art |
| 音效设计、音乐、自适应音频 | game-development/game-audio |
核心原则（全平台）
1. 游戏循环
不论平台，所有游戏都遵循这一模式：
INPUT -> 读取玩家操作
UPDATE -> 处理游戏逻辑（固定步长）
RENDER -> 绘制帧（插值）
固定步长规则：
- 物理/逻辑：固定频率（例如 50Hz）
- 渲染：尽可能快
- 在不同状态间做插值以保证画面平滑
2. 模式选择矩阵
| 模式 | 使用场景 | 示例 |
|---|---|---|
| 状态机（State Machine） | 3-5 个离散状态 | 玩家：Idle（待机）->Walk（行走）->Jump（跳跃） |
| 对象池（Object Pooling） | 频繁生成/销毁 | 子弹、粒子 |
| 观察者/事件（Observer/Events） | 跨系统通信 | 生命值->UI（界面）更新 |
| ECS（实体组件系统） | 大量相似实体 | RTS（即时战略）单位、粒子 |
| 命令（Command） | 撤销、回放、联网同步 | 输入记录 |
| 行为树（Behavior Tree） | 复杂 AI（人工智能）决策 | 敌人 AI |
决策规则： 先用状态机。只有在性能需要时再引入 ECS。
3. 输入抽象
将输入抽象为动作（Actions），而不是原始按键：
"jump" -> Space、手柄 A、触摸点击
"move" -> WASD、左摇杆、虚拟摇杆
原因： 便于多平台支持与可重绑控制。
4. 性能预算（60 FPS（帧率） = 16.67ms）
| 系统 | 预算 |
|---|---|
| 输入 | 1ms |
| 物理 | 3ms |
| AI（人工智能） | 2ms |
| 游戏逻辑 | 4ms |
| 渲染 | 5ms |
| 缓冲 | 1.67ms |
优化优先级：
- 算法（O(n²) -> O(n log n)）
- 批处理（减少 draw calls（绘制调用））
- 对象池（避免 GC（垃圾回收）峰值）
- LOD（细节层级，按距离调整细节）
- 裁剪（跳过不可见）
5. AI 复杂度选择
| AI 类型 | 复杂度 | 使用场景 |
|---|---|---|
| FSM（有限状态机） | 简单 | 3-5 状态，行为可预测 |
| 行为树（Behavior Tree） | 中等 | 模块化，策划友好 |
| GOAP（目标导向行动规划） | 高 | 基于规划的涌现行为 |
| 效用 AI（Utility AI） | 高 | 基于评分决策 |
6. 碰撞策略
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 168 lines · 20 tokens per session scan A f133124cd3ee
game-development is a skill published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,482 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
loading-assets
Use this skill when loading assets in Phaser 4. Covers the Loader plugin, loading images, spritesheets, atlases, audio, JSON, tilemaps, bitmap fonts, and tracking load progress. Triggers on: preload, this.load, asset loading, spritesheet, atlas, load progress.
2d-games
2D game development principles. Sprites, tilemaps, physics, camera.
soundclaw
Control Spotify playback, search music, and return shareable music links.
sprite-gen
Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…
skeleton
Edit skeleton bone transforms/hierarchy, retargeting modes, curve metadata, blend profiles, bone constraints, and learn constraints from animations (VibeUE SkeletonService). Socket CRUD, bone enumeration, physics-asset, and material/LOD inspection are owned by the engine SkeletalMeshTools. Use when the user asks to…
animation-montage
Create and manipulate Animation Montages — sections, slots, segments, branching points, notifies, and blend settings (AnimMontageService). Use when the user asks to create a montage (from an animation or empty), add or link montage sections, set up slots/segments, add branching points, or adjust montage blend timing.