Skills Plugins MCP Prompt Model 博客 我的中心

unity-scriptdesign

Advise on Unity gameplay script quality

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=besty0728-unity-skills-skillsforunity-unity-skills-skills-scriptdesign-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name unity-scriptdesign description Advise on Unity gameplay script quality Before calling any skill in this module: if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via GET /skills/recommend?includeSchema=true ) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun. Triggers Reviewing code quality Untangling tightly-coupled scripts Planning a refactor for maintainability 审查代码质量、理顺高耦合脚本、为可维护性规划重构 Unity Script Design Review Use this skill before creating gameplay scripts, or after scripts are generated and need a design pass. Review Checklist Responsibility: does the script have one clear job? Role: should it really be a MonoBehaviour , ScriptableObject , or plain C# class? Coupling: are dependencies explicit instead of hidden globals or deep scene lookups? Communication: should this be a direct reference, interface call, or event? Performance: is there unnecessary Update , repeated Find , avoidable allocation, or reflection in hot paths? Lifecycle: are subscriptions, timers, and async work cleaned up clearly? Inspector UX: are serialized fields private, grouped, and explained? Testability: can the core logic move into a plain C# class? Naming: do class and field names explain intent without cryptic abbreviations? Data Lifecycle Boundary The Review Checklist above asks "where does this class live". Ask the same question for every field . Every piece of state has one of three lifecycles, and putting a field on the wrong one is the most common cause of "why did this break when the designer tweaked a value" and "why are my unit tests flaky". Lifecycle When the value is decided Where it belongs Typical idiom Authoring-time By a designer in the Editor, before Play ScriptableObject asset, or [SerializeField] private on a prefab Immutable at runtime; read via _config.Speed Composition-time Once per scene/instance, at Awake / Start private field, assigned from GetComponent / GetComponentInChildren / ctor arg Cached reference, no per-frame lookup Runtime-mutable Every frame or on gameplay events private backing field + public read-only property + event Exposed via public float Health { get; private set; } + OnHealthChanged Typical assignments Weapon damage / fire rate / clip size → Authoring-time (ScriptableObject so balance can be hot-swapped). Enemy AI's current target Transform → Composition-time if set once at spawn, Runtime-mutable if re-targeted each frame. Player current HP → Runtime-mutable with event. Never public float hp; . Reference to Rigidbody / Animator on the same GameObject → Composition-time , cached in Awake . Level music track → Authoring-time via ScriptableObject level descriptor. "Is in combat" flag → Runtime-mutable , but usually derived from other state — review whether it should be a field at all. Why the separation matters Mixing the three lifecycles is what turns a clean class into a god object. A MonoBehaviour whose public float speed is edited by both the Inspector and a power-up script has two owners and no invariant; a bug in either path corrupts the other. The ECS baking pipeline makes this distinction a hard architectural boundary (Authoring → Baker → System), and the discipline transfers directly: if you would not mix an Authoring component with runtime write-back in ECS, do not mix them in a MonoBehaviour either. Source: EntitiesSamples/Docs/baking.md:5-16 . Guardrails Mode : Documentation only — no REST skills to gate; load freely under any operating mode (Approval / Auto / Bypass). Prefer descriptive names over local shorthand. Do not “optimize” readability away for imagined productivity gains. Do not recommend complex patterns if a smaller refactor fixes the real problem. Output Format Keep: what is already good Simplify: what should stay straightforward Refactor: the highest-value structural change Performance notes: only real hotspots, not theoretical micro-optimizations Maintainability notes: naming, ownership, coupling, editor usability
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。