Lua Engineering Agent Skill

Develops, refactors, and audits high-performance Lua application and game-client code with clean module architectures and safe host interop.

Context cost
500 tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 2.0 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Build, refactor, or review Lua application and game-client code with explicit module boundaries, table semantics, coroutine ownership, error handling, and safe host-language interoperation. Use for .lua files or Lua-driven features.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

gamedevperformance

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md2.0 kB · preview
--- name: lua ---
6# Lua Engineering
7
8## 使用范围
9
10用于 Lua 功能开发、重构、审查和性能排查。开始前确认 Lua 版本、运行宿主、模块加载方式、是否存在静态检查或测试工具;不要假设所有项目使用相同的标准库或 Lua/C# 桥接层。
11
12## 工作方式
13
14- 使用局部变量和显式模块导出,避免无意创建全局变量。模块初始化应可预测,并避免依赖加载顺序产生副作用。
15- 明确 table 是数组、映射还是对象;不要依赖 pairs 的遍历顺序,也不要在遍历时随意增删同一张 table。需要稳定顺序时使用明确数组或排序。
16- nil 会移除 table 键。设计配置、序列化和可选字段时区分“缺失”“空值”和默认值,避免把默认值悄悄写回共享配置。
17- 协程必须有启动者、取消条件和错误传播路径;脚本热重载、场景卸载或对象销毁后不得继续驱动失效协程。
18- 跨 Lua 与宿主语言边界时,集中处理类型转换、对象生命周期和异常。跨边界调用必须检查对象是否仍有效,且不要把宿主框架的路径、生成代码或绑定名称写成通用约定。
19- 优化前先定位热点。高频路径中关注临时 table、字符串拼接、元方法和跨语言调用次数;保留清晰实现,除非性能测量证明需要优化。
20- 用项目现有的测试或最小可复现脚本验证模块行为,覆盖模块加载、错误输入、协程取消和关键数据结构。
21
22## 交付与边界
23
24交付时说明运行时假设、模块 API、状态所有权和验证方法。xLua、ToLua、SLua、热更新框架与游戏事件系统的细节应由对应项目的 .agents/skills/ 约束,而不是写入此通用技能。
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md80 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
430
on trigger
The instruction body, read only when the skill fires.
0.25%
of a 200k window
Ten skills this size would take about 3% of the window before you open a file.
050k100k150k200k context window

500 tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 2.0 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md2.0 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Lua Engineering · 500 tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/lua-engineering/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/lua-engineering" ] && { [ ! -e .claude/skills/lua-engineering ] || { mv .claude/skills/lua-engineering "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/lua-engineering" .claude/skills/ && echo "Installed .claude/skills/lua-engineering"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add weiweimhy/lua-engineering

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/lua-engineering/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/lua-engineering/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/lua-engineering" ] && { [ ! -e ~/.claude/skills/lua-engineering ] || { mv ~/.claude/skills/lua-engineering "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/lua-engineering" ~/.claude/skills/ && echo "Installed ~/.claude/skills/lua-engineering" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/lua-engineering/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as lua in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, lua-engineering.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceweiweimhy/lua-engineering

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill