Agent skill

Luban Dev

by AmaniDawn in AmaniDawn/DGame

DGame Luban 游戏配置全栈工具,支持枚举/Bean/数据表/字段/数据行的增删改查、配置校验、引用检查、导表脚本调用、ConfigMgr 封装与运行时消费链路排查。触发场景:(1) 编辑 GameConfig/Datas 下的游戏配置数据(道具表、文本表、模型表、音效表、特效表、GM 表等),(2) 新增/修改/删除配置表结构、字段、枚举或 Bean,(3) 处理…

MITAuto-check passedDocuments & Office

Install Luban Dev

skills CLI
$ npx skills add AmaniDawn/DGame --skill luban-dev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AmaniDawn/DGame luban-dev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AmaniDawn/DGame.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/luban-dev .claude/skills/luban-dev && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
luban-dev
GitHub stars
169
Token cost
~2.1k tokens
SKILL.md length
430 words
Files
15 (incl. scripts, references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

DGame Luban 游戏配置全栈工具,支持枚举/Bean/数据表/字段/数据行的增删改查、配置校验、引用检查、导表脚本调用、ConfigMgr 封装与运行时消费链路排查。触发场景:(1) 编辑 GameConfig/Datas 下的游戏配置数据(道具表、文本表、模型表、音效表、特效表、GM 表等),(2) 新增/修改/删除配置表结构、字段、枚举或 Bean,(3) 处理…

  • Works in 5 steps: 先判断改动属于数据、表结构、Bean/Enum、schema、模板、导表脚本还是运… → 读现有定义:tables.xlsx、beans.xlsx、enums.xlsx、目… → 改源文件,不改 LubanConfig/ 下生成代码。 → …
  • Tasks that involve Excel spreadsheets
  • SKILL.md covers 核心约定, 导表与发布成对约束, 默认工作流 and 新增配置表, plus 4 more sections
  • Runs Python scripts from its folder; calls python, bash and pip

What it does

Luban Dev is an agent skill from AmaniDawn/DGame. DGame Luban 游戏配置全栈工具,支持枚举/Bean/数据表/字段/数据行的增删改查、配置校验、引用检查、导表脚本调用、ConfigMgr 封装与运行时消费链路排查。触发场景:(1) 编辑 GameConfig/Datas 下的游戏配置数据(道具表、文本表、模型表、音效表、特效表、GM 表等),(2) 新增/修改/删除配置表结构、字段、枚举或 Bean,(3) 处理 tables.xlsx/beans.xlsx/enums.xlsx、 自动导入表或 DGame Sheet 拆表规则,(4) 修改 luban.conf、Defines、CustomTemplate 或 GenerateToolBinary 导表脚本,(5) 生成/校验客户端 GameProto 配置代码和二进制配置数据,(6) 排查 ConfigSystem、Tables、GameLogic/ConfigMgr 配置访问问题。即使用户未明确说 “Luban”,只要是在编辑或排查游戏配置数据,也应使用此技能。

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/command-reference.md` and `references/data-sources.md`).

It sits in Documents & Office, covering Excel spreadsheets. It works with Microsoft Excel. The repository describes itself as: 根据TEngine框架,结合工作经验,修改和增加一些实用性拓展修改的框架(包括但不限于工具方法,工具编辑器,部分底层逻辑调整)。不合入TEngine,主要是不想让TEngine太冗杂。 The licence is MIT.

When your agent uses it

  • Tasks that involve Excel spreadsheets

Example prompts

  • “/luban-dev”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 先判断改动属于数据、表结构、Bean/Enum、schema、模板、导表脚本还是运行时消费。
  2. 读现有定义:tables.xlsx、beans.xlsx、enums.xlsx、目标业务表和相关 ConfigMgr。
  3. 改源文件,不改 LubanConfig/ 下生成代码。
  4. 运行或提示运行默认导表脚本。
  5. 验证生成目录、Unity 编译、ConfigSystem.Instance.Tables 访问和业务管理器封装。

What it can do on your machine

Read from SKILL.md and the folder at commit df0e6f4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • bash
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • datable.cn

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Luban Dev loads about 2.1k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 430 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from AmaniDawn/DGame at commit df0e6f4, republished under its MIT licence (© AmaniDawn). 430 words, ~2,068 tokens.

Download SKILL.mdSave it as .claude/skills/luban-dev/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
luban-dev
description
DGame Luban 游戏配置全栈工具,支持枚举/Bean/数据表/字段/数据行的增删改查、配置校验、引用检查、导表脚本调用、ConfigMgr 封装与运行时消费链路排查。触发场景:(1) 编辑 GameConfig/Datas 下的游戏配置数据(道具表、文本表、模型表、音效表、特效表、GM 表等),(2) 新增/修改/删除配置表结构、字段、枚举或 Bean,(3) 处理 __tables__.xlsx/__beans__.xlsx/__enums__.xlsx、# 自动导入表或 DGame Sheet 拆表规则,(4) 修改 luban.conf、Defines、CustomTemplate 或 GenerateTool_Binary 导表脚本,(5) 生成/校验客户端 GameProto 配置代码和二进制配置数据,(6) 排查 ConfigSystem、Tables、GameLogic/ConfigMgr 配置访问问题。即使用户未明确说 “Luban”,只要是在编辑或排查游戏配置数据,也应使用此技能。

DGame Luban 配置开发

核心约定

现有 Excel 表结构保护
  • 修改已有业务表字段前,先按逻辑字段名压缩并删除字段区间内、字段末尾的空列,再追加字段。

  • DGame 普通表通常包含 ##var、##type、##group 和 ## 注释标记行,但这不是固定行号规则。修改前必须读取当前 Sheet 的全部标记行;多行 ##var/##type、纵表和额外注释行必须按原顺序保留,字段工具应复用现有注释行。

  • 追加/删除字段后必须检查 field list 的列号连续、validate --all 通过,再执行导表。

  • 源头:GameConfig/Datas/、GameConfig/Defines/、GameConfig/CustomTemplate/,不要手改生成产物。

  • 默认生成:客户端 cs-bin 代码 + bin/json 数据,优先走 LazyLoad。

  • 默认脚本:GameConfig/GenerateTool_Binary/gen_bin_client_lazyload.bat。

  • 代码输出:GameUnity/Assets/Scripts/HotFix/GameProto/LubanConfig/。

  • 桥接文件:ConfigSystem.cs、ExternalTypeUtil.cs 由模板复制到 GameUnity/Assets/Scripts/HotFix/GameProto/。

  • 数据输出:二进制到 GameUnity/Assets/BundleAssets/Configs/Binary/;Json 路径以 GenerateTool_Binary/path_define.* 当前配置为准。

  • 命名空间/顶层模块:GameProto;总表管理器:Tables。

  • 业务访问:优先在 GameUnity/Assets/Scripts/HotFix/GameLogic/ConfigMgr/ 封装 XxxConfigMgr,不要把 TbXXX 访问散落到业务层。

导出脚本

所有脚本位于 GameConfig/GenerateTool_Binary/,使用相对路径调用。

脚本用途说明
gen_bin_client_lazyload客户端(推荐,LazyLoad 模板)AI 默认调用此脚本
gen_bin_client客户端(标准模板)非懒加载
gen_bin_server_lazyload服务端(LazyLoad 模板)需要服务端配置时使用
gen_bin_server服务端(标准模板)非懒加载
gen_bin_all_lazyload客户端 + 服务端(LazyLoad 模板)一键导出两端
gen_bin_all客户端 + 服务端(标准模板)一键导出两端,非懒加载
AI 调用导表命令

根据操作系统选择对应扩展名。默认只导客户端 LazyLoad:

Windows:

powershell
cmd /c "set AI_MODE=1 && GameConfig\GenerateTool_Binary\gen_bin_client_lazyload.bat"

macOS/Linux:

bash
bash GameConfig/GenerateTool_Binary/gen_bin_client_lazyload.sh
Workflow 导表边界

跨配置或需要写入生产输出时,优先使用仓库 Workflow:

powershell
python .agents/scripts/workflow.py luban validate
python .agents/scripts/workflow.py luban test
python .agents/scripts/workflow.py luban preview --mode lazyload
python .agents/scripts/workflow.py approve --plan <preview.json> --by <实际确认人> --reason <实际确认记录> --high-risk
python .agents/scripts/workflow.py luban apply --plan <preview.json> --approval <approval.json>

validate 和 test 不写生产目录;preview 会先执行一次隔离导表并记录 manifest,再生成绑定当前工作区、输入文件和输出范围的计划。需要 Unity 测试时,在 preview 中显式填写 --editmode-filter / --playmode-filter;未填写时 apply 只验证构建和 Editor 编译,并在报告中明确记录未执行测试。apply 必须使用同一计划和一次性审批,并在导表后比对隔离产物清单。直接调用 gen 只适用于用户已经明确授权生产目录写入的场景。

导表与发布成对约束

  • Luban 生成的 GameUnity/Assets/Scripts/HotFix/GameProto/LubanConfig/ 代码与 GameUnity/Assets/BundleAssets/Configs/Binary/ 二进制必须来自同一次导表;只更新其中一侧会造成运行时反序列化或字段错位。
  • 修改 __tables__.xlsx 的 tags、group_by 或 read_schema_from_file 后,必须重新执行对应客户端/全量导表脚本,并检查生成代码、Binary 和 Unity 编译结果。
  • read_schema_from_file 是表级开关:业务 Excel 已带 ##var/##type/##group 表头时通常设为 true;schema 已在 Defines 中维护、业务文件只提供数据时设为 false。不要凭表名猜值。

默认工作流

  1. 先判断改动属于数据、表结构、Bean/Enum、schema、模板、导表脚本还是运行时消费。
  2. 读现有定义:__tables__.xlsx、__beans__.xlsx、__enums__.xlsx、目标业务表和相关 ConfigMgr。
  3. 改源文件,不改 LubanConfig/ 下生成代码。
  4. 运行或提示运行默认导表脚本。
  5. 验证生成目录、Unity 编译、ConfigSystem.Instance.Tables 访问和业务管理器封装。

新增配置表

  1. 在 GameConfig/Datas/ 新增业务 Excel,普通表可使用 ##var、##type、##group、## 标记行;这是推荐格式,不代表所有现有表都固定为四行。
  2. 需要复合字段时补 __beans__.xlsx,需要枚举时补 __enums__.xlsx。
  3. 默认推荐在 __tables__.xlsx 显式注册 full_name、value_type、input、mode、tags。
  4. Luban 支持文件名 #<value_type>-<comment>.xlsx 自动导入,不需要在 __tables__.xlsx 注册;DGame 可用但不作为默认推荐。
  5. DGame 扩展支持 Sheet 名 #<value_type>-<comment> 自动拆表;导表前会拆成临时 # 文件,同样不需要注册,但仍按自动导入场景谨慎使用。
  6. 需要按字段分组访问时,优先在 __tables__.xlsx 的 tags 写 group_by:字段名。例如 group_by:GroupId 会为表生成 GroupedDataMap 和 GetListByGroupId(int),按组快速取得数据;自动导入表如需特殊 tags,先确认当前 Luban 支持方式。
  7. 配置 __tables__.xlsx 时必须明确写入 read_schema_from_file:true 表示从业务 Excel 表头读取字段定义,false 表示使用 Defines/schema 中的定义。新增表工具会根据实际 Sheet 标记行推断并写入布尔值,也可通过 --read-schema-from-file 或 --schema-in-defines 显式指定;该值错误会导致 schema 解析或导表失败。
  8. 单例配置可用 mode=one。
  9. 导表后在 GameLogic/ConfigMgr/ 补 XxxConfigMgr。

业务层常用访问:

csharp
using GameLogic;

var modelCfg = ModelConfigMgr.Instance.GetOrDefault(modelId);
var hasModel = ModelConfigMgr.Instance.ContainsKey(modelId);
var ok = SoundConfigMgr.Instance.TryGetValue(soundId, out var soundCfg);

只有在 XxxConfigMgr 内部封装时才直接碰 TbXXX:

csharp
using GameProto;

public ModelConfig GetOrDefault(int modelID) => TbModelConfig.GetOrDefault(modelID);

操作工具

可用 scripts/luban_helper.py 读写 Excel 配置,适合批量增删字段、查引用、校验数据。

前置条件

Python 3.8+,pip install -r .agents/skills/luban-dev/scripts/requirements.txt

执行方式
powershell
python .agents/skills/luban-dev/scripts/luban_helper.py --data-dir GameConfig/Datas <command>

--data-dir 默认就是 GameConfig/Datas,可省略;PowerShell 中 JSON 参数推荐用 --file 从文件读取。

参数类型:位置参数直接传值,不加 -- 前缀。例如 table get TbItemConfig,不是 table get --name TbItemConfig。

Show full SKILL.md (171 more words)Show less
命令速查
分类命令功能
枚举enum list/get/add/update/delete枚举 CRUD
结构bean list/get/add/update/deleteBean CRUD
表table list/get/add/update/delete表 CRUD;默认显式注册到 __tables__.xlsx
字段field list/add/update/delete/disable/enable字段操作,支持 ## 禁用字段
数据row list/get/query/add/update/delete数据行操作
批量batch fields/rows批量字段/数据行操作
导入导出export/importJSON 导入导出
验证validate / ref数据验证 / 引用检查
类型type list/validate/suggest/search/guide/info类型系统
自动auto list/create# 自动导入表;DGame 支持但不默认推荐
管理rename/copy/diff/template表管理工具
附加alias/tag/variant/multirow/cache常量别名、标签、字段变体、多行结构、缓存
操作规范
  • 只读操作(list/get/query/search/validate/ref/diff):可直接执行。
  • 写入操作(add/update/delete/import/rename/copy/template/create):先确认目标表、字段、Sheet 和影响面。
  • 删除操作:先跑 ref 检查引用,提醒兼容性风险,再二次确认。
  • 修改前:先 table get / field list 确认结构,row get 避免主键冲突。
  • 修改后:跑 validate --all,再运行 DGame 导表脚本。
  • 自动导入:Luban 支持 # 文件,DGame 支持 # Sheet 拆表,但默认仍推荐 __tables__.xlsx 显式注册。
  • 迁移自动导入:migrate-auto 在 DGame 版本中保留命令入口但禁止执行,避免把推荐的显式注册表误迁移。
分组自动推断

添加字段时不指定 --group,脚本会按字段名和类型做保守推断:

  • c(客户端):name、desc、icon、image、sprite、model、spine、effect、sound、audio、ui、location、path、prefab、asset、local 等。
  • s(服务端):server、backend、logic、damage、hp、mp、exp、level、rate、attack、defense、platform、channel 等。
  • cs(两端):id、*_id、无法明确归属的字段。

这是辅助推断,不是架构决策;关键配置仍以目标表现有 ##group 和需求为准。

红线

  • 不直接改 GameUnity/Assets/Scripts/HotFix/GameProto/LubanConfig/。
  • 字段改名、删字段、改类型要当作兼容性风险处理。
  • 资源加载链路以当前 ConfigSystem 和 DGame 资源模块为准;若文档和代码冲突,优先信任代码。
  • 配置表运行时中文文本仍遵守项目文本规范,不把玩家可见文本硬编码进业务代码。

按需说明

场景文档
DGame 集成、目录、导表、运行时加载dgame-integration.md
DGame 表注册、自动导入、Sheet 拆表dgame-table-rules.md
工具命令详解、Excel CRUDoperating-guide.md
Luban 类型系统type-system.md
Schema / Bean / Enum / Table 定义schema.md
luban.conf 配置项luban-conf.md
校验器与引用检查validators.md
Excel 数据格式excel-format.md
CLI 参数command-reference.md
JSON/XML/YAML/Lua 数据源data-sources.md
DGame 运行时加载、ConfigMgr 封装、类型映射runtime.md

示例:DGame 当前不额外内置 examples/,以真实项目 GameConfig/Datas/、GameConfig/Defines/、GameConfig/CustomTemplate/、GameConfig/GenerateTool_Binary/ 作为示例来源。

脚本:scripts/luban_helper.py(DGame 化配置表操作工具)、scripts/requirements.txt(依赖)。

官方文档:https://www.datable.cn/docs/intro

导表空白行警告

Luban 提示表尾空白数据影响性能时,先执行 cleanup blank-rows TABLE 预览,确认 last_data_row 后再加 --apply。工具只删除表尾连续且所有业务列为空的行,不删除中间空行或含数据的行。清理后重新执行 validate --all 和导表脚本。

© AmaniDawn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in .agents/skills/luban-dev of AmaniDawn/DGame.

  • SKILL.md
  • agents/openai.yaml
  • references/command-reference.md
  • references/data-sources.md
  • references/dgame-integration.md
  • references/dgame-table-rules.md
  • references/excel-format.md
  • references/luban-conf.md
  • references/operating-guide.md
  • references/runtime.md
  • references/schema.md
  • references/type-system.md
  • references/validators.md
  • scripts/luban_helper.py
  • scripts/requirements.txt

Open the folder on GitHubat commit df0e6f4

Compare with similar skills

Luban Dev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Luban Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Luban Dev this skillAmaniDawn/DGame169—~2.1kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78214 repos~3.2kAutomated safety check: NotesMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence
Docx4jplutext/docx4j2.4k—~2.5kAutomated safety check: PassNone
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0
Cyber Pptcrazyykhllc-bit/CyberPPT1.8k—~10kAutomated safety check: PassMIT

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    782 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Docx4j

    plutext/docx4j

    A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…

    2.4k GitHub stars~2.5k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed
  • Cyber Ppt

    crazyykhllc-bit/CyberPPT

    当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。

    1.8k GitHub stars~10k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • Jev SEO

    AgriciDaniel/jev-seo

    Full live SEO audit of any website from its homepage URL, powered by Jev (TypeSafe's System One model).

    539 GitHub stars~2.5k tokensUpdated 17 days ago
    Documents & OfficeAuto-check: notes

More from AmaniDawn/DGame

  • Unity CLI

    AmaniDawn/DGame

    安装和修复 DGame Unity CLI,使用内嵌 Pipeline 与项目级 Workflow 排查 CLI/MCP 连接,查询 Unity Editor/Development Player,执行编译、测试和受控验证。涉及 CLI 安装、连接配置或实际 Unity 状态时使用;纯源码或文档任务不连接 Editor。

    169 GitHub stars~554 tokensUpdated 2 days ago
    Auto-check passed
  • Dgame Dev

    AmaniDawn/DGame

    DGame Unity 项目开发指导。触发词:DGame, GameModule, UIWindow, UIWidget, UIModule, AddUIEvent, GameEvent, GameEventDriver, EEventGroup, LoadAssetAsync, LoadGameObjectAsync, SetSprite, ConfigSystem, HybridCLR…

    169 GitHub stars~892 tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Luban Dev

What does Luban Dev do?

DGame Luban 游戏配置全栈工具,支持枚举/Bean/数据表/字段/数据行的增删改查、配置校验、引用检查、导表脚本调用、ConfigMgr 封装与运行时消费链路排查。触发场景:(1) 编辑 GameConfig/Datas 下的游戏配置数据(道具表、文本表、模型表、音效表、特效表、GM 表等),(2) 新增/修改/删除配置表结构、字段、枚举或 Bean,(3) 处理…. Luban Dev is an agent skill from AmaniDawn/DGame.

When should I use Luban Dev?

Luban Dev fits situations like: tasks that involve Excel spreadsheets.

How do I install Luban Dev in Claude Code?

Run `npx skills add AmaniDawn/DGame --skill luban-dev -a claude-code`. Or copy the skill folder (.agents/skills/luban-dev in AmaniDawn/DGame) into .claude/skills/luban-dev in your project. Claude Code loads it when a task matches its description.

How do I install Luban Dev in Codex?

Run `npx skills add AmaniDawn/DGame --skill luban-dev -a codex`. Or copy the skill folder (.agents/skills/luban-dev in AmaniDawn/DGame) into .agents/skills/luban-dev in your project. Codex loads it when a task matches its description.

Can I use Luban Dev in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AmaniDawn/DGame --skill luban-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/luban-dev, .gemini/skills/luban-dev, .github/skills/luban-dev and .opencode/skills/luban-dev in your project.

What does Luban Dev need to run?

Going by SKILL.md and its folder, Luban Dev needs Python for the scripts in its folder and the command-line tools its instructions call (python, bash and pip). Our summary lists: Python 3.

Does Luban Dev access the network?

SKILL.md names 1 domain. As links in the text: datable.cn. This is read from the text; nothing was executed.

Is Luban Dev safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Luban Dev use?

Luban Dev is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Luban Dev use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.

What are the alternatives to Luban Dev?

Skills that share tags, products or a category with Luban Dev: Markitdown (ImCa0/just-laws, 782 stars), Data Table Manager (n8n-io/n8n, 207k stars), Docx4j (plutext/docx4j, 2.4k stars) and Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Luban Dev?

AmaniDawn (a GitHub user) maintains it in AmaniDawn/DGame, which has 169 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

Source: AmaniDawn/DGame on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.