Agent skill

Gscore Plugin Development

by Genshin-bots in Genshin-bots/gsuid_core

当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 toai"、"注册 aitools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright…

GPL-3.0Auto-check passedAI & LLM Engineering

Install Gscore Plugin Development

skills CLI
$ npx skills add Genshin-bots/gsuid_core --skill gscore-plugin-development -a claude-code

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

GitHub CLI
$ gh skill install Genshin-bots/gsuid_core gscore-plugin-development --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/Genshin-bots/gsuid_core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gscore-plugin-development .claude/skills/gscore-plugin-development && 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
gscore-plugin-development
GitHub stars
357
Token cost
~3.1k tokens
SKILL.md length
584 words
Files
23 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
GPL-3.0

At a glance

当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 toai"、"注册 aitools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright…

  • Works in 12 steps: 新建插件:先看 一、插件基础结构 确定目录与命名,参考 十五、完整插件示例 起步。 → 加命令:看 二、SV 与触发器 选合适触发器,按 三、消息收发 写发送 /… → 加配置:看 四、配置管理 定义 CONFIG_DEFAULT 与… → …
  • Tasks that involve Hooks and plugins
  • SKILL.md covers 文档目录索引, 推荐开发流程(按需跳转), 关键概念速记(先看这一段再决定读哪一章) and 关联文档(本 SKILL 文件夹内), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gscore Plugin Development is an agent skill from Genshin-bots/gsuid_core. 当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 toai"、"注册 aitools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright 哪个用哪个"、 "插件怎么挂自己的 HTTP 接口"、"插件怎么注册 FastAPI 路由"、 "插件怎么挂前端页面"、"registerpluginpage"、"插件页 iframe"、 "怎么扩展 RAG 嵌入后端"、"注册自定义 Embedding Provider"时触发此 SKILL。 对所有 GsCore Bot 插件开发任务都应优先读取此 SKILL。 为 GsCore 机器人框架编写插件的完整指南。涵盖项目级目录规范(参照 ZZZeroUID / SayuStock)、 Plugins/SV 双层架构、各类触发器的语义差异(oncommand vs onprefix vs onfullmatch vs onkeyword vs…

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including reference files (for example `references/01-plugin-basics.md`, `references/02-sv-and-triggers.md` and `references/03-messaging.md`).

It sits in AI & LLM Engineering, covering Hooks and plugins, Building AI agents and Backend development. It works with Playwright and FastAPI. The repository describes itself as: 💖一套业务逻辑,多个平台支持!异步核心框架GsCore,为插件编写提供完善平台支持、核心数据库统一、复用游戏查询逻辑、网页控制台,支持Bot列表: NoneBot2 & HoshinoBot & ZeroBot & YunZaiBot & Koishi. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Hooks and plugins
  • Tasks that involve Building AI agents
  • Tasks that involve Backend development

Example prompts

  • “帮我写一个 GsCore 插件”
  • “给这个插件加功能”
  • “改造触发器支持 AI”
  • “/gscore-plugin-development”

Workflow steps

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

  1. 新建插件:先看 一、插件基础结构 确定目录与命名,参考 十五、完整插件示例 起步。
  2. 加命令:看 二、SV 与触发器 选合适触发器,按 三、消息收发 写发送 / 多步会话;要监听进群/退群/戳一戳用 on_meta(§2.6),要撤回/禁言看 §3.5。
  3. 加配置:看 四、配置管理 定义 CONFIG_DEFAULT 与 StringConfig。
  4. 加数据库表:看 五、数据库操作;纯 SELECT 用 @with_read_session,写入仍用 @with_session;要可视化后台看 §5.5,要给已部署用户补字段看 §5.7。
  5. 加定时推送:看 六、定时任务与订阅 的 gs_subscribe 强制规范。
  6. 加启动逻辑:在 七、生命周期钩子 选合适的钩子。
  7. 加帮助 / 状态:看 八、帮助系统注册。
  8. 画图:参考 九、图片渲染范式 的"决策口诀"选 PIL / pytakumi / playwright。
  9. 想被 AI 调用
  10. 挂自己的 HTTP 后端接口:看 十九、FastAPI 插件 API——复用 gsuid_core.webconsole.app_app.app,3 行加一个接口;要同时挂 前端页 用 二十二、插件 Web 页面 的 register_plugin_page +…
  11. 扩展 RAG 嵌入后端:看 二十、嵌入 Provider 注册表——用 register_embedding_provider 注册 sentence_transformers / llama.cpp embedding 等自定义 Provider,懒 import +…
  12. 定制 MCP Server(Bearer 鉴权 / 工具导出过滤 / Event 会话补全):看 gscore-ai-core-api §11.1.7。

What it can do on your machine

Read from SKILL.md and the folder at commit f8c6dd2. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Gscore Plugin Development loads about 3.1k tokens when it runs, and up to ~60k if it reads all its reference files. Until then it costs about 238 tokens; SKILL.md has 584 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~238
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~60k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Genshin-bots/gsuid_core at commit f8c6dd2, republished under its GPL-3.0 licence (© Genshin-bots). 584 words, ~3,053 tokens.

Download SKILL.mdSave it as .claude/skills/gscore-plugin-development/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.
name
gscore-plugin-development
description
当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 to_ai"、"注册 ai_tools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright 哪个用哪个"、 "插件怎么挂自己的 HTTP 接口"、"插件怎么注册 FastAPI 路由"、 "插件怎么挂前端页面"、"register_plugin_page"、"插件页 iframe"、 "怎么扩展 RAG 嵌入后端"、"注册自定义 Embedding Provider"时触发此 SKILL。 对所有 GsCore Bot 插件开发任务都应优先读取此 SKILL。 为 GsCore 机器人框架编写插件的完整指南。涵盖项目级目录规范(参照 ZZZeroUID / SayuStock)、 Plugins/SV 双层架构、各类触发器的语义差异(on_command vs on_prefix vs on_fullmatch vs on_keyword vs on_regex vs on_message vs on_file)、on_meta 监听平台元事件(进群 / 退群 / 戳一戳 三种标准事件)、消息收发与撤回(wait_recall / unsend)/ 禁言(ban)、数据库操作并注册到网页控制台 (site.register_admin / GsAdminModel)、订阅系统(gs_subscribe)、定时任务、配置管理、 帮助系统(register_help + get_new_help)、推荐的渲染范式(优先 PIL → pytakumi → playwright 兜底)、AI 工具集成(@ai_tools、to_ai、ai_return、create_agent)、 知识库 / 别名注册、启动钩子、to_ai 批量改造工作流、为插件挂 FastAPI 后端接口、 嵌入 Provider 注册表(插件扩展 RAG 嵌入后端)。

GsCore 插件开发完整指南(核心入口)

本 SKILL 已按章节拆分为主入口 + references/ 子文档的形式组织。Agent 在需要某专题细节时, 顺着下文的相对路径按需 ViewFile / ReadFile 加载对应文件,不要一次性把所有内容塞进上下文。

文档目录索引

章节主题链接
一插件基础结构(目录、命名、入口三件套、Plugins vs SV、pyproject、资源路径、meta plugin、ruff / .vscode)references/01-plugin-basics.md
二SV 与触发器(SV 实例、八种触发器语义对比、装饰器通用参数、签名规范)references/02-sv-and-triggers.md
三消息收发(Event 属性、bot.send 各种形态、send_option、多步会话)references/03-messaging.md
四配置管理(CONFIG_DEFAULT、StringConfig、所有配置类型)references/04-config-management.md
五数据库操作(SQLModel 基类、@with_session / @with_read_session、async_maker、注册到 Web 控制台、exec_list 自动迁移)references/05-database.md
六定时任务与订阅(APScheduler、gs_subscribe 全套 API)references/06-scheduler-and-subscribe.md
七启动 / 关闭 / Bot 上线钩子(4 类钩子的区别与适用场景)references/07-lifecycle-hooks.md
八帮助系统注册(register_help、get_new_help、register_status)references/08-help-system.md
九图片渲染范式(PIL → pytakumi → playwright;AI 资料图走 render_chart_spec)references/09-image-rendering.md
十AI 集成:to_ai 与 ai_return(优先方案)references/10-ai-to-ai-and-ai-return.md
十一AI 集成:@ai_tools(含 covers/aliases;仅纯 AI 内部工具)references/11-ai-tools-decorator.md
十二AI 集成:知识库(ai_entity)与别名(ai_alias)注册references/12-ai-knowledge-and-alias.md
十三AI 集成:create_agent(临时专用 AI Agent)references/13-ai-create-agent.md
十四AI 集成:能力代理(AgentNode)Cookbook + render_agent / 业务节点(如 stock_report)+ plugin_developer_agentreferences/14-ai-capability-profile.md
十五完整插件示例(MyGameUID 端到端)references/15-full-plugin-example.md
十六常用工具模块速查(get_res_path / send_msg_to_master / error_reply / 限流 / 缓存 / 字体 / to_thread / cache_data / 批量播报 / 常用 import)references/16-common-utilities.md
十七代码规范红线(禁止 try/except 兜底、cast、type:ignore、getattr/dict.get 兜底、Any、同步阻塞函数)references/17-code-redlines.md
十八to_ai 批量改造工作流(背景、Step 0~4、完整股票 / 游戏示例、质量检查清单、Q&A)references/18-ai-trigger-migration.md
十九为插件挂 FastAPI 后端接口(共享 app、鉴权、CRUD、命名规范、反模式)references/19-fastapi-plugin-api.md
二十嵌入 Provider 注册表(插件扩展 RAG 嵌入后端:懒 import、工厂模式、降级策略)references/20-embedding-provider-registry.md
二十一AI 集成:在插件 repo 内管理 AI Skill(ai_skill 注册目录式 SKILL.md + 脚本/资源)references/21-ai-skill-registration.md
二十二为插件挂 Web 控制台页面(register_plugin_page + PluginAPI + 页面 i18n + Hub iframe)references/22-plugin-pages.md

推荐开发流程(按需跳转)

  1. 新建插件:先看 一、插件基础结构 确定目录与命名,参考 十五、完整插件示例 起步。
  2. 加命令:看 二、SV 与触发器 选合适触发器,按 三、消息收发 写发送 / 多步会话;要监听进群/退群/戳一戳用 on_meta(§2.6),要撤回/禁言看 §3.5。
  3. 加配置:看 四、配置管理 定义 CONFIG_DEFAULT 与 StringConfig。
  4. 加数据库表:看 五、数据库操作;纯 SELECT 用 @with_read_session,写入仍用 @with_session;要可视化后台看 §5.5,要给已部署用户补字段看 §5.7。
  5. 加定时推送:看 六、定时任务与订阅 的 gs_subscribe 强制规范。
  6. 加启动逻辑:在 七、生命周期钩子 选合适的钩子。
  7. 加帮助 / 状态:看 八、帮助系统注册。
  8. 画图:参考 九、图片渲染范式 的"决策口诀"选 PIL / pytakumi / playwright。
  9. 想被 AI 调用:
  10. 挂自己的 HTTP 后端接口:看 十九、FastAPI 插件 API——复用 gsuid_core.webconsole.app_app.app,3 行加一个接口;要同时挂 前端页 用 二十二、插件 Web 页面 的 register_plugin_page + PluginAPI。
  11. 扩展 RAG 嵌入后端:看 二十、嵌入 Provider 注册表——用 register_embedding_provider 注册 sentence_transformers / llama.cpp embedding 等自定义 Provider,懒 import + 工厂模式,自动出现在 WebConsole 下拉选项。
  12. 定制 MCP Server(Bearer 鉴权 / 工具导出过滤 / Event 会话补全):看 gscore-ai-core-api §11.1.7。
  13. 遇到 API 缓存 / 限流 / 字体 / 错误码 / 推主人 / 批量播报 等问题:直接看 十六、常用工具模块速查。
  14. 写完代码:用 十七、代码规范红线 自查(try/except、cast、type:ignore、getattr 兜底、Any、同步阻塞函数全部禁止)。
Show full SKILL.md (274 more words)Show less

关键概念速记(先看这一段再决定读哪一章)

  • 嵌套加载:外层 __init__.py + 外层 __nest__.py(空文件) + 内层 __init__.py 声明 Plugins(...) + 内层 __full__.py(空文件)。详见 一、插件基础结构 §1.2。
  • 基础设施插件(meta plugin):[tool.gsuid] kind = "meta" + 内层 api/。别人硬依赖 from gscore_mail.api import send;软依赖先 import_api("gscore_mail") 再同样 import。不要 try/except,不要改 Core 去声明对方的类型。详见 §1.6。
  • 每个插件自带 Ruff / .vscode:插件常被单独打开,读不到 Core 根配置。根目录放 ruff.toml + .vscode/extensions.json + .vscode/settings.json(extraPaths 指到 Core 仓库根)。详见 §1.7。
  • Plugins vs SV:插件级 vs 服务模块级;SV 自动从调用栈推断归属。详见 §1.3。
  • 触发器选择:on_command(推荐默认)vs on_prefix(强制带参)vs on_fullmatch(精确匹配)vs on_keyword(污染消息流,慎用)vs on_regex(复杂结构)vs on_file / on_message(特殊)。详见 §2.2。
  • 监听平台事件用 on_meta:标准元事件仅三种——user_join_group / user_exit_group / poke,data 字段跨平台统一(适配器侧已归一),可放心监听;其他事件不做适配。触发器内用 ev.get_meta(key) 读字段;与命令路径双向隔离。详见 §2.6。
  • 撤回 / 禁言:bot.send(..., wait_recall=True) 返回出站 id 列表(Optional[List[str]]),配 bot.unsend(...) 撤回;bot.ban(user_id, group_id, duration) 禁言(duration=0 解禁)。三者 HTTP 模式不支持。详见 §3.5。
  • to_ai vs @ai_tools 二选一:同一函数不可同时用。命令也允许用户直接触发 → to_ai;纯 AI 内部工具 → @ai_tools。详见 §10 / §11。
  • 插件工具要被跨措辞召回:填 covers(数据域) + aliases(领域·同义问法),勿只靠 docstring。详见 §11.5。
  • 主动推送必须用 gs_subscribe:不要 for bot in gss.active_bot.items(): await bot.target_send(...) 硬塞群号。详见 §6.2。
  • 数据库 Schema 变更用 exec_list:放在 on_core_start_before 阶段执行。详见 §5.7。
  • 只读查询用 @with_read_session:纯 SELECT 走独立读槽(SQLite WAL);写入 / 读后写仍用 @with_session。详见 §5.3。
  • MCP Server 插件钩子:register_mcp_token_verifier / register_mcp_event_enricher / register_mcp_export_filter,在插件 __init__.py 顶层注册。详见 gscore-ai-core-api §11.1.7。
  • 唯一允许 try/except 的地方:_ai_return_xxx() 辅助函数。详见 §17.3。
  • 图片渲染优先级:PIL(首选)→ pytakumi(推荐)→ playwright(兜底)。详见 §9.1。
  • 能力代理用 AgentNode + register_agent_node:交付边界默认框架叠加;出图派 render_agent;业务强制「插件工具 > web」。详见 §14。
  • to_ai 改造三层:触发器层 to_ai="..." + 数据/渲染层 ai_return() + 业务画像 CapabilityAgentProfile;详见 §18.1 与 §18.3 Step 0.4。
  • ai_return 注入点 = 数据已拿到 / 图片未生成:必须在数据层函数里,不能只在触发器层。详见 §18.3 Step 3。
  • 插件 FastAPI = 共享 app + Depends(require_auth):从 gsuid_core.webconsole.app_app import app 即可挂自己的 /api/<插件名>/... 路由;详见 §19.2 与 §19.3。
  • 插件前端页 = register_plugin_page + web/ 静态目录:Hub /plugins 右侧按钮打开 iframe;页面 i18n 放 web/locales/{zh-CN,en-US,ja-JP}.json,引入 /plugin-pages/_sdk/gshub-plugin.js。API 用 PluginAPI() 前缀 /api/<plugin_id>。详见 §22。
  • 嵌入 Provider 注册 = 懒 import + 工厂模式:插件 __init__.py 顶层调用 register_embedding_provider 注册 EmbeddingProviderEntry,重依赖只能在 factory 内部 import;注册时序保证早于消费;配置指向的 Provider 不可用时框架自动降级回 local 并记录 error,不会导致 AI 核心整体不可用。详见 §20。
  • AI Skill 随插件走 = ai_skill(目录):插件 __init__.py 顶层一行 ai_skill(Path(__file__).parent / "skills") 即把 repo 内 skills/<name>/SKILL.md(+ 脚本/资源)注册为运行时技能,无需挪进 data/ai_core/skills/;webconsole 内标记 source="plugin" 且只读。注意「运行时 Skill」≠「.agents/skills 开发文档 skill」。详见 §21。

关联文档(本 SKILL 文件夹内)

关联文档(同仓库其他位置)

© Genshin-bots, GPL-3.0. 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 22 other files (references) in .agents/skills/gscore-plugin-development of Genshin-bots/gsuid_core.

  • SKILL.md
  • references/01-plugin-basics.md
  • references/02-sv-and-triggers.md
  • references/03-messaging.md
  • references/04-config-management.md
  • references/05-database.md
  • references/06-scheduler-and-subscribe.md
  • references/07-lifecycle-hooks.md
  • references/08-help-system.md
  • references/09-image-rendering.md
  • references/10-ai-to-ai-and-ai-return.md
  • references/11-ai-tools-decorator.md
  • references/12-ai-knowledge-and-alias.md
  • references/13-ai-create-agent.md
  • references/14-ai-capability-profile.md
  • references/15-full-plugin-example.md
  • references/16-common-utilities.md
  • references/17-code-redlines.md
  • references/18-ai-trigger-migration.md
  • references/19-fastapi-plugin-api.md
  • … and 3 more

Open the folder on GitHubat commit f8c6dd2

Compare with similar skills

Gscore Plugin Development 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.

Gscore Plugin Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gscore Plugin Development this skillGenshin-bots/gsuid_core357—~3.1kAutomated safety check: PassGPL-3.0
AI SDK Developmenttrypostit/trypost6782 repos~3.5kAutomated safety check: PassMIT
Spring AI Integrationrrezartprebreza/spring-boot-skills2981 repos~2.5kAutomated safety check: PassMIT
AWS SDK Java V2 Bedrockgiuseppe-trisciuoglio/developer-kit3551 repos~3.2kAutomated safety check: NotesMIT
Cloudbase Agent PythonTencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~2.9kAutomated safety check: NotesMIT
Cookbook Aimldatabricks-solutions/databricks-apps-cookbook183—~1.7kAutomated safety check: PassCustom licence

Similar skills

  • AI SDK Development

    trypostit/trypost

    TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK.

    678 GitHub starsUsed in 2 repos~3.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Spring AI Integration

    rrezartprebreza/spring-boot-skills

    A skill your agent uses when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot.

    298 GitHub starsUsed in 1 repo~2.5k tokens
    AI & LLM EngineeringAuto-check passed
  • AWS SDK Java V2 Bedrock

    giuseppe-trisciuoglio/developer-kit

    Provides Amazon Bedrock patterns using AWS SDK for Java 2.x.

    355 GitHub starsUsed in 1 repo~3.2k tokens
    AI & LLM EngineeringAuto-check: notes
  • Cloudbase Agent Python

    TencentCloudBase/CloudBase-AI-Toolkit

    Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming +…

    1.1k GitHub starsUsed in 2 repos~2.9k tokens
    AI & LLM EngineeringAuto-check: notes
  • Cookbook Aiml

    databricks-solutions/databricks-apps-cookbook

    Invoke ML models, run vector search, and connect to MCP servers from Databricks Apps.

    183 GitHub stars~1.7k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Langchain RAG

    langchain-ai/langchain-skills

    Official

    INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    AI & LLM EngineeringAuto-check passed

More from Genshin-bots/gsuid_core

  • Test Audit

    Genshin-bots/gsuid_core

    Invoke whenever writing, changing, reviewing, or sweeping tests.

    357 GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Hai Simplified Technical

    Genshin-bots/gsuid_core

    Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague…

    357 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

Questions about Gscore Plugin Development

What does Gscore Plugin Development do?

当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 toai"、"注册 aitools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright…. Gscore Plugin Development is an agent skill from Genshin-bots/gsuid_core.

When should I use Gscore Plugin Development?

Gscore Plugin Development fits situations like: tasks that involve Hooks and plugins; tasks that involve Building AI agents; tasks that involve Backend development.

How do I install Gscore Plugin Development in Claude Code?

Run `npx skills add Genshin-bots/gsuid_core --skill gscore-plugin-development -a claude-code`. Or copy the skill folder (.agents/skills/gscore-plugin-development in Genshin-bots/gsuid_core) into .claude/skills/gscore-plugin-development in your project. Claude Code loads it when a task matches its description.

How do I install Gscore Plugin Development in Codex?

Run `npx skills add Genshin-bots/gsuid_core --skill gscore-plugin-development -a codex`. Or copy the skill folder (.agents/skills/gscore-plugin-development in Genshin-bots/gsuid_core) into .agents/skills/gscore-plugin-development in your project. Codex loads it when a task matches its description.

Can I use Gscore Plugin Development 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 Genshin-bots/gsuid_core --skill gscore-plugin-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gscore-plugin-development, .gemini/skills/gscore-plugin-development, .github/skills/gscore-plugin-development and .opencode/skills/gscore-plugin-development in your project.

What does Gscore Plugin Development need to run?

SKILL.md names no scripts, command-line tools or credentials: Gscore Plugin Development is instructions for the agent only.

Does Gscore Plugin Development access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gscore Plugin Development 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. Review the folder before installing.

What licence does Gscore Plugin Development use?

Gscore Plugin Development is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gscore Plugin Development use?

About 3.1k tokens (SKILL.md is roughly 12k 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 57k tokens, read only when the agent opens those files.

What are the alternatives to Gscore Plugin Development?

Skills that share tags, products or a category with Gscore Plugin Development: AI SDK Development (trypostit/trypost, 678 stars), Spring AI Integration (rrezartprebreza/spring-boot-skills, 298 stars), AWS SDK Java V2 Bedrock (giuseppe-trisciuoglio/developer-kit, 355 stars) and Cloudbase Agent Python (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gscore Plugin Development?

Genshin-bots (a GitHub organization) maintains it in Genshin-bots/gsuid_core, which has 357 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

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