gscore-development

gscore-development is a Codebase mapping & onboarding skill for AI agents, published by Genshin-bots in the gsuid_core repository on GitHub. Skillspace rates gscore-development D (62/100) and it passed the safety scan; the rating is based on static analysis only.

当用户要求"维护/开发 gsuid_core 框架本身"、"GsCore 是怎么启动的"、 "消息从进来到 AI 回复经过了哪些步骤"、"触发器是怎么匹配的"、 "handle_event / handle_ai_chat 干了什么"、"AI Session 怎么路由 / 怎么隔离"、 "工具注册表 / 渐进式工具加载 / find_tools 是怎么回事"、 "AI 为什么召不回某个插件的工具 / 工具选错插件 / 实体路由"、 "记忆没存下来 / 偏好记忆为空 / 私聊记忆 scope 不对"、 "AI 回复里出现 \<br\> / 输出文本归一化"、 "Heartbeat 定时巡检 / 免唤醒续聊怎么实现"、"记忆系统 / 偏好记忆 / 双路检索原理"、 "RAG 知识库 SQL 真值源 / 嵌入 Provider"、"定时任务 / Kanban 长任务编排"、 "启动钩子 on_core_start(_before) / init_ai_core 顺序"、"配置系统 / 配置热重载"、 "数据库基类 / @with_session / AI 表与总开关"、"帮助系统 register_help"、 "_Bot / Bot / MockBot 区别"、"网页控制台认证加密"、 "改框架要注意什么 / 有哪些已知坑"时触发此 SKILL。 凡是改动 `gsuid_core/` 框架核心(非业务插件)的任务都应优先读取此 SKILL。 面向 **GsCore(早柚核心 / gsuid-core)框架开发者与维护者**的系统级开发指南。 与「插件开发」「适配器开发」「AI Core API(给插件用)」三个 SKILL 不同,本 SKILL 讲的是**框架自身的内部实现与设计约束**:项目启动时序与两阶段钩子、插件发现/加载/ 依赖安装、配置系统(CoreConfig / PluginConfigStore / SV 配置 / 热重载)、事件处理 入口 `handler.py` 与触发器匹配、命令 vs AI 的分流、`handle_ai_chat` 全链路、 `_Bot`/`Bot`/`MockBot` 三类 Bot、AI Session 路由与隔离、Persona 系统、工具注册表与 渐进式装配(三层工具池 + Reranker 精排 +…

Grade
D
Quality
62 / 100
Safety
Passed
GitHub stars
338

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
78 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
GPL-3.0
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.