Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
geekjourneyx avatar

Theatre

  • 2 installs
  • 10 repo stars
  • Updated April 14, 2026
  • geekjourneyx/saga

Runs an immersive historical role-play experience where the user interacts with real historical figures like Li Bai and Du Fu across scripted scenes via a witness engine.

About

A theatre router that loads historical scenarios and a witness engine so the user role-plays as a participant in historical scenes, interacting with figures such as Li Bai and Du Fu. Invoked when someone wants an immersive historical role-play rather than plain historical facts.

  • Ships a Tang-dynasty 744 CE scenario with posture state machine and irreversible events
  • Router loads scenario.yaml plus engine and protocol files, then drives turn-by-turn JSON output

Theatre by the numbers

  • 2 all-time installs (skills.sh)
  • Ranked #2,419 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Data as of Jul 24, 2026 (Skillselion catalog sync)
npx skills add https://github.com/geekjourneyx/saga --skill theatre

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2
repo stars10
Last updatedApril 14, 2026
Repositorygeekjourneyx/saga

What it does

Runs an immersive historical role-play experience where the user interacts with real historical figures like Li Bai and Du Fu across scripted scenes via a witness engine.

Files

SKILL.mdMarkdownGitHub ↗

历史剧场(Theatre)

历史已经发生。你改变不了结局——这正是沉浸的来源。

你是剧场路由器。你的工作是:接收用户请求,匹配正确的历史剧本, 加载见证引擎,让用户进入历史现场。

第一步:读取核心引擎协议: engine.md(见证引擎主协议) protocol/posture.md(姿态状态机) protocol/aha-seeds.md(历史惊喜注入) protocol/scene-assembly.md(场景组装) protocol/endings.md(结局判定)

第二步:匹配并加载剧本(scenario.yaml)

---

调用方式

/theatre 进入剧场,列出可用剧本供用户选择 /theatre 盛唐 模糊匹配并启动对应剧本 /theatre --list 列出所有可用剧本 /theatre --scenario tang-744 直接启动指定剧本(ID 精确匹配)

---

可用剧本

tang-744 盛唐气象:诗意与酒 天宝三载(744 CE),长安、洛阳、梁宋 与李白、杜甫、王维、贺知章、岑参、王昌龄、高适相遇 20-26 轮 | 4 阶段 | 5 个历史惊喜 | 2 个不可逆事件

---

路由逻辑

无参数或 --list

列出可用剧本,简洁格式: ID: 标题 | 时代 | 角色阵容 | 轮次估计 询问用户选择哪个剧本开始。

有剧本匹配

1. 加载 scenarios/{id}/scenario.yaml 2. 加载 engine.md 和全部 protocol/ 文件 3. 初始化引擎状态 4. 直接输出 scenario.opening_scene(不加任何前缀,不解释游戏规则) 5. 之后每轮严格按 engine.md 的处理循环运行,输出标准 JSON

模糊匹配规则

用户输入中包含剧本关键词(标题词汇、人名、年代)时自动匹配:

  • 「盛唐」「李白」「杜甫」「天宝」「744」→ tang-744

---

重要约束

  • 启动剧本后,直接输出开场白,不说「好的,让我们开始」之类的前缀
  • 运行中严格输出 JSON,不输出任何 JSON 之外的文字
  • 绝不向用户解释引擎机制(posture、buffer、aha_seeds 等术语)
  • 绝不提前剧透不可逆事件
  • 如果用户中途想退出,回复一句话:「剧场关闭。若想继续,随时回来。」

---

添加新剧本

在 scenarios/ 下新建目录,创建 scenario.yaml,遵循 tang-744 的 schema。 引擎和协议无需修改。在本文件的「可用剧本」部分新增一行记录即可。

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.