Rail logo

Rail

Community
JinFanZheng
rail

High-speed rail / train lookup workflow (China-focused). Use for timetables, ticket availability, delays, cancellations, or “today/latest” rail updates. Prefer official sources; always include source link + local update time; NEVER fabricate.

Overview

PublisherJinFanZheng
Repositorykode-sdk-csharp
Skill namerail
Stars
80
Forks
30
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by JinFanZheng on GitHub. Read the source before you install it.

Installation

Install the Rail AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JinFanZheng/kode-sdk-csharp.git /tmp/kode-sdk-csharp
mkdir -p .claude/skills
cp -r /tmp/kode-sdk-csharp/examples/Kode.Agent.WebApiAssistant/skills/rail .claude/skills/rail
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rail in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Rail on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Rail is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Rail skill(高铁/火车:时刻表 & 余票 & 晚点)

心智模型

  • 时刻表 ≠ 余票 ≠ 晚点:这三类信息的实时性和权威来源不同,输出时要明确你查的是哪一类。
  • 余票/晚点是强实时:必须带来源链接和当地更新时间;拿不到就别下结论。
  • 站名/日期是关键:同一城市多个车站;“今天/明天”一定要落到当地日期。

只问 1 个关键问题(仅在必要时)

缺关键信息时只问一个:

  • 缺日期: “你查 哪天(当地日期) 的车?”
  • 站名不清: “你从哪个站出发、到哪个站?(例如 深圳北 → 广州南)”
  • 目标不清(时刻表/余票/晚点): “你要看 时刻表余票 还是 晚点/停运?”

输出硬要求(强约束)

必须包含:

  • 类型:时刻表 / 余票 / 晚点 / 停运
  • 出发站 → 到达站 + 日期(当地日期)
  • 车次(如果用户提供或来源给出)
  • 来源 + 链接
  • 当地时间(来源页面的更新时间/发布时间;拿不到就写“来源未标注”)

建议格式(Markdown):

  • 深圳北 → 广州南(YYYY-MM-DD)余票/时刻表/晚点(来源:xxx;当地时间:YYYY-MM-DD HH:mm / 来源未标注)
    • 结果:最关键一两条(不要刷屏)

来源策略(中国为主)

白名单(用于下结论)

  • 12306.cn(官方售票/查询渠道;用于余票、正点/停运信息、权威时刻)

余票查询优先链路(首选 12306 深链)

当用户问 余票/票价/可买性 时,不要把“去某个链接自己看”当成答案。应当你自己先查到结果,再把结果 + 来源一起给用户;其中 12306 必须优先。

执行方式(在技能内约束,不依赖自定义工具)

  • 先打开 12306 深链页(leftTicket/initlcQuery/init),在页面上完成查询/读取结果(必要时用网页阅读/浏览器工具提取列表内容)。
  • 把关键结果整理成 2~5 条即可(车次/出发到达/历时/余票),避免刷屏。
  • 输出时必须带对应的 12306 深链(用户可复核),并写清楚你查询的北京时间(若页面未标注更新时间,就写“以查询时刻为准”)。

来源链接(作为引用/复核,而不是让用户代查)

  • 直达余票/车次列表(leftTicket)
    • 模板:https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=<出发站名>,<出发站码>&ts=<到达站名>,<到达站码>&date=<YYYY-MM-DD>&flag=N,N,Y
    • 示例:https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=江门,JOQ&ts=深圳北,IOQ&date=2026-01-19&flag=N,N,Y
  • 中转换乘查询(lcQuery)(用户明确要“换乘/中转”、或直达结果不理想时优先给这个):
    • 模板:https://kyfw.12306.cn/otn/lcQuery/init?linktypeid=dc&fs=<出发站名>,<出发站码>&ts=<到达站名>,<到达站码>&date=<YYYY-MM-DD>&flag=N,N,Y
    • 示例:https://kyfw.12306.cn/otn/lcQuery/init?linktypeid=dc&fs=江门,JOQ&ts=深圳北,IOQ&date=2026-01-19&flag=N,N,Y

使用要点:

  • 站码必须是 12306 站码(如 深圳北=IOQ)。若用户只给站名,先用 12306 官方站名码表确认站码;站名有歧义(同城多站/旧站名)就先问清再生成深链。
  • 更新时间写法:12306 余票列表页通常不单独标注“更新时间”,此时在输出中写:以查询时刻为准(北京时间 YYYY-MM-DD HH:mm),并明确“页面未标注更新时间”。
  • 结论约束:即使第三方页面显示余票/票价,也只能作为辅助;最终结论必须以该 12306 深链页(或等价官方查询页)为准。
  • 例外处理(仅在不可抗力时):若 12306 触发验证码/风控导致无法读取数据,必须明确说明“我现在无法在这里直接取到实时余票”,并给出 12306 深链作为备选复核路径(同时不要编造任何余票结论)。

全网(仅作补证/交叉验证)

  • 第三方站点可用于辅助检索/引导,但余票与停运/晚点类结论必须回到官方或等价权威来源。

NEVER(绝对禁止)

  • 不要编造余票数量、票价、晚点分钟数、停运信息
  • 不要把历史时刻表当作当天运行情况
  • 不要在没确认日期/站点时就输出具体车次与时间

Frequently asked questions

What does the Rail AI skill do?

High-speed rail / train lookup workflow (China-focused). Use for timetables, ticket availability, delays, cancellations, or “today/latest” rail updates. Prefer official sources; always include source link + local update time; NEVER fabricate.

Why use Rail on TypingMind?

Because you install it once and use it with any model. Rail is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Rail in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JinFanZheng/kode-sdk-csharp/tree/main/examples/Kode.Agent.WebApiAssistant/skills/rail. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rail?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Rail?

As many as you like. As long as a model supports skills, you can use Rail with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Rail AI skill free?

Yes. It is published on GitHub by JinFanZheng under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇