New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Train Tickets

by nano-muse in nano-muse/nanoMuse

Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment.

GPL-3.0Auto-check passedAgent Workflows

Install Train Tickets

skills CLI
$ npx skills add nano-muse/nanoMuse --skill train-tickets -a claude-code

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

GitHub CLI
$ gh skill install nano-muse/nanoMuse train-tickets --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/nano-muse/nanoMuse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nanomuse/skills/builtin/train-tickets .claude/skills/train-tickets && 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
train-tickets
GitHub stars
608
Token cost
~1.4k tokens
SKILL.md length
814 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
GPL-3.0

At a glance

Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment.

  • Works in 4 steps: 12306__get-current-date first whenever… → 12306get-station-code-of-citys with… → 12306__get-tickets with date,… → …
  • The user asks about 火车票 / 高铁 / 12306
  • SKILL.md covers Is the server there?, What you need, Searching and Booking, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Train Tickets is an agent skill from nano-muse/nanoMuse. Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment. Use when the user asks about 火车票 / 高铁 / 12306 or a train between two cities.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers… The licence is GPL-3.0.

When your agent uses it

  • The user asks about 火车票 / 高铁 / 12306
  • A train between two cities

Example prompts

  • “Use the train-tickets skill to train in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking…”
  • “/train-tickets”

Workflow steps

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

  1. 12306__get-current-date first whenever the user said 明天 / 后天 / 下周三; the server's date is the one that counts, not yours.
  2. 12306get-station-code-of-citys with citys = 北京|上海 gives the code that stands for a whole city (every station in it). A specific station…
  3. 12306__get-tickets with date, fromStation, toStation (names or codes), and the filters that fit: trainFilterFlags (G 高铁/城际, D 动车, GD both…
  4. No direct train: 12306get-interline-tickets with the same arguments, middleStation optional: the first ten connections. Where a train…

What it can do on your machine

Read from SKILL.md and the folder at commit 2524aab. 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 (its code samples are toml).

    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):

    • github.com

    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

Train Tickets loads about 1.4k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 814 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 nano-muse/nanoMuse at commit 2524aab, republished under its GPL-3.0 licence (© nano-muse). 814 words, ~1,371 tokens.

Download SKILL.mdSave it as .claude/skills/train-tickets/SKILL.md (or your agent's skills folder).
name
train-tickets
description
Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment. Use when the user asks about 火车票 / 高铁 / 12306 or a train between two cities.
channel
mixed
metadata
author: nanoMuse version: "2"

Train tickets (12306)

Two hands, in this order. Searching is done with the 12306__* tools, a community MCP server (12306-mcp) that reads 12306's public timetable and seat counts; no login, no browser, no phone, nothing typed into an app. Booking has no API a personal agent may use; it happens on the phone's screen with phone_task, and only when the user has picked a train and said to book it.

Is the server there?

Look for 12306__get-tickets in your tools (the tools list is the only place it can be: no shell command or script to check). If it is not there, say so in one line, give the user the lines to add to config.toml, and, when a phone is connected, offer the search on the phone's screen instead (the old way, below); otherwise stop:

toml
[[mcp.servers]]
name = "12306"
command = "npx"
args = ["-y", "12306-mcp"]
risk = "safe"
egress = true

Node is needed for npx; the phone's own runtime has it.

What you need

  • From, to, the date, and whether it must be 高铁/动车 (G/D) or any train. The user's habits from recall (preferred stations, morning or evening, seat class, who travels) count as answers. Ask for the rest with one ask_user call.
  • Passengers, seat class and budget only matter for booking; do not ask for them to run a search.

Searching

  1. 12306__get-current-date first whenever the user said 明天 / 后天 / 下周三; the server's date is the one that counts, not yours.
  2. 12306__get-station-code-of-citys with citys = 北京|上海 gives the code that stands for a whole city (every station in it). A specific station (北京南, 上海虹桥): 12306__get-station-code-by-names. All the stations of a city: 12306__get-stations-code-in-city.
  3. 12306__get-tickets with date, fromStation, toStation (names or codes), and the filters that fit: trainFilterFlags (G 高铁/城际, D 动车, GD both, Z/T/K the slow ones, F 复兴号), earliestStartTime / latestStartTime (hours, 0–24), sortFlag (startTime, arriveTime, duration), limitedNum (ask for 5–8, not the whole day). One call; a second only if the first came back empty (widen the hours or drop the flag).
  4. No direct train: 12306__get-interline-tickets with the same arguments, middleStation optional: the first ten connections. Where a train stops and when: 12306__get-train-route-stations with trainCode and departDate.

Then, in your own words, the options that fit, three at most: 车次, 出发站 and time, 到达站 and time, 历时, the seat the user wants with its price and whether there are seats left (剩余 N 张 / 有 / 无). Say which you would take and why (earliest, shortest, cheapest that still has seats). Seat counts move by the minute; say so when the number is small.

Show full SKILL.md (402 more words)Show less

Booking

Only when the user has picked a train and said to book it, and only with a phone connected (the system prompt says whether one is). Without a phone, say the train, date and price and that the booking is theirs to make in the app; offer a reminder for when sales open or a calendar entry.

  • phone_task, app = 铁路12306: open the chosen train on the chosen date, pick the seat class and the passengers the user named, and stop on the order confirmation screen; read back the train, date, passengers, seats, total. The goal must say: 停在提交订单页，不要点「提交订单」或任何支付按钮。
  • Show the user that summary and ask whether to place the order. Only with a yes, one more phone_task for 提交订单; Sentinel will ask the user again for that tap; that is expected, not an error. Payment (支付) is the user's: say the order is placed and waiting to be paid in the app, and stop.
  • Never enter a password, a verification code or an ID number; when the app asks for one, stop with what the screen says and let the user do it.

Searching on the screen (fallback)

Only when the server is not configured and a phone is connected. One phone_task, app = 铁路12306, with a goal like:

在 12306 首页把出发地设为「北京」、目的地设为「上海」、日期设为 9月25日，点「查询车票」。在结果页读出按发车时间最早的前 5 班：车次、发车站和发车时间、到达站和到达时间、历时、二等座价格和余票。只查询，不要点任何车次进入下单。

Rules for the operator you can put in context: the left station is 出发, the right one 到达, the swap icon sits between them; the date is picked on a calendar page; 筛选 / 只看高铁 narrow the list; the results list scrolls. Prices on the list page are the lowest class ("¥xxx 起"); say so.

With the other hands

  • 12306 + 高德: the route to the station at that hour (the amap skill) and the train make one plan: leave home at 07:10, G1 at 08:00.
  • 12306 + 飞书 / 腾讯会议: the train that fits a meeting's time; the chosen 车次 and times go to the colleague or the group through lark-cli, once the user approves the text.
  • 12306 + the calendar and reminders: an event for the departure (station, 车次, seat), a reminder to pay within the app's time limit after 提交订单.

Finish

  • Reply with the trains or the order in a few lines: train, date, times, price, state (查询 / 已提交待支付). Save nothing unless asked; if the user wants it kept, trips/<route>-<date>.md in the workspace.
  • remember the stations and times the user keeps choosing, so the next search needs no question.

© nano-muse, 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

Just SKILL.md in nanomuse/skills/builtin/train-tickets of nano-muse/nanoMuse.

Open the folder on GitHubat commit 2524aab

Compare with similar skills

Train Tickets 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.

Train Tickets compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Train Tickets this skillnano-muse/nanoMuse608—~1.4kAutomated safety check: PassGPL-3.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from nano-muse/nanoMuse

All 11 skills in this repo

  • Amap

    nano-muse/nanoMuse

    Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.

    608 GitHub stars~964 tokensUpdated today
    Auto-check passed

  • Kuaidi100

    nano-muse/nanoMuse

    Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server: any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number.

    608 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Compare Options

    nano-muse/nanoMuse

    Compare two to five options (products, plans, places, tools, offers) on the criteria that matter to the user, in a table the user can re-weight, with a recommendation.

    608 GitHub stars~588 tokensUpdated today
    Auto-check passed

  • Feishu

    nano-muse/nanoMuse

    The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open.

    608 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Inbox Triage

    nano-muse/nanoMuse

    Go through recent mail and sort it into needs-a-reply, waiting-on-others, to-do and can-ignore, with draft replies ready for review.

    608 GitHub stars~597 tokensUpdated today
    Auto-check passed

  • Meeting Prep

    nano-muse/nanoMuse

    Prepare for a meeting (who is in it, what was last said with them, what the user owes them and wants from them) as a one-page brief.

    608 GitHub stars~659 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Train Tickets

What does Train Tickets do?

Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment. Train Tickets is an agent skill from nano-muse/nanoMuse. Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment.

When should I use Train Tickets?

Train Tickets fits situations like: the user asks about 火车票 / 高铁 / 12306; A train between two cities.

How do I install Train Tickets in Claude Code?

Run `npx skills add nano-muse/nanoMuse --skill train-tickets -a claude-code`. Or copy the skill folder (nanomuse/skills/builtin/train-tickets in nano-muse/nanoMuse) into .claude/skills/train-tickets in your project. Claude Code loads it when a task matches its description.

How do I install Train Tickets in Codex?

Run `npx skills add nano-muse/nanoMuse --skill train-tickets -a codex`. Or copy the skill folder (nanomuse/skills/builtin/train-tickets in nano-muse/nanoMuse) into .agents/skills/train-tickets in your project. Codex loads it when a task matches its description.

Can I use Train Tickets 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 nano-muse/nanoMuse --skill train-tickets -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/train-tickets, .gemini/skills/train-tickets, .github/skills/train-tickets and .opencode/skills/train-tickets in your project.

What does Train Tickets need to run?

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

Does Train Tickets access the network?

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

Is Train Tickets 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 Train Tickets use?

Train Tickets 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 Train Tickets use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Train Tickets?

Skills that share tags, products or a category with Train Tickets: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and MemPalace Memory Search (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Train Tickets?

nano-muse (a GitHub organization) maintains it in nano-muse/nanoMuse, which has 608 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

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