Token导航 LogoToken导航

Agent Skill · 研究检索

central-station(中央车站)

central-station 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

central-station 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 4,033。

总安装 36,720周安装 1,484GitHub Stars 253下载 11,760核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:central-station(中央车站)
来源仓库:https://github.com/railwayapp/railway-skills
仓库路径:skills/central-station
安装命令:
npx skills add https://github.com/railwayapp/railway-skills --skill central-station
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/railwayapp/railway-skills --skill central-station

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

搜索和浏览 Railway 的社区支持平台以获取话题、讨论和解决方案。

查询八个主题(问题、反馈、社区、计费、错误赏金、隐私、滥用、模板)的最新、趋势或固定线程,并按状态和排序顺序进行过滤 通过 GraphQL 统一搜索或 LLM 数据导出端点搜索线程内容,以在所有公共线程中进行全文关键字匹配 以结构化数据或呈现的降价形式获取各个线程,以实现清晰的可读性 线程状态包括 OPEN、SOLVED、AWAITING_RAILWAY_RESPONSE、AWAITING_USER_RESPONSE、CLOSED 和 ARCHIVED,以帮助识别解决状态

来源仓库内路径:skills/central-station

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/railwayapp/railway-skills --skill central-stat…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

central-station 怎么安装?

在终端执行 npx skills add https://github.com/railwayapp/railway-skills --skill central-station。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

central-station 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

central-station 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

central-station 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

central-station 用的人多吗?

公开数据是累计安装 36,720 次,近一周安装 1,484 次,下载 11,760 次,GitHub 253 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

central-station 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
central-station

中央车站 · 本页

36,720253需要联网MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Central Station

Search and browse Railway's Central Station - the community support platform for threads, discussions, and documentation.

API Endpoints

EndpointURL
GraphQLhttps://station-server.railway.com/gql
Thread Markdownhttps://station-server.railway.com/api/threads/:slug
LLM Data Exporthttps://station-server.railway.com/api/llms-station
Frontendhttps://station.railway.com

When to Use

  • User wants to search Central Station threads or docs
  • User asks about community discussions or support questions
  • User wants to find threads about a specific topic (deployments, databases, etc.)
  • User asks "what are people asking about X"
  • User wants to see recent threads or questions
  • User mentions Central Station, community threads, or support discussions
  • User wants to find existing solutions before creating a new thread

When NOT to Use

  • User wants Railway product documentation - use railway-docs skill
  • User wants to check their project status - use status skill
  • User wants to manage their Railway project - use appropriate skill (deploy, environment, etc.)

Docs Search

For official Railway documentation, use the railway-docs skill which fetches from https://docs.railway.com/api/llms-docs.md.

Central Station's unifiedSearch can identify document types but has limited field access:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  --data-raw '{"query":"{ unifiedSearch(input: { query: \"volumes\", limit: 10 }) { results { document { __typename } } } }"}'

Document types returned: EsThreadItem (threads) and DocSearchResult (docs).

Note: For searching thread content, use the LLM Data Export endpoint instead (see below) which provides full thread data.

Quick Actions

Get Recent Threads

Fetch recent threads, optionally filtered by topic:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ threads(first: 10, sort: recent_activity) { edges { node { slug subject status topic { slug displayName } upvoteCount createdAt } } } }"}'

With topic filter:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ threads(first: 10, sort: recent_activity, topic: \"questions\") { edges { node { slug subject status topic { displayName } upvoteCount } } } }"}'

Get Thread by Slug

Fetch a specific thread with its content:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ thread(slug: \"THREAD_SLUG\") { slug subject status content { data } topic { displayName } upvoteCount } }"}'

Get Thread as Markdown

For a cleaner read, fetch the thread as markdown:

# Append .md to the frontend URL (requires topic slug)
curl -s 'https://station.railway.com/TOPIC_SLUG/THREAD_SLUG.md'

# Or use API with format query parameter
curl -s 'https://station-server.railway.com/api/threads/THREAD_SLUG?format=md'

# Or use API with Accept header
curl -s 'https://station-server.railway.com/api/threads/THREAD_SLUG' \
  -H 'Accept: text/markdown'

List Topics

Get all available topics:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ topics { slug displayName displayNamePlural } }"}'

Returns: questions, feedback, community, billing, bug-bounty, privacy, abuse, templates

Get Trending Threads

Fetch currently trending threads:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ trendingThreads { slug subject status topic { displayName } upvoteCount } }"}'

Get Pinned Threads

Fetch pinned/important threads:

curl -s 'https://station-server.railway.com/gql' \
  -H 'content-type: application/json' \
  -d '{"query": "{ pinnedThreads { slug subject topic { displayName } } }"}'

Search via LLM Data Export

For searching thread content, fetch all threads and filter locally:

curl -s 'https://station-server.railway.com/api/llms-station' | jq '.items[] | select(.title | test("postgres"; "i")) | {title, topic: .topic.name, status: .metadata.status}'

This endpoint returns all public threads with full content, useful for searching by keywords.

Thread Statuses

StatusDescription
OPENUnresolved, accepting responses
SOLVEDMarked as resolved
AWAITING_RAILWAY_RESPONSEWaiting for Railway team
AWAITING_USER_RESPONSEWaiting for original poster
CLOSEDNo longer accepting responses
ARCHIVEDOld thread, preserved for reference

Sort Options

For the threads query, use the sort parameter:

Sort ValueDescription
recent_activityMost recently active (default)
newestNewest first
highest_votesMost upvoted

Presenting Results

When showing threads:

  1. Thread title - The subject
  2. Topic - Category (questions, feedback, etc.)
  3. Status - Open, solved, awaiting response
  4. Summary - Brief preview from content
  5. Link - https://station.railway.com/{topic_slug}/{thread_slug}

Format example:

Found 3 threads about "postgres":

1. "Connection timeout when connecting to Postgres"
   Topic: questions | Status: SOLVED | Upvotes: 5
   https://station.railway.com/questions/connection-timeout-postgres

2. "How to connect to Postgres from local development"
   Topic: community | Status: OPEN | Upvotes: 12
   https://station.railway.com/community/connect-postgres-local

3. "Postgres SSL certificate verification failed"
   Topic: questions | Status: AWAITING_RAILWAY_RESPONSE
   https://station.railway.com/questions/postgres-ssl-verification

Common Search Patterns

User QueryFilter/Search
"Why is my deploy failing?"topic: questions, search: "deploy"
"Can't connect to database"topic: questions, search: "database" or "postgres"
"Domain not working"topic: questions, search: "domain"
"Feature requests"topic: feedback
"What are people building?"topic: community

Composability

  • After finding a thread: Summarize the solution or link to it
  • No results found: Suggest using railway-docs skill or creating a new thread
  • Technical issue found: Use relevant skill (deploy, environment, etc.) to help fix it

Error Handling

No Results Found

No threads found. Try:
- Different topic filter
- Checking Railway docs instead
- Creating a new thread at https://station.railway.com

Invalid Topic

List available topics first:

curl -s 'https://station-server.railway.com/gql' -H 'content-type: application/json' -d '{"query": "{ topics { slug } }"}'

Thread Not Found

Thread not found. It may have been deleted or marked private.

平台分布

Claude Code

31.12%
按下载量换算3,660

OpenCode

23.55%
按下载量换算2,769

Cursor

16.46%
按下载量换算1,936

Codex

12.03%
按下载量换算1,415

Gemini CLI

8.48%
按下载量换算997

Antigravity

3.36%
按下载量换算395

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills