← 返回 Skills 市场
MTA Commuter
作者
Frankie Ottomanelli
· GitHub ↗
· v1.0.0
· MIT-0
72
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mta-commuter
功能描述
NYC commuter transit: LIRR, Metro-North, and Subway schedules, trip planning, and service alerts. Use when the user asks about train departures, arrivals, co...
安全使用建议
This skill looks like a straightforward, coherent MTA transit tool, but review a few practical points before installing: 1) Privacy: saved addresses are written to skills/mta/data/locations.json — treat that file as sensitive. The setup step says to 'geocode via web search', which will expose addresses to whatever geocoding/web service the agent uses. 2) Track watch uses undocumented endpoints (backend-unified.mylirr.org and backend-unified.mymnr.org) — the skill documents this; these endpoints may change or be rate‑limited. Running frequent cron polling (examples show every 20s) will generate repeated network requests; lower the frequency if you’re concerned about load or hitting rate limits. 3) Feeds: some GTFS‑RT endpoints in feeds.json point at api-endpoint.mta.info — these can require an MTA API key in other contexts; if real‑time data appears missing, confirm whether your environment/platform needs an API key or headers. 4) Run tests and inspect scripts if you want to be cautious: network calls are made with urllib (gtfs downloads, GTFS‑RT, alerts, track endpoints). If you rely on notification channels (Telegram via openclaw cron), ensure those channels are configured securely. If you want me to, I can: list every external URL the skill contacts, show where locations.json is read/written, or highlight all places the skill performs network I/O.
功能分析
Type: OpenClaw Skill
Name: mta-commuter
Version: 1.0.0
The skill bundle is a legitimate NYC transit tool for LIRR, Metro-North, and Subway schedules. It uses official MTA GTFS feeds and undocumented but relevant MTA web-app endpoints (e.g., backend-unified.mylirr.org) to provide real-time data and track assignments. The code is well-structured, includes an extensive test suite, and the instructions in SKILL.md are strictly aligned with the stated purpose of transit planning and location management without any signs of malicious intent or prompt injection attacks.
能力标签
能力评估
Purpose & Capability
Name/description (LIRR, Metro‑North, Subway schedules, trip planning, alerts) match the included Python scripts and data files. Required binary (python3) and the single pip dependency (gtfs‑realtime‑bindings) are appropriate for parsing GTFS and GTFS‑RT feeds. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md stays on task (how to run lookups, multi‑leg planning, alerts, station searches). It does instruct the agent to geocode user addresses 'via web search' during setup and to save addresses to data/locations.json — this means user addresses will be sent to whatever geocoding/web service the agent uses and stored locally. It also recommends using openclaw cron to poll track endpoints frequently (examples show every 20s), which will generate repeated network requests to the documented and undocumented endpoints. These are operational/privacy considerations rather than indicators of malice.
Install Mechanism
This is instruction‑only with no registry install spec; SKILL.md notes a single pip requirement (gtfs‑realtime‑bindings). Using pip for a protobuf binding is proportional. No arbitrary remote archive downloads or extract/install steps are present.
Credentials
The skill declares no required environment variables or credentials, which matches most of the code. One minor potential mismatch: feeds.json uses api-endpoint.mta.info GTFS‑RT URLs (MTA developer endpoints) while SKILL.md states 'no API key required.' In practice some MTA endpoints require an API key; the code does not send custom auth headers, so availability may vary. The skill also reads/writes data/locations.json (local storage of saved addresses) which is expected but should be considered sensitive.
Persistence & Privilege
The skill is not always-on and is user-invocable. It stores saved locations to its own data/locations.json (normal). It does not request to modify other skills' configs or system-wide settings. The only persistence/automation example is adding openclaw cron jobs for track watches — that is a normal platform operation but can cause frequent autonomous network polling if configured.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install mta-commuter - 安装完成后，直接呼叫该 Skill 的名称或使用
/mta-commuter触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release providing schedules, trip planning, and service alerts for LIRR, Metro-North, and NYC Subway.
- Supports direct schedule lookup, multi-leg trip planning, and finding nearby stations across all covered systems.
- Live train delay and service alert integration using MTA GTFS static and real-time feeds.
- Includes track watch functionality for LIRR and Metro-North departure platforms (via optional cron jobs).
- Allows user location management for personalized trip planning.
- Provides setup guidance and usage examples for all major features.
元数据
常见问题
MTA Commuter 是什么？
NYC commuter transit: LIRR, Metro-North, and Subway schedules, trip planning, and service alerts. Use when the user asks about train departures, arrivals, co... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 72 次。
如何安装 MTA Commuter？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mta-commuter」即可一键安装，无需额外配置。
MTA Commuter 是免费的吗？
是的，MTA Commuter 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
MTA Commuter 支持哪些平台？
MTA Commuter 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 MTA Commuter？
由 Frankie Ottomanelli（@ottomanelli）开发并维护，当前版本 v1.0.0。
推荐 Skills