bahn

What This Skill Does

The Bahn skill for OpenClaw is a powerful, integrated toolkit for interacting with the Deutsche Bahn ecosystem without the need for private API keys. It functions as a specialized interface to various data streams including the IRIS XML interface, Vendo, and the analytical data provided by bahn.expert. Whether you are a daily commuter or an occasional traveler, this tool allows you to parse messy text snippets from the DB Navigator app, track real-time delays, calculate the probability of missing a transfer, and pull historical performance statistics for specific train services. By abstracting the complexity of German transit data, the Bahn skill enables agents to provide actionable, evidence-based travel advice.

Installation

To integrate this skill into your environment, use the OpenClaw manager via your terminal:

clawhub install openclaw/skills/skills/ableitung/openclaw-bahn

Ensure that you have Node.js installed in your environment, as the skill runs on a modular Node.js architecture found within the scripts/ directory of the OpenClaw repository.

Use Cases

• Commute Planning: Quickly identify whether a connection is feasible by calculating the probability of catching a short transfer.
• Delay Management: Automatically parse a shareable text snippet from the DB app to see if your train will be delayed and how that affects your overall journey.
• Historical Analysis: Use the --stats flag to check the reliability of a specific ICE connection before booking.
• Disruption Monitoring: Identify station-specific departures or track a single train by category and number to stay ahead of infrastructure-related delays.

Example Prompts

1. "Check the probability of me catching the transfer in Frankfurt for my current trip: [paste shareable text]."
2. "What are the historical delay patterns for ICE 933? I need to know if it's usually on time."
3. "Show me the live departures for Wuppertal Hbf right now, and include any relevant disruption information."

Tips & Limitations

• Use --json: When integrating this skill into larger automation workflows, always append the --json flag to receive structured output that your agent can programmatically interpret.
• Data Sources: The skill aggregates data from multiple sources. While generally accurate, keep in mind that real-time data is subject to network latency and the reporting speed of Deutsche Bahn’s own infrastructure.
• Model Opt-ins: The --predict and --stats flags are computationally more intensive and fetch extra data from bahn.expert. Only use these when you specifically need probabilistic insights, as they are not required for standard departure lookups.