bvg-route

Route planning for Berlin public transport (BVG) using the v6.bvg.transport.rest API. Use when the user asks for: (1) route suggestions between two addresses or stops, (2) live next-departure info for a stop, (3) arrival-time–based journey planning (arrive-by or depart-at). Supports outputting 2–3 options ranked by travel time, transfers, and walking, and returning step-by-step directions and refresh tokens for live updates.

7 stars

Best use case

bvg-route is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Route planning for Berlin public transport (BVG) using the v6.bvg.transport.rest API. Use when the user asks for: (1) route suggestions between two addresses or stops, (2) live next-departure info for a stop, (3) arrival-time–based journey planning (arrive-by or depart-at). Supports outputting 2–3 options ranked by travel time, transfers, and walking, and returning step-by-step directions and refresh tokens for live updates.

Teams using bvg-route should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/bvg-route/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/jaysonsantos/bvg-route/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/bvg-route/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How bvg-route Compares

Feature / Agentbvg-routeStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Route planning for Berlin public transport (BVG) using the v6.bvg.transport.rest API. Use when the user asks for: (1) route suggestions between two addresses or stops, (2) live next-departure info for a stop, (3) arrival-time–based journey planning (arrive-by or depart-at). Supports outputting 2–3 options ranked by travel time, transfers, and walking, and returning step-by-step directions and refresh tokens for live updates.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# BVG Route Planner Skill

Purpose
- Provide concise, actionable public-transport directions in Berlin using the v6.bvg.transport.rest API.

When to use
- User asks for directions between two places in Berlin (addresses, stop names, or coordinates).
- User asks for next departures from a stop/station.
- User requests to arrive by a specific time (arrive-by) or depart at a specific time.

Core behavior
1. Resolve `from` and `to` into either stop IDs (preferred) or address/POI objects using GET /locations or /locations/nearby.
2. Call GET /journeys with arrival or departure parameter as requested, request results=3 and stopovers=true to construct step-by-step legs.
3. Format 2–3 options: show total travel time, number of transfers, walking time, and estimated departure/arrival times.
4. Provide step-by-step instructions for the selected journey: walk to stop A (distance/time), take line X toward Y, get off at stop B (platform if available), final walk to destination.
5. When appropriate, include the journey refreshToken and a GET /journeys/:ref refresh step to update realtime delays.
6. For simple next-departure queries, use GET /stops/:id/departures with duration=20 (or configurable) and return the nearest 3 departures.

Outputs
- Human-readable routes with departure times, transfers, walking distances, estimated arrival, and concise step list.
- Machine-friendly JSON (optional) containing journey id, refreshToken, legs, and stop IDs for programmatic refreshes.

References
- The skill expects to use the v6.bvg.transport.rest API (https://v6.bvg.transport.rest/api.html). See references/API.md for summary and examples.

Examples (triggers)
- "How do I get from Invalidenstraße 43 10115 to Leibnizstraße 62 by public transport?"
- "When is the next U-Bahn from U Rosenthaler Platz?"
- "Find journeys that arrive at Deutsche Oper by 17:50 tonight, fastest option first."

Notes for implementers
- **IBNR format (CRITICAL):** The `/journeys` endpoint requires **base IBNR codes only** (6 digits), not the full ID with `::` suffixes.
  - ❌ Wrong: `de:11000:900110001::3` or `de:11000:900110001`
  - ✅ Correct: `900110001` (extract base 6-digit code from `/stops` results)
  - Process: Call `/stops?query=...` first, extract the 6-digit `id` from results, use that for `/journeys`.
- **URL encoding (CRITICAL):** All query string parameters must be properly URL-encoded using `urllib.parse.quote()` or equivalent. Examples:
  - Space → `%20`
  - `ö` → `%C3%B6`
  - `ü` → `%C3%BC`
  - `Ä` → `%C3%84`
  - Special chars like `&`, `?`, `#` → their percent-encoded equivalents
  - Example: `Schönhauser Allee` → `Sch%C3%B6nhauser%20Allee`
  - Every API call with address/stop name strings in query params must encode before building the URL.
- Prefer stop/station IDs when calling /journeys (more reliable than fuzzy names): Use `/stops?query=...` to resolve names → base IBNR.
- Use `stopovers=true` to build readable step lists; include `entrances=true` when walking-to-entrance accuracy is important.
- Request `results=3` then offer the top 2–3 to the user.
- Handle timezone-aware ISO datetimes; default to Europe/Berlin if none provided.

Related Skills

routemesh-rpc

7
from Demerzels-lab/elsamultiskillagent

Call RouteMesh's unified JSON-RPC endpoint (lb.routeme.sh) for any EVM chainId using a helper script. Use when you need to fetch onchain data (eth_* methods), debug RPC responses, or demo RouteMesh routing for a chain/method.

camino-route

7
from Demerzels-lab/elsamultiskillagent

Get detailed routing between two points with distance, duration, and optional turn-by-turn directions.

terrain-route-video

7
from Demerzels-lab/elsamultiskillagent

Generate a minimalist terrain-style animated driving route video (MP4) from a list of stops (cities/POIs)

semantic-router

7
from Demerzels-lab/elsamultiskillagent

Auto-routing skill with configurable model pools and task type matching.

router

7
from Demerzels-lab/elsamultiskillagent

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.

nano-banana-pro-openrouter

7
from Demerzels-lab/elsamultiskillagent

Generate images with Nano Banana Pro via OpenRouter. Use when the user asks for image generation, mentions Nano Banana Pro, Gemini 3 Pro Image, or OpenRouter image generation.

model-router

7
from Demerzels-lab/elsamultiskillagent

A comprehensive AI model routing system that automatically selects the optimal model for any task. Set up multiple AI providers (Anthropic, OpenAI, Gemini, Moonshot, Z.ai, GLM) with secure API key storage, then route tasks to the best model based on task type, complexity, and cost optimization. Includes interactive setup wizard, task classification, and cost-effective delegation patterns. Use when you need "use X model for this", "switch model", "optimal model", "which model should I use", or to balance quality vs cost across multiple AI providers.

imagerouter

7
from Demerzels-lab/elsamultiskillagent

Generate AI images with any model using ImageRouter API (requires API key).

rotate-openrouter-key

7
from Demerzels-lab/elsamultiskillagent

Safely rotate the OpenRouter API key across all config files in an OpenClaw installation.

add-top-openrouter-models

7
from Demerzels-lab/elsamultiskillagent

Sync OpenRouter models used by OpenClaw into this installation's config.

sonnet-model-router

7
from Demerzels-lab/elsamultiskillagent

Self-aware multi-provider model routing for OpenClaw.

smart-router

7
from Demerzels-lab/elsamultiskillagent

Expertise-aware model router with semantic domain scoring, context-overflow protection, and security redaction. Automatically selects the optimal AI model using weighted expertise scoring (Feb 2026 benchmarks). Supports Claude, GPT, Gemini, Grok with automatic fallback chains, HITL gates, and cost optimization.