A Python-based terminal utility for real-time monitoring of public transport bus stops in Chile.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ibuscl-cli
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install ibuscl-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
iBus CLI is a technical utility designed to provide developers with instant access to real-time bus arrival data for the Chilean public transportation network. By utilizing this tool within the Openclaw Skills framework, users can query stop codes and receive detailed information about approaching buses, including license plates and estimated distances. It is built to be lightweight, fast, and adaptable for both personal use and complex automation systems, bridging the gap between official transit data and your terminal environment.
Ensure you have Python 3.9+ installed. You can install iBus CLI directly using the following command:
bash <(curl -sSL https://raw.githubusercontent.com/iiroak/iBus.CL-API/main/install.sh)
For a manual installation from the source code, navigate to the repository and use:
pip install .
The skill organizes transit data into stop-level and service-level objects. When using the --raw flag, the following schema is returned:
| Property | Description |
|---|---|
paradero.codigo |
The unique identifier for the bus stop. |
paradero.nombre |
The descriptive name of the stop location. |
servicios |
An array containing details for every bus route passing the stop. |
buses[].patente |
The unique license plate of the approaching vehicle. |
buses[].distancia |
The real-time distance in meters from the vehicle to the stop. |
buses[].tiempo_llegada |
Qualitative arrival estimate (e.g., Llegando, Mas de 26 min). |
Loading
An AI-powered skill that transforms static images into high-quality 1080p video clips with music and transitions without requiring local hardware.

An automated video editing agent that processes raw footage into professional 1080p MP4 files using cloud-based GPU rendering and natural language commands.

A framework for building persistent memory systems that allow AI agents to retain information across sessions and context window resets.

An advanced skill for adding a structured knowledge graph layer to AI agents, enabling complex relationship traversal and multi-hop data retrieval.

Transform photo collections into high-quality 1080p MP4 videos using powerful cloud-based GPU rendering and natural language commands.

An automated cloud-rendering skill that transforms raw images, clips, and audio into professional promotional videos using simple text descriptions.








































