vector-robot_skill

Overview

This skill lets you control an Anki Vector robot running wire-pod. It provides endpoints and helper scripts to speak through Vector, stream its camera, move head/lift/wheels, change eye colors, check battery, and trigger built-in animations. Use the wire-pod HTTP API and optional OpenClaw proxy for voice integration.

How this skill works

Commands are sent to the wire-pod HTTP API with a serial parameter identifying the robot. The skill sequences behavior control, speech, or motion calls to avoid conflicts and exposes simple curl examples and helper scripts for common tasks. Optional proxy integration forwards voice requests to a local AI service via request.json/response.json files for conversational replies.

When to use it

• You want Vector to speak or play a voiced response remotely.
• You need camera frames from Vector for monitoring or computer vision tasks.
• You want to move Vector’s head, lift, or wheels from scripts or automation.
• You want to change eye colors, volume, or query battery status.
• You need to trigger Vector animations or cloud intents programmatically.

Best practices

• Always include the &serial=SERIAL parameter to target the correct robot.
• Acquire behavior control before speech or risky movement and release it afterward to avoid conflicts.
• Be cautious with wheel commands: cliff sensors are disabled during behavior control—test at low speeds first.
• Use the provided helper scripts for common flows to reduce mistakes and URL-encode text for speech endpoints.
• When enabling voice proxy, restrict access to localhost or secure the endpoint to avoid unauthorized control.

Example use cases

• Announce notifications through Vector by sending text to the say_text endpoint via scripts.
• Stream or capture a camera frame for remote monitoring or to feed a vision pipeline.
• Execute a choreographed action: assume behavior control, run an animation or speech, then release control.
• Change eye color and volume as part of a mood or status indicator in an automation workflow.
• Integrate voice input by running the proxy server and reading/writing request.json and response.json for conversational responses.