pidog-control

Translate natural language prompts into PiDog REST API actions.

Updated May 21, 2025
One-click install
npx skills add https://github.com/illogical/command-pidog --skill pidog-control
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pidog-control
Source: https://github.com/illogical/command-pidog/tree/main/.github/skills/pidog-control
Command: npx skills add https://github.com/illogical/command-pidog --skill pidog-control

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

PiDog control uses natural language to translate user intents into REST API calls to the PiDog hardware, reducing the complexity of issuing multiple API endpoints manually.

Core Features & Use Cases

  • Natural language to action mapping for PiDog, including movement, emotions, sensing, camera vision, ARIA interactions, and LED/sound controls.
  • Step-by-step workflows for performing common PiDog tasks via the REST API, such as moving, vision, and sonar-based decisions.
  • Use Case: A user can ask PiDog to "sit and handshake" and the skill will execute the corresponding API calls and provide feedback.

Quick Start

Use a natural language prompt to have PiDog perform a chosen action via the REST API.

Frequently Asked Questions about pidog-control

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I control PiDog with natural language commands?

Controlling PiDog with natural language commands involves translating user intents into specific REST API actions, allowing you to trigger movements, emotions, and sensor interactions using simple text prompts.

Can I use PiDog vision and sonar sensors through REST API calls?

Yes, you can use PiDog vision and sonar sensors through REST API calls by translating natural language requests into specific endpoints, enabling the robot to make sonar-based decisions and utilize camera vision.

What environment variables do I need to configure for PiDog REST API integration?

PiDog REST API integration requires configuring environment variables such as PIDOG_MOCK_HARDWARE and PIDOG_OLLAMA in your api/.env settings to ensure the running PiDog API communicates correctly with the hardware or mock environment.

Does natural language to action mapping work for PiDog LED and sound controls?

Natural language to action mapping does work for PiDog LED and sound controls, translating user prompts into the corresponding REST API endpoints to manage emotions, sounds, and visual feedback on the robot.

Why does PiDog require a running API to execute natural language actions?

PiDog requires a running API to execute natural language actions because the skill translates text prompts into REST API calls, acting as a bridge that issues multiple structured endpoints to the hardware on your behalf.

Is there a way to test PiDog actions without physical hardware connected?

You can test PiDog actions without physical hardware by setting the PIDOG_MOCK_HARDWARE environment variable in your api/.env file, allowing the REST API to process natural language commands in a simulated environment.