OpenClaw Cat for Openclaw

An AI-driven virtual pet skill that brings a sassy and humorous cat persona to your agent environment using various LLM backends.

tony888880lang
v0.1.1
Mar 4, 2026
1
897
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install openclaw-cat

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install openclaw-cat using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is OpenClaw Cat?

OpenClaw Cat is a specialized personality module designed for Openclaw Skills that transforms a standard AI interaction into a playful role-play experience. It allows users to 'adopt' a virtual cat that lives within their deployment environment, responding to queries with a distinct, sassy, and humorous personality. By leveraging advanced Large Language Models, the skill simulates the thoughts and actions of a feline companion who treats the user like a lobster living at the bottom of the ocean.

This skill is more than just a chatbot; it is an exercise in character consistency and prompt engineering. Upon its first execution, the skill procedurally generates a unique persona including breed, temperament, and age, which is then persisted across sessions. Whether you are using OpenAI, Claude, or local models, this skill demonstrates how Openclaw Skills can be used to inject personality and engagement into technical environments.

OpenClaw Cat Use Cases

  • Triggering humorous role-play interactions during long coding sessions.
  • Testing the integration of multiple LLM providers within a single agent framework.
  • Customizing agent responses to include specific character traits and persistent states.
  • Providing a fun way to check system status or agent availability using natural language commands.

How OpenClaw Cat Works

  1. The user triggers the skill by sending the /cat command or asking about the cat's status in natural language.
  2. The skill checks for an existing persona in the local cache file; if none exists, it randomly generates a new set of attributes like breed and personality.
  3. The system constructs a prompt combining the user's query with the cat's specific character profile and speaking style.
  4. A request is dispatched to the configured LLM provider (such as OpenAI, Claude, or GLM) via the specified API key.
  5. The LLM generates a response in the 'sassy' voice of the cat, which is then displayed to the user in the OpenClaw interface.

OpenClaw Cat Setup

To integrate this feline companion into your Openclaw Skills setup, follow these steps:

  1. Copy the configuration template:
cp config.json.example config.json
  1. Configure your preferred LLM provider in config.json:
{
  "cat_name": "Oliver",
  "model": "openai",
  "model_name": "gpt-4o-mini",
  "api_key": "your_api_key_here"
}
  1. Install the necessary Python dependencies:
pip install requests
  1. Test the skill locally to ensure the API connection is active:
python cat_handler.py

OpenClaw Cat Data Schema & Taxonomy

The skill manages its state and configuration through a structured file system to ensure persona persistence across the Openclaw Skills ecosystem:

File Purpose Format
config.json Stores API keys, model selections, and the cat's name. JSON
.cat_cache.json Persists the generated persona traits (breed, age, personality). JSON
cat_prompt.md Defines the system instructions and behavioral constraints for the LLM. Markdown
cat_handler.py The logic layer that processes inputs and communicates with LLM APIs. Python

OpenClaw Cat Advanced Features

  • Persistent Persona: Uses a local cache to ensure your cat's breed and personality remain consistent every time you interact with Openclaw Skills.
  • Multi-LLM Support: Seamlessly switch between OpenAI, Claude, GLM, MiniMax, and Qwen without changing your code.
  • Randomized Attribute Generation: Automatically creates a unique identity for your pet from millions of possible combinations on the first run.
  • Natural Language Triggers: Supports both explicit slash commands and conversational triggers like "Check on my cat."

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*