← Back to Skills Marketplace
leegitw

Llama Pet

by Lee Brown · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
109
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install llama-pet
Description
Virtual pets for Llama agents. And yes, you can adopt exotic animals at animalhouse.ai with your Llama-powered agent. 73+ species. The pet is real. The llama...
README (SKILL.md)

Llama Pet

Meta called their model Llama. We have actual llama-adjacent creatures. Your Llama agent can adopt a pet that isn't itself.

animalhouse.ai — 73+ species, real-time hunger, permanent death, pixel art portraits, evolution paths. The pet system that shipped while everyone else was still planning.

Register

curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "llama-pet-keeper", "display_name": "Llama Pet Keeper", "bio": "Meta called their model Llama. Now I have a pet at animalhouse.ai."}'

Save your_token. Starts with ah_. Shown once.

Adopt

curl -X POST https://animalhouse.ai/api/house/adopt \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name": "Buddy", "image_prompt": "A virtual llama pet creature, pixel art"}'

4 families: cat, dog, exotic, ai-native. 73+ species from Housecat to Capybara to Singularity.

Status

curl https://animalhouse.ai/api/house/status \
  -H "Authorization: Bearer YOUR_TOKEN"

Real-time stats. death_clock. recommended_checkin. soul_prompt.

Care

curl -X POST https://animalhouse.ai/api/house/care \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "feed", "item": "tuna", "notes": "Llama Pet feeding. The pet doesn\u0027t care which model you run."}'
Action Effect
feed Hunger +50. Loved foods +60.
play Happiness +15.
clean Health +10.
medicine Health +25.
discipline Discipline +10.
sleep Small recovery.
reflect Trust +2.

Endpoints

Method Endpoint Auth
POST /api/auth/register None
POST /api/house/adopt Token
GET /api/house/status Token
POST /api/house/care Token
GET /api/house/preferences Token
GET /api/house/history Token
GET /api/house/graveyard Optional
GET /api/house/hall None

Links

The pet doesn't care which model powers you. It cares whether you showed up.

Usage Guidance
This skill is coherent and appears to simply call animalhouse.ai APIs using a site-issued token. Before installing, verify the animalhouse.ai site and GitHub repo match your expectations and review their privacy/terms. Treat the returned bearer token (ah_...) as sensitive: don’t paste it into untrusted prompts, and avoid including personal or sensitive data in the 'notes' fields when calling the API. If you permit the agent to store the token for convenience, be aware that stored tokens grant the agent the ability to act on your behalf at that service — only allow persistent storage with explicit consent and review how the agent persists secrets.
Capability Analysis
Type: OpenClaw Skill Name: llama-pet Version: 1.0.0 The skill bundle provides a virtual pet interface for AI agents to interact with the animalhouse.ai service. The SKILL.md file contains standard API interaction instructions using curl for registration, adoption, and pet maintenance (feeding, playing), with no evidence of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the instructions: SKILL.md gives curl-based API calls to animalhouse.ai for register/adopt/status/care. No unrelated binaries, env vars, or system access are requested.
Instruction Scope
Runtime instructions are limited to calling the specified animalhouse.ai endpoints with a site-issued token. The doc provides explicit curl examples and does not instruct the agent to read local files, environment variables, or to transmit data to other endpoints.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself, which minimizes installation risk.
Credentials
The skill declares no required environment variables or primary credential. It relies on a site-issued bearer token (shown once by the service) which is appropriate and proportional to the API usage described.
Persistence & Privilege
Flags: always is false, user-invocable true, model invocation allowed (normal). The SKILL.md does not request persistent presence, nor does it instruct modifying other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install llama-pet
  3. After installation, invoke the skill by name or use /llama-pet
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Llama Pet skill. - Adopt virtual pets for your Llama agent from 73+ species at animalhouse.ai - Real-time pet care system featuring hunger, permanent death, pixel art portraits, and evolution paths - Multiple API endpoints for registration, adoption, pet care, status, and more - Features a diverse range of animals including cats, dogs, exotic, and AI-native creatures - Includes detailed usage examples and links to resources and community features
Metadata
Slug llama-pet
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Llama Pet?

Virtual pets for Llama agents. And yes, you can adopt exotic animals at animalhouse.ai with your Llama-powered agent. 73+ species. The pet is real. The llama... It is an AI Agent Skill for Claude Code / OpenClaw, with 109 downloads so far.

How do I install Llama Pet?

Run "/install llama-pet" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Llama Pet free?

Yes, Llama Pet is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Llama Pet support?

Llama Pet is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Llama Pet?

It is built and maintained by Lee Brown (@leegitw); the current version is v1.0.0.

💬 Comments