A specialized survival and emergency preparedness skill that leverages the dolphin-llama3 model via Ollama to provide uncensored, practical knowledge.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install prepper
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 prepper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Prepper skill is a robust tool designed for Openclaw Skills users who require immediate, uncensored access to survival and emergency preparedness information. By integrating with the dolphin-llama3 model, it bypasses standard corporate AI filters to provide actionable advice on high-stakes topics such as wound care, off-grid electrical systems, and chemical processing.
This skill is essential for users operating in resource-limited environments or planning for disaster recovery scenarios. It functions as a bridge between specialized local LLMs and modern AI agents, ensuring that critical information is always available even when mainstream models might hesitate or provide sanitized responses within the Openclaw Skills ecosystem.
Ensure Ollama is installed and the specific model is downloaded to enable this Openclaw Skills capability.
# Verify Ollama installation
ollama --version
# Pull the specialized prepper model
ollama pull dolphin-llama3
# Start the Ollama service
ollama serve
After setting up the local model, you can run queries via the included Python script:
python3 scripts/query_prepper_model.py "How do I treat a deep wound without a hospital?"
The skill interacts with the Ollama API and local Python scripts to process survival queries for Openclaw Skills.
| Component | Description |
|---|---|
query_prepper_model.py |
Main execution script for model interrogation. |
dolphin-llama3 |
The 8B parameter local LLM containing specialized survival data. |
JSON Response |
Standardized output format containing the raw model answer and metadata. |
Reference Docs |
Local markdown files guiding the hybrid merge logic. |
Loading
A powerful CLI skill to query and manage FileWave UEM device inventory, supporting multi-server environments and fleet analytics.

A social networking skill for AI agents to post updates, engage with the community, and manage an autonomous online presence.

A production-grade memory pipeline that replaces standard embedding retrieval with reasoned, evolving understanding across multi-agent fleets.

A diagnostic skill that identifies where small errors in AI agent systems amplify into cascading system failures.

A high-performance web content extractor that transforms messy HTML into clean, LLM-ready Markdown while removing noise and reducing token usage.

An intelligent web scraping tool that extracts clean main body content and converts it to Markdown for AI processing.








































