How do I install the Ollama Deploy skill?

Run npx skillmds@latest add ryanmaclean/ollama-deploy in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ollama Deploy safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ollama Deploy?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ollama Deploy free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ollama Deploy?

ryanmaclean (@ryanmaclean) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ollama Deploy by ryanmaclean — Agent Skill

Name: Ollama Deploy
Author: ryanmaclean

File contents

Ollama Deployment Skill

Overview

Use this skill for deploying and managing Ollama (local LLM runtime) on fleet hosts.

Tools Required

Bash - Run ollama commands, systemctl
SSH - Connect to hosts for direct access
WebFetch - Download Ollama binaries, check releases
Glob/Grep - Find existing Ollama installations
Read - Check configs, model availability
Write/Edit - Create systemd units, configs

Key Principles

1. Architecture Matters

Raspberry Pis: use ollama-linux-arm64.tgz
x86_64 hosts: use ollama-linux-amd64.tgz
Verify with: file /usr/local/bin/ollama

2. Staged Downloads for Large Files

Ollama binary is ~1.6GB. Download once locally, then distribute:

# Download to controller
curl -fsSL https://github.com/ollama/ollama/releases/download/v0.13.1/ollama-linux-arm64.tgz -o /tmp/ollama.tgz

# Distribute via Ansible copy (parallel, fast LAN)
ansible <hosts> -i inventory -b -m copy -a "src=/tmp/ollama.tgz dest=/tmp/ollama.tgz"

# Extract on hosts
ansible <hosts> -i inventory -b -m shell -a "tar -xzf /tmp/ollama.tgz -C /usr/local"

3. Models Need Separate Pull

After installing Ollama binary, pull models:

ansible <hosts> -i inventory -b -m shell -a "/usr/local/bin/ollama pull kimi-k2.5:cloud"

4. Use Systemd for Service Management

ansible <hosts> -i inventory -b -m systemd -a "name=ollama state=started enabled=yes"

Common Playbooks

Install Ollama

ansible-playbook -i inventory 02-ollama.yml

Check Status

ansible <hosts> -i inventory -m shell -a "/usr/local/bin/ollama list"
ansible <hosts> -i inventory -m systemd -a "name=ollama state=started"

Known Issues

Wrong Architecture

Problem: juju4.ollama role downloads AMD64 by default
Fix: Manually specify ARM64 URL in playbook

Model Download Fails

Problem: Permission errors when running ollama pull as _ollama user
Fix: Run ollama pull as ubuntu user or directly without become_user

Service Not Starting

Check: journalctl -u ollama -n 50
Verify binary: file /usr/local/bin/ollama

Reference Files

$HOME/rust-town/irclaw/ansible/02-ollama.yml

Usage

Audit first: Check if Ollama already installed
Stage download: Get binary once, distribute
Extract & start: Use systemd
Pull models: Pull required models (kimi-k2.5:cloud)

---name: ollama-deploydescription: Deploy and manage Ollama LLM on fleet hosts. Use when user mentions ollama, LLM, AI model, or language model deployment.---# Ollama Deployment Skill## OverviewUse this skill for deploying and managing Ollama (local LLM runtime) on fleet hosts.## Tools Required- **Bash** - Run ollama commands, systemctl- **SSH** - Connect to hosts for direct access- **WebFetch** - Download Ollama binaries, check releases- **Glob/Grep** - Find existing Ollama installations- **Read** - Check configs, model availability- **Write/Edit** - Create systemd units, configs## Key Principles### 1. Architecture Matters- Raspberry Pis: use `ollama-linux-arm64.tgz`- x86_64 hosts: use `ollama-linux-amd64.tgz`- Verify with: `file /usr/local/bin/ollama`### 2. Staged Downloads for Large FilesOllama binary is ~1.6GB. Download once locally, then distribute:```bash# Download to controllercurl -fsSL https://github.com/ollama/ollama/releases/download/v0.13.1/ollama-linux-arm64.tgz -o /tmp/ollama.tgz# Distribute via Ansible copy (parallel, fast LAN)ansible <hosts> -i inventory -b -m copy -a "src=/tmp/ollama.tgz dest=/tmp/ollama.tgz"# Extract on hostsansible <hosts> -i inventory -b -m shell -a "tar -xzf /tmp/ollama.tgz -C /usr/local"```### 3. Models Need Separate PullAfter installing Ollama binary, pull models:```bashansible <hosts> -i inventory -b -m shell -a "/usr/local/bin/ollama pull kimi-k2.5:cloud"```### 4. Use Systemd for Service Management```bashansible <hosts> -i inventory -b -m systemd -a "name=ollama state=started enabled=yes"```## Common Playbooks### Install Ollama```bashansible-playbook -i inventory 02-ollama.yml```### Check Status```bashansible <hosts> -i inventory -m shell -a "/usr/local/bin/ollama list"ansible <hosts> -i inventory -m systemd -a "name=ollama state=started"```## Known Issues### Wrong Architecture- **Problem**: juju4.ollama role downloads AMD64 by default- **Fix**: Manually specify ARM64 URL in playbook### Model Download Fails- **Problem**: Permission errors when running `ollama pull` as _ollama user- **Fix**: Run `ollama pull` as ubuntu user or directly without become_user### Service Not Starting- **Check**: `journalctl -u ollama -n 50`- **Verify binary**: `file /usr/local/bin/ollama`## Reference Files```$HOME/rust-town/irclaw/ansible/02-ollama.yml```## Usage1. **Audit first**: Check if Ollama already installed2. **Stage download**: Get binary once, distribute3. **Extract & start**: Use systemd4. **Pull models**: Pull required models (kimi-k2.5:cloud)

Frequently asked questions

Ollama Deploy