Ollama Model Management
Use this skill when the user asks to pull new models, list active models, or check the status of the Ollama engine inside the container.
Install
$ agentstack add skill-dor-rondel-agent-skills-ollama-model-management ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Ollama Model Management
This skill handles interaction with the Ollama service to update, add, or audit local LLM and embedding models.
🛠️ Service Target
- Host Address: http://127.0.0.1:11435
- Default Preloaded Models:
llama3,nomic-embed-text
🏃♂️ Core Commands
1. List Installed Models
Query the active Ollama engine inside the container to see what weights are already loaded on disk:
docker exec -it ollama ollama list2. Download / Pull a New Model
Instruct the containerized daemon to pull down a new model directly from the Ollama registry:
docker exec -it ollama ollama pull 3. Check Service Logs
If a model fails to load or download, inspect the execution logs directly from the active service:
docker-compose logs ollamaSource & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dor-rondel
- Source: dor-rondel/agent-skills-mcp
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.