How do I install the Ollama skill?

Run npx skillmds@latest add buzzmatic/ollama 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 safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ollama?

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 free to use?

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

Who published Ollama?

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

Ollama by buzzmatic — Agent Skill

Name: Ollama
Rating: 4.5 (4 reviews)
Author: Buzzmatic

Ollama

Run and interact with local Ollama LLM models. Use when agents need to run local AI models for text generation, chat completions, embeddings, or model management. Supports listing available models, pulling/downloading new models, generating text completions, chat completions (single and bulk), generating embeddings, and inspecting model details. No API key required - connects to local Ollama instance (default http://localhost:11434). Set OLLAMA_HOST env var to override.

Buzzmatic Updated Sep 22, 2026

File contents

Ollama Local LLM Skill

Interact with locally-running Ollama models via a single unified script.

Prerequisites

Ollama must be running locally. Start with ollama serve or via the Ollama desktop app. Default endpoint: http://localhost:11434. Override with OLLAMA_HOST env var.

Quick Start

All commands use the same script with subcommands:

python skills/ollama/scripts/ollama_api.py [--timeout 300] <command> [options]

Outputs are written to output/ under the current working directory.

Commands

List Models

python skills/ollama/scripts/ollama_api.py list

Pull a Model

python skills/ollama/scripts/ollama_api.py pull --model qwen3:8b
python skills/ollama/scripts/ollama_api.py pull --model llama3.2

Show Model Info

python skills/ollama/scripts/ollama_api.py show --model qwen3:8b

Generate (Text Completion)

python skills/ollama/scripts/ollama_api.py generate \
  --model qwen3:8b \
  --prompt "Explain backlinks in SEO" \
  --system "You are an SEO expert" \
  --temperature 0.7 \
  --num-predict 500

From file:

python skills/ollama/scripts/ollama_api.py generate \
  --model qwen3:8b \
  --prompt-file data/processed/prompt.txt

Chat Completion

python skills/ollama/scripts/ollama_api.py chat \
  --model qwen3:8b \
  --messages '[{"role":"user","content":"What is SEO?"}]' \
  --temperature 0.7

With system message:

python skills/ollama/scripts/ollama_api.py chat \
  --model qwen3:8b \
  --messages '[{"role":"system","content":"You are an SEO expert"},{"role":"user","content":"Explain keyword clustering"}]'

From file:

python skills/ollama/scripts/ollama_api.py chat \
  --model qwen3:8b \
  --messages-file data/processed/conversation.json

With structured JSON output:

python skills/ollama/scripts/ollama_api.py chat \
  --model qwen3:8b \
  --messages '[{"role":"user","content":"List 3 SEO tools"}]' \
  --format json

Bulk Chat (JSONL)

Process multiple requests from a JSONL file:

python skills/ollama/scripts/ollama_api.py chat-bulk \
  --model qwen3:8b \
  --messages-file prompts.jsonl \
  --rate-limit 30

JSONL format:

{"messages":[{"role":"user","content":"Analyze: seo tools"}],"id":"kw_001"}
{"messages":[{"role":"user","content":"Analyze: backlinks"}],"id":"kw_002"}

Embeddings

Requires an embedding model (e.g. nomic-embed-text, mxbai-embed-large). Pull one first:

python skills/ollama/scripts/ollama_api.py pull --model nomic-embed-text

Then generate embeddings:

python skills/ollama/scripts/ollama_api.py embed \
  --model nomic-embed-text \
  --input "What is search engine optimization?"

From file (one text per line):

python skills/ollama/scripts/ollama_api.py embed \
  --model nomic-embed-text \
  --input-file texts.txt

Delete a Model

python skills/ollama/scripts/ollama_api.py delete --model llama3.2

Generation Options

Available for generate, chat, and chat-bulk:

Flag	Description
`--temperature`	Sampling temperature (0-2)
`--top-p`	Nucleus sampling
`--top-k`	Top-k sampling
`--num-predict`	Max tokens to generate
`--num-ctx`	Context window size
`--seed`	Random seed for reproducibility
`--repeat-penalty`	Repetition penalty
`--stop`	Comma-separated stop sequences

Output Format

All commands return JSON to stdout:

{
  "output_files": ["output/ollama_generate_...json"],
  "summary": "Generated 150 tokens in 2.3s with qwen3:8b",
  "response": "First 500 chars of response...",
  "stats": { "model": "qwen3:8b", "eval_count": 150, "total_duration_s": 2.3 }
}

Error Handling

If Ollama is not running, the script exits with code 1 and prints:

{"error": "Cannot connect to Ollama. Is it running? Start with: ollama serve"}

---name: ollamadescription: Run and interact with local Ollama LLM models. Use when agents need to run local AI models for text generation, chat completions, embeddings, or model management. Supports listing available models, pulling/downloading new models, generating text completions, chat completions (single and bulk), generating embeddings, and inspecting model details. No API key required - connects to local Ollama instance (default http://localhost:11434). Set OLLAMA_HOST env var to override.---# Ollama Local LLM SkillInteract with locally-running Ollama models via a single unified script.## PrerequisitesOllama must be running locally. Start with `ollama serve` or via the Ollama desktop app. Default endpoint: `http://localhost:11434`. Override with `OLLAMA_HOST` env var.## Quick StartAll commands use the same script with subcommands:```bashpython skills/ollama/scripts/ollama_api.py [--timeout 300] <command> [options]```Outputs are written to `output/` under the current working directory.## Commands### List Models```bashpython skills/ollama/scripts/ollama_api.py list```### Pull a Model```bashpython skills/ollama/scripts/ollama_api.py pull --model qwen3:8bpython skills/ollama/scripts/ollama_api.py pull --model llama3.2```### Show Model Info```bashpython skills/ollama/scripts/ollama_api.py show --model qwen3:8b```### Generate (Text Completion)```bashpython skills/ollama/scripts/ollama_api.py generate \ --model qwen3:8b \ --prompt "Explain backlinks in SEO" \ --system "You are an SEO expert" \ --temperature 0.7 \ --num-predict 500```From file:```bashpython skills/ollama/scripts/ollama_api.py generate \ --model qwen3:8b \ --prompt-file data/processed/prompt.txt```### Chat Completion```bashpython skills/ollama/scripts/ollama_api.py chat \ --model qwen3:8b \ --messages '[{"role":"user","content":"What is SEO?"}]' \ --temperature 0.7```With system message:```bashpython skills/ollama/scripts/ollama_api.py chat \ --model qwen3:8b \ --messages '[{"role":"system","content":"You are an SEO expert"},{"role":"user","content":"Explain keyword clustering"}]'```From file:```bashpython skills/ollama/scripts/ollama_api.py chat \ --model qwen3:8b \ --messages-file data/processed/conversation.json```With structured JSON output:```bashpython skills/ollama/scripts/ollama_api.py chat \ --model qwen3:8b \ --messages '[{"role":"user","content":"List 3 SEO tools"}]' \ --format json```### Bulk Chat (JSONL)Process multiple requests from a JSONL file:```bashpython skills/ollama/scripts/ollama_api.py chat-bulk \ --model qwen3:8b \ --messages-file prompts.jsonl \ --rate-limit 30```**JSONL format:**```json{"messages":[{"role":"user","content":"Analyze: seo tools"}],"id":"kw_001"}{"messages":[{"role":"user","content":"Analyze: backlinks"}],"id":"kw_002"}```### EmbeddingsRequires an embedding model (e.g. `nomic-embed-text`, `mxbai-embed-large`). Pull one first:```bashpython skills/ollama/scripts/ollama_api.py pull --model nomic-embed-text```Then generate embeddings:```bashpython skills/ollama/scripts/ollama_api.py embed \ --model nomic-embed-text \ --input "What is search engine optimization?"```From file (one text per line):```bashpython skills/ollama/scripts/ollama_api.py embed \ --model nomic-embed-text \ --input-file texts.txt```### Delete a Model```bashpython skills/ollama/scripts/ollama_api.py delete --model llama3.2```## Generation OptionsAvailable for `generate`, `chat`, and `chat-bulk`:| Flag | Description ||------|-------------|| `--temperature` | Sampling temperature (0-2) || `--top-p` | Nucleus sampling || `--top-k` | Top-k sampling || `--num-predict` | Max tokens to generate || `--num-ctx` | Context window size || `--seed` | Random seed for reproducibility || `--repeat-penalty` | Repetition penalty || `--stop` | Comma-separated stop sequences |## Output FormatAll commands return JSON to stdout:```json{ "output_files": ["output/ollama_generate_...json"], "summary": "Generated 150 tokens in 2.3s with qwen3:8b", "response": "First 500 chars of response...", "stats": { "model": "qwen3:8b", "eval_count": 150, "total_duration_s": 2.3 }}```## Error HandlingIf Ollama is not running, the script exits with code 1 and prints:```json{"error": "Cannot connect to Ollama. Is it running? Start with: ollama serve"}```

Frequently asked questions