Ollama

This gets you working with Ollama's local AI runtime through its REST API and OpenAI-compatible endpoints. You'll want it when you're building chat completions, embeddings, or streaming responses against locally running models like Llama or Gemma. The skill covers both the native API at localhost:11434 and the v1 endpoints that work with OpenAI's Python and JavaScript libraries. It includes real examples for vision models, structured JSON outputs with Pydantic, and cloud model authentication. The reference docs are thorough on environment variables, GPU loading checks with ollama ps, and platform-specific server configuration. Honest take: if you're running models locally instead of hitting external APIs, this covers the practical integration patterns you'll actually use.

skills.sh installs: 234
GitHub stars: 40
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rawveg/skillsforge-marketplace --skill ollama --agent claude-code

Installs into .claude/skills of the current project.

Files

Ollama Skill

Comprehensive assistance with Ollama development - the local AI model runtime for running and interacting with large language models programmatically.

When to Use This Skill

This skill should be triggered when:

Running local AI models with Ollama
Building applications that interact with Ollama's API
Implementing chat completions, embeddings, or streaming responses
Setting up Ollama authentication or cloud models
Configuring Ollama server (environment variables, ports, proxies)
Using Ollama with OpenAI-compatible libraries
Troubleshooting Ollama installations or GPU compatibility
Implementing tool calling, structured outputs, or vision capabilities
Working with Ollama in Docker or behind proxies
Creating, copying, pushing, or managing Ollama models

Quick Reference

1. Basic Chat Completion (cURL)

Generate a simple chat response:

curl http://localhost:11434/api/chat -d '{
  "model": "gemma3",
  "messages": [
    {
      "role": "user",
      "content": "Why is the sky blue?"
    }
  ]
}'