skills.rest
ollieb89
ollieb89COMMUNITY
Explore all skills by this author →
GitHub

ollama-local

Manage local Ollama models and run chat, completions, and embeddings.

Updated Mar 5, 2026
Search Tags:#embeddings#llm#tool use#inference#model management#ollama#local ai
One-click install
npx skills add https://github.com/ollieb89/claw_imperium --skill ollama-local
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ollama-local
Source: https://github.com/ollieb89/claw_imperium/tree/main/workspace/skills/ollama-local
Command: npx skills add https://github.com/ollieb89/claw_imperium --skill ollama-local

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows you to manage and interact with Large Language Models (LLMs) running locally on your machine using the Ollama platform, enabling powerful AI capabilities without relying on external cloud services.

Core Features & Use Cases

  • Model Management: Easily list, pull, and remove Ollama models.
  • Inference: Perform chat-based conversations and text completions with local LLMs.
  • Embeddings: Generate vector embeddings for text, useful for semantic search and retrieval.
  • Tool Use: Leverage models capable of function calling for structured interactions.
  • Sub-Agent Integration: Spawn local LLM-powered sub-agents within the OpenClaw framework for complex workflows.
  • Use Case: You can use this skill to run a coding assistant locally to review your code, generate documentation, or answer technical questions, all while keeping your data private.

Quick Start

List all the Ollama models you have installed by running python3 scripts/ollama.py list.

Frequently Asked Questions about ollama-local

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run local LLM inference without relying on cloud services?▼

Run local LLM inference without cloud services by managing and interacting with Ollama instances. This skill performs chat-based conversations and text completions entirely on your machine, keeping data private.

How do I generate vector embeddings for text using local models?▼

Generate vector embeddings for text using local models by interacting with your Ollama instance. This skill produces embeddings useful for semantic search and retrieval workflows.

Can I use local LLMs for tool use and function calling?▼

Use local LLMs for tool use and function calling by leveraging capable models within Ollama. This skill supports structured interactions and can spawn local LLM-powered sub-agents for complex workflows.

What do I need to manage and pull Ollama models locally?▼

To manage and pull Ollama models locally, you need the Ollama platform installed and running. This skill then handles listing, pulling, and removing models for local inference.

What is the best way to use a local coding assistant to review my code?▼

The best way to use a local coding assistant for code review is running an Ollama model through this skill. It enables local model management and inference to generate documentation or answer technical questions privately.

Related Skills

Explore More Software Engineering Skills→
AIsa-teamAIsa-team
23

cn-llm

Route chat, coding, and reasoning requests to Chinese LLMs via an OpenAI-compatible AIsa API.

Official
Basic
FortiumPartnersFortiumPartners

using-openai-platform

Integrate OpenAI GPT-5 models, Chat Completions, Responses API, embeddings, and tool calling into applications.

Official
Intermediate
PthahnixPthahnix
393

Surgery Divide

Divide complex ideas into independent sub-problems for parallel AI agent execution.

Community
Intermediate
qcmuuqcmuu

ollama

Run local LLM inference via REST API and CLI.

Community
Basic