“Ollama”

Use this skill when running, managing, or interacting with LLM models via `ollama` — locally or on a remote machine.

Claude Code 安裝本地 AI Ollama。說「安裝 Ollama」「本地 AI」時載入。

Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

Codex 安裝本地 AI Ollama。說「安裝 Ollama」「本地 AI」時載入。

Use Ollama Cloud web APIs for single-query web search and single-page web fetch.

Synchronizes the list of available models in the 'opencode.json' configuration file's 'ollama' provider models list with the actual models available on the…

Use to launch, talk to, check, or clean up local Ollama models.

Make quick local decisions with Ollama System One (yes/no, choice, or score).

Post a messages to Ollama and send the result via mail

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

Call your local Ollama or vLLM model over MCP with schema-validated JSON output

Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

Stop Ollama model reload churn caused by callers sending different num_ctx values.

Install and configure Ollama for local embeddings with GrepAI.

Queue manager skill for serializing local Ollama agent invocations from other skills; enqueues requests, runs one-at-a-time with queue.lock, writes callback…

Configure Ollama as embedding provider for GrepAI.

On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.

Review and rewrite LangChain, LlamaIndex, Ollama, and XRPL code against current APIs.

Free Ollama hardening checker, plus tools for privacy architecture and the Data Dignity Standard.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Intraday stock recommendations using Ollama web search, local LLM ranking, and Dhan live quotes.

Keep vLLM and Ollama from fighting over one GPU.

Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…

Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.