neuroskill-llm

Run a local llama.cpp server for OpenAI-compatible chat and GGUF model management.

11|4|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/NeuroSkill-com/skills --skill neuroskill-llm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: neuroskill-llm
Source: https://github.com/NeuroSkill-com/skills/tree/main/skills/neuroskill-llm
Command: npx skills add https://github.com/NeuroSkill-com/skills --skill neuroskill-llm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The built-in NeuroSkill LLM server removes dependency on remote APIs by running llama.cpp locally so you can chat, manage models, and execute tools without exposing private data.

Core Features & Use Cases

  • Server Lifecycle Control: Monitor status, start and stop inference, and view logs across CLI, WebSocket, and HTTP interfaces.
  • Model & Vision Management: Catalog, download, select, pause, resume, and delete GGUF models plus mmproj vision projectors with deployment-ready safeguards.
  • Interactive Usage: Stream multi-turn chat, single-shot prompts, automated tool calling, and persistent history while visualizing EEG signals, tool outputs, and hardware status.

Quick Start

Start the llm server, load a model, and ask it to explain EEG frequency bands.

Frequently Asked Questions about neuroskill-llm

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

FAQPage Schema
How do I run a local llama.cpp inference server without external APIs?

You can run a local llama.cpp inference server without external APIs by managing the server lifecycle, loading GGUF models, and accessing OpenAI-compatible chat through CLI, WebSocket, or HTTP endpoints.

Can I manage GGUF models and vision projectors locally?

You can manage GGUF models and vision projectors locally by cataloging, downloading, selecting, pausing, resuming, and deleting them with deployment-ready safeguards.

Does local llama.cpp support streaming chat and automatic tool calling?

Local llama.cpp supports streaming chat and automatic tool calling, allowing you to run multi-turn chat, single-shot prompts, and tune GenParams while maintaining persistent session history.

What is the best way to monitor local LLM server status and hardware usage?

The best way to monitor local LLM server status and hardware usage is by viewing logs and hardware status reporting interfaces during inference to ensure stable operation.

Do I need remote API keys to use OpenAI-compatible chat with local models?

You do not need remote API keys to use OpenAI-compatible chat with local models because the server runs llama.cpp locally to keep data private and execute tools independently.