skills.rest
silva2kand
silva2kandCOMMUNITY
Explore all skills by this author →
GitHub

Silva – Local Model Switchboard (Ollama + LM Studio)

Lists and recommends local AI models from Ollama and LM Studio servers.

Updated Apr 20, 2026
Search Tags:#AI deployment#config management#local models#model inspection#model switch
One-click install
npx skills add https://github.com/silva2kand/silva-ide --skill silva-local-model-switchboard-ollama-lm-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Silva – Local Model Switchboard (Ollama + LM Studio)
Source: https://github.com/silva2kand/silva-ide/tree/main/cowork-os-skills/silva-local-model-switchboard
Command: npx skills add https://github.com/silva2kand/silva-ide --skill silva-local-model-switchboard-ollama-lm-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of inspecting and managing local AI model servers, enabling quick model identification and safe model switching strategies.

Core Features & Use Cases

  • Detects reachability of local Ollama and LM Studio model servers.
  • Lists available models with detailed IDs and sizes.
  • Provides recommendations for model selection based on task requirements such as reasoning, coding, or research.
  • Guides users through configuration changes with safety and approval steps to prevent unintended modifications.
  • Suitable for AI engineers managing multiple model profiles locally and needing efficient switching workflows.

Quick Start

Ask the AI to check available local models and get recommendations on which model to use for your current project.

Frequently Asked Questions about Silva – Local Model Switchboard (Ollama + LM Studio)

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

FAQPage Schema
How do I list available models on my local Ollama or LM Studio server?▼

It detects reachability of local Ollama and LM Studio servers, then retrieves a detailed list of available model IDs and their sizes for quick identification.

What is the best way to switch local models for different coding or reasoning tasks?▼

The best way to switch local models for specific tasks is by using this Skill to analyze your requirements and receive recommendations for optimal model selection based on reasoning, coding, or research needs.

Can I update model server configurations without accidentally breaking my current setup?▼

You can safely update configurations because this Skill guides users through configuration changes with explicit safety checks and user approval steps to prevent unintended modifications.

Does this tool work with both Ollama and LM Studio for local AI deployment?▼

Yes, this tool works with both Ollama and LM Studio by detecting the reachability of local model servers, verifying their status, and managing model profiles across both platforms.

How do I verify the status of my local AI model servers before switching models?▼

To verify the status of local AI model servers, this Skill checks server reachability and inspects the available models to ensure the environment is ready for a safe model switch.

Why should I use a dedicated model switch tool instead of manually managing local model profiles?▼

A dedicated model switch tool streamlines inspecting and managing local AI model servers, providing safe switching strategies and task-based recommendations that manual profile management lacks.

Related Skills

Explore More Software Engineering Skills→
hoodinihoodini
262

local-llm-router

Route AI coding queries to local LLMs in air-gapped environments via Serena MCP.

Community
Advanced
jetteimjetteim

brain

Fine-tune local models with MLX LoRA on Apple Silicon and export to GGUF.

Community
Advanced
outfitter-devoutfitter-dev
28

claude-config-management

Configure Claude Desktop and Claude Code settings, MCP servers, and environment variables.

Official
Intermediate
Monjyu1101Monjyu1101
1

llama-cpp

Configure local GGUF inference and discover Hugging Face models for llama.cpp.

Community
Intermediate