Do I need three different API providers to use this?

Not necessarily. You can use a mix of local models and cloud APIs, or even the same provider for multiple surgeons, though using different models is recommended for better cross-examination.

How does setup-team detect local models?

The skill runs a detection command that scans standard ports and services for common local providers like Ollama, LM Studio, and MLX to identify active models.

Can I run 3-Surgeons entirely for free?

Yes. The setup-team skill can help you configure a fully local environment using tools like Ollama or LM Studio, resulting in zero API costs.

Are my API keys stored in the config file?

No. Following security best practices, the skill guides you to set environment variables. The configuration file only references the variable name, never the key itself.

What happens if a surgeon goes offline?

The skill includes a verification flow using the '3s probe' command to help you identify which model is failing and provides steps to reconfigure the connection.

3-Surgeons Team Setup

Name: 3-Surgeons Team Setup
Author: supportersimulator

bysupportersimulator

0•

Data Science & ML

Configures and verifies the 3-Surgeons multi-model consensus system by detecting local backends and managing API providers.

The 3-Surgeons Team Setup skill (setup-team) provides a seamless onboarding experience for assembling a three-LLM cross-examination environment. It intelligently detects running local inference servers like Ollama or LM Studio, guides users through secure API key configuration for cloud providers, and verifies connectivity across the entire team of 'surgeons.' By prioritizing security and ease of use, it ensures that your consensus system is correctly calibrated for high-stakes decision-making without ever storing sensitive credentials in plaintext configuration files.

Key Features

01Automatic detection of local LLM backends (Ollama, MLX, LM Studio, vLLM)

02Flexible configuration paths for local-only, cloud-only, or hybrid setups

03Interactive connectivity probing to verify surgeon responsiveness

040 GitHub stars

05Multi-provider support including OpenAI, Anthropic, DeepSeek, and Groq

06Secure API key handling via environment variables to prevent credential leakage

Use Cases

01Migrating from local inference to cloud-based LLM providers for increased reasoning power

02Diagnosing and repairing broken connections between different model backends

03Initial onboarding and configuration of the 3-Surgeons multi-model framework

Key Features

01Automatic detection of local LLM backends (Ollama, MLX, LM Studio, vLLM)

02Flexible configuration paths for local-only, cloud-only, or hybrid setups

03Interactive connectivity probing to verify surgeon responsiveness

040 GitHub stars

05Multi-provider support including OpenAI, Anthropic, DeepSeek, and Groq

06Secure API key handling via environment variables to prevent credential leakage

Use Cases

01Migrating from local inference to cloud-based LLM providers for increased reasoning power

02Diagnosing and repairing broken connections between different model backends

03Initial onboarding and configuration of the 3-Surgeons multi-model framework