multi-model

Coordinate parallel AI model reviews across multiple CLIs and synthesize results.

8|2|Updated Feb 9, 2026

Search Tags:#llm #orchestration #memory #synthesis #council #multimodel #cli-discovery

Ready to run

npx skills add https://github.com/mikeparcewski/wicked-garden --skill multi-model-mikeparcewski

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: multi-model
Source: https://github.com/mikeparcewski/wicked-garden/tree/main/skills/multi-model
Command: npx skills add https://github.com/mikeparcewski/wicked-garden --skill multi-model-mikeparcewski

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Collaborate across multiple AI models to surface diverse perspectives for technical decisions, reducing reliance on a single viewpoint.

Core Features & Use Cases

Cross-model discovery: detect installed CLIs such as codex, copilot, gemini, opencode, pi, aider, llm, aichat, and goose at runtime.
Parallel council & synthesis: dispatch the same scaffold to all available CLIs and synthesize results with model-attribution.
Persistent context: store transcripts and decisions in wicked-brain:memory and jam to enable auditability and iteration.

Quick Start

Invoke a cross-model council: supply a scaffold and let CLIs respond in parallel.

Frequently Asked Questions about multi-model

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

FAQPage Schema

How do I orchestrate multiple AI models to get diverse perspectives for technical decisions?▼

Multi-model orchestration coordinates cross-model AI reviews by dispatching a fixed 4-question scaffold to multiple CLIs in parallel, gathering diverse analyses, and synthesizing the results with model-attribution to reduce reliance on a single viewpoint.

Which AI CLIs can be discovered and orchestrated for a parallel council?▼

Runtime CLI discovery detects installed models including Codex, Copilot, Gemini, Opencode, Pi, Aider, llm, aichat, and Goose, running a quorum check before dispatching the scaffold to the available CLIs for parallel analysis.

How do I run a cross-model council to synthesize parallel AI analyses?▼

To run a cross-model council, supply a scaffold and let the available CLIs respond in parallel. The system dispatches the fixed 4-question scaffold, verifies a quorum, and synthesizes the parallel responses into a single attributed output.

Does multi-model collaboration store transcripts and decisions for auditability?▼

Multi-model collaboration persists context by storing transcripts and decisions in memory-backed storage using wicked-brain:memory and jam, enabling full auditability and iterative refinement of technical decisions over time.

What are the limitations of using a fixed scaffold for cross-model AI reviews?▼

The fixed 4-question scaffold limits the scope of cross-model AI reviews to predefined inquiries, requiring a quorum of detected CLIs to proceed, which restricts ad-hoc questioning and depends on multiple models being installed at runtime.

When should I use a multi-model council instead of a single AI model for technical decisions?▼

Use a multi-model council when technical decisions require diverse perspectives to avoid single-viewpoint bias, applying parallel dispatch across multiple CLIs to surface contrasting analyses and synthesize a comprehensive, model-attributed conclusion.