# Thinking Model Combination

When one mental model leaves a material blind spot on a multi-domain or high-stakes...

- Repository: https://github.com/tjboudreaux/cc-thinking-skills (1690 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-08-07
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-model-combination -g -a claude-code -y`
Codex: `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-model-combination -g -a codex -y`
Cursor: `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-model-combination -g -a cursor -y`
Gemini CLI: `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-model-combination -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add tjboudreaux/cc-thinking-skills`

## Description

When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Model Combination

**Core rule:** Combine only when each model answers a different named question. Cap at three, name the conflict rule before applying, then synthesize once.

## When to Use

- One model already applied (or clearly primary) still leaves a material blind spot that another mechanism covers.
- Problem spans domains (e.g. risk + choice + system structure) and stakes justify multi-lens work.
- You need independent checks, not confirmation of the same conclusion.
- You can name a distinct role per model before running them.

## When NOT to Use

- A single catalog skill fully answers the unknown, apply that skill alone.
- Routine, local, or fully reversible work where multi-lens cost exceeds upside.
- You cannot state what unique question each extra model answers (checkbox / model soup).
- Near-duplicate mechanisms (two diagnosis skills that ask the same causal question).
- Time budget cannot support genuine synthesis, prefer one honest model over contradictory partials.

## Procedure

The rest: https://github.com/tjboudreaux/cc-thinking-skills/blob/HEAD/skills/thinking-model-combination/SKILL.md