thinking-model-combination
Agent skill fromtjboudreaux/cc-thinking-skills
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.
How to install thinking-model-combination
install thinking-model-combination
# install the cc-thinking-skills pack with the skills CLI
npx skills add tjboudreaux/cc-thinking-skills# or add only this skill to Claude Code: copy the folder
skills/thinking-model-combination/
# into
~/.claude/skills/thinking-model-combination/ (all projects)
.claude/skills/thinking-model-combination/ (one project)
1# Model Combination23**Core rule:** Combine only when each model answers a different named question. Cap at three, name the conflict rule before applying, then synthesize once.45## When to Use67- One model already applied (or clearly primary) still leaves a material blind spot that another mechanism covers.8- Problem spans domains (e.g. risk + choice + system structure) and stakes justify multi-lens work.9- You need independent checks, not confirmation of the same conclusion.10- You can name a distinct role per model before running them.1112## When NOT to Use1314- A single catalog skill fully answers the unknown — apply that skill alone.15- Routine, local, or fully reversible work where multi-lens cost exceeds upside.16- You cannot state what unique question each extra model answers (checkbox / model soup).17- Near-duplicate mechanisms (two diagnosis skills that ask the same causal question).18- Time budget cannot support genuine synthesis — prefer one honest model over contradictory partials.1920## Procedure21221. **State the unknown and the gap.** Write the decision question. If one model already covers it, stop and use that model alone. Otherwise name the specific blind spot (e.g. "failure modes unexamined", "displaced alternative unknown").23…
Excerpt shown under the repository's MIT license.
