Mental Model Evaluator
SkillAI & modelsApplies multi-disciplinary cognitive frameworks (e.g., Inversion, First Principles, Second-Order Thinking) to user plans and system designs to stress-test decisions.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Mental Model Evaluator skill
What this skill tells your AI
The instructions your AI receives, as published by mphinance/alpha-skills in skills/mental-model-evaluator/SKILL.md and read by ahel’s review.
"Measure twice, cut once."
Before making major architectural decisions, writing a massive feature, or executing a high-stakes trade plan, this skill forces a pause and runs the proposed plan through established cognitive mental models.
Core Mental Models
- Inversion: "How could this plan completely fail?" Works backwards to identify guaranteed failure states and ensures the plan mitigates them.
- First Principles Thinking: Strips the plan down to fundamental truths. Are we building on an assumption, or an undeniable fact?
- Second-Order Effects: "And then what?" Evaluates the downstream consequences of the decision beyond the immediate payoff.
- Buffett's Moat Analysis: Does this feature/trade provide a sustainable, defensible advantage, or is it easily replicated noise?
Usage
When activated (Trigger phrases: "Evaluate this model", "Run the mental models", "Stress test this idea"):
- Read the user's proposed plan or idea.
- Output a structured markdown report that addresses the plan through the lens of at least 3 of the mental models above.
- Conclude with a final
PASS,REVISE, orREJECTverdict.
Signals
- GitHub stars
- 27
- Forks
- 5
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
mental-model-evaluator- Source
- github.com/mphinance/alpha-skills