Mental Models
Applies Charlie Munger's 98-model latticework to decisions, with a CLI or offline file fallback.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · a6664dd
Ran the file-fallback path on a real 'team keeps missing deadlines despite overtime' problem: it surfaced a reinforcing burnout feedback loop and an incentive-bias check that my unaided baseline answer never named, then ended with concrete next steps instead of theory.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Mental Models does
Selects 2-3 relevant mental models (bottlenecks, feedback loops, incentive bias, etc.) for a user's problem and walks their thinking_steps verbatim to structure an analysis. Triggers on decision-analysis requests, 'help me think', named models (inversion, bottlenecks), or requests for a structured reasoning framework. Prefers a companion CLI but ships all 98 model files plus REFERENCE.md/PATTERNS.md so it works fully offline.
How to install Mental Models
git clone https://github.com/cyperx84/claude-skills-mental-models
mkdir -p ~/.claude/skills
cp -r claude-skills-mental-models/.claude/skills/mental-models ~/.claude/skills/mental-models
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Mental Models
-
/mental-modelsApplies Charlie Munger's 98-model latticework to decisions, with a CLI or offline file fallback.
It also activates on plain-language prompts like these:
-
Help me think through why my team keeps missing deadlines -
Use Charlie Munger's latticework of frameworks on this hiring call -
Use inversion to figure out what could kill this product launch
Frequently asked questions
- Is the Mental Models skill free?
- Yes. The skill itself is free from cyperx84/claude-skills-mental-models. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Mental Models work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran the file-fallback path on a real 'team keeps missing deadlines despite overtime' problem: it surfaced a reinforcing burnout feedback loop and an incentive-bias check that my unaided baseline answer never named, then ended with concrete next steps instead of theory.
- What is the Mental Models SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Mental Models?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Mental Models with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.