Meta Mental Models

What it does

When your agent uses it

• The user needs to think more clearly
• Avoid cognitive blind spots
• Apply cross-disciplinary reasoning
• Evaluate a complex decision from multiple angles — even if they say how should I think about this

Example prompts

• “how should I think about this”
• “what am I missing”
• “give me a different perspective”
• “/meta-mental-models”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1State the decision or problem
2. 2Select 2-3 relevant models from different disciplines
3. 3Apply each model to the situation — what does it suggest?
4. 4Compare conclusions — where do they agree? Where do they disagree?
5. 5Synthesize — the disagreement reveals the key trade-off to resolve

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Meta Mental Models loads about 1.2k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 392 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~107

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~7.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 392 words, ~1,169 tokens.

name

meta-mental-models

description

Apply a latticework of mental models from multiple disciplines to improve decision quality. Use this skill when the user needs to think more clearly, avoid cognitive blind spots, apply cross-disciplinary reasoning, or evaluate a complex decision from multiple angles — even if they say 'how should I think about this', 'what am I missing', 'give me a different perspective', or 'what frameworks apply here'.

metadata.category

WP-22 跨學科

metadata.tags

meta-thinking, mental-models, munger, decision-making

IRON LAW: Use Multiple Models, Not Just Your Favorite

"To a man with a hammer, everything looks like a nail." (Munger)
A single mental model creates blind spots. Apply 2-3 models from
DIFFERENT disciplines to any important decision. Where models agree,
confidence is high. Where they disagree, the disagreement reveals
the most important dimension of the decision.

# Multi-Model Analysis: {Decision}

## Models Applied
| Model | Discipline | Insight |
|-------|-----------|---------|
| {model 1} | {field} | {what this model says about the situation} |
| {model 2} | {field} | {what this model says} |
| {model 3} | {field} | {what this model says} |

## Convergence
{Where models agree — high confidence}

## Divergence
{Where models disagree — key trade-off to resolve}

## Synthesis
{Recommended decision based on multi-model analysis}

© asgard-ai-platform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in meta-mental-models of asgard-ai-platform/skills.

• SKILL.md
• examples/sample_scenario.md
• references/mental-models-catalog.md

Open the folder on GitHubat commit 4e7f4f8