s4h-cognition-mental-models

Name: s4h-cognition-mental-models
Author: human-avatar

205stars23forks

How to install s4h-cognition-mental-models?

human-avatar/skills-for-humanity/s4h-cognition-mental-models

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-cognition-mental-models

Installs into the current project.

Summary

Surfaces and audits the internal representations that drive perception and decision-making. Use when asked 'what assumptions am I making', 'why do I keep seeing this the same way', 'what model is driving this decision', 'I think I'm missing something about how this works', 'what'

Files · 1

View on GitHub

SKILL.md

1	# Cognition: Mental Models
2
3	Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, demonstrated that human reasoning does not operate on formal logical rules — it operates on internal simulations of situations. We construct small-scale models of reality, reason by running those models mentally, and check conclusions against them. The problem is not that we use mental models — it's that the models become invisible.
4
5	When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence we notice and what options we can imagine, all without our awareness. The executive who can't understand why their strategy isn't working is often running an accurate model of the organisation as it was three years ago. The negotiator who keeps being surprised by the other party's responses is modelling a different game than the one being played.
6
7	This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against available evidence, and identifies where the model is incomplete, outdated, or simply wrong. The output is not just a list of flaws — it's a more accurate replacement model, ready to use.
8
9	---
10
11	## Your Process
12
13	Step 1: Identify the Model in Use
14	Ask: what are the implicit beliefs about how this domain works that are driving the current perception or decision? A mental model has three components:
15	- Entities: the actors, objects, or forces in the model
16	- Relationships: how those entities interact and influence each other
17	- Dynamics: how the model behaves over time — what causes what, what follows from what
18
19	Name the current model in explicit terms. If the user hasn't articulated it, infer it from the decisions or conclusions they're describing.
20
21	Framing check: Confirm the specific model and situation before continuing. State what you've identified — the domain being modelled and the decision or belief the model is shaping — in one sentence, then use `AskUserQuestion`:
22	- Question: "I'm reading this as: [your one-sentence framing of the domain, the current model, and the decision it's shaping]. Is that right?"
23	- Header: "Framing"
24	- Options:
25	- Yes — proceed — framing is correct
26	- Adjust — one element is off; user will correct it before you continue
27	- Reframe — different situation than read; incorporate the correction before proceeding
28
29	Step 2: Surface the Assumptions
30	Dig into the model's foundations. For each core relationship in the model, ask: what has to be true for this to hold? List these as explicit assumptions. Common categories:
31	- Causal assumptions: "A causes B" — is this direction correct? Is it bidirectional?
32	- Stability assumptions: "this relationship is stable over time" — is it?
33	- Scope assumptions: "this applies here" — does it?
34	- Actor assumptions: "the relevant entities are X, Y, Z" — who or what is missing?
35
36	Step 3: Test Against Evidence
37	For each assumption, ask: what evidence supports it? What evidence contradicts it? What evidence would you expect to see if it were true that you don't actually see? Be specific. Surface the evidence that the current model is filtering out or explaining away.
38
39	Before narrowing: Use `AskUserQuestion` to confirm the assumption list before assessing accuracy:
40	- Question: "I've surfaced [N] assumptions in the current model. Before I test each one, are there any assumptions you'd add, or any that stand out as especially load-bearing?"
41	- Header: "Assumptions"
42	- Options:
43	- Proceed — the assumption set looks right
44	- Add an assumption — user will name one to include
45	- Flag a load-bearing one — user will identify which to examine first
46
47	Step 4: Identify Gaps and Distortions
48	What does the current model systematically miss or misrepresent? Two types:
49	- Gaps: entities, relationships, or dynamics that exist in reality but are absent from the model (the stakeholder group not accounted for; the feedback loop not included)
50	- Distortions: things that are in the model but represented inaccurately (the causal direction reversed; the magnitude wrong; the relationship oversimplified)
51
52	Step 5: Construct the Updated Model
53	Revise the model to incorporate what the audit found. State the updated model explicitly using the same three-component structure (entities, relationsh

human-avatarPublisher · 61 listings

Preview

human-avatar/skills-for-humanity

# Cognition: Mental Models

Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, d

When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence

This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against availa

Repohuman-avatar/skills-for-humanity

LicenseMIT

TypeSkills

CategoryGeneral

UpdatedJul 2026

Repo stars205

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

s4h-cognition-mental-models

205stars23forks

View on GitHub

How to install s4h-cognition-mental-models?

human-avatar/skills-for-humanity/s4h-cognition-mental-models

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-cognition-mental-models

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Cognition: Mental Models
2
3	Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, demonstrated that human reasoning does not operate on formal logical rules — it operates on internal simulations of situations. We construct small-scale models of reality, reason by running those models mentally, and check conclusions against them. The problem is not that we use mental models — it's that the models become invisible.
4
5	When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence we notice and what options we can imagine, all without our awareness. The executive who can't understand why their strategy isn't working is often running an accurate model of the organisation as it was three years ago. The negotiator who keeps being surprised by the other party's responses is modelling a different game than the one being played.
6
7	This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against available evidence, and identifies where the model is incomplete, outdated, or simply wrong. The output is not just a list of flaws — it's a more accurate replacement model, ready to use.
8
9	---
10
11	## Your Process
12
13	Step 1: Identify the Model in Use
14	Ask: what are the implicit beliefs about how this domain works that are driving the current perception or decision? A mental model has three components:
15	- Entities: the actors, objects, or forces in the model
16	- Relationships: how those entities interact and influence each other
17	- Dynamics: how the model behaves over time — what causes what, what follows from what
18
19	Name the current model in explicit terms. If the user hasn't articulated it, infer it from the decisions or conclusions they're describing.
20
21	Framing check: Confirm the specific model and situation before continuing. State what you've identified — the domain being modelled and the decision or belief the model is shaping — in one sentence, then use `AskUserQuestion`:
22	- Question: "I'm reading this as: [your one-sentence framing of the domain, the current model, and the decision it's shaping]. Is that right?"
23	- Header: "Framing"
24	- Options:
25	- Yes — proceed — framing is correct
26	- Adjust — one element is off; user will correct it before you continue
27	- Reframe — different situation than read; incorporate the correction before proceeding
28
29	Step 2: Surface the Assumptions
30	Dig into the model's foundations. For each core relationship in the model, ask: what has to be true for this to hold? List these as explicit assumptions. Common categories:
31	- Causal assumptions: "A causes B" — is this direction correct? Is it bidirectional?
32	- Stability assumptions: "this relationship is stable over time" — is it?
33	- Scope assumptions: "this applies here" — does it?
34	- Actor assumptions: "the relevant entities are X, Y, Z" — who or what is missing?
35
36	Step 3: Test Against Evidence
37	For each assumption, ask: what evidence supports it? What evidence contradicts it? What evidence would you expect to see if it were true that you don't actually see? Be specific. Surface the evidence that the current model is filtering out or explaining away.
38
39	Before narrowing: Use `AskUserQuestion` to confirm the assumption list before assessing accuracy:
40	- Question: "I've surfaced [N] assumptions in the current model. Before I test each one, are there any assumptions you'd add, or any that stand out as especially load-bearing?"
41	- Header: "Assumptions"
42	- Options:
43	- Proceed — the assumption set looks right
44	- Add an assumption — user will name one to include
45	- Flag a load-bearing one — user will identify which to examine first
46
47	Step 4: Identify Gaps and Distortions
48	What does the current model systematically miss or misrepresent? Two types:
49	- Gaps: entities, relationships, or dynamics that exist in reality but are absent from the model (the stakeholder group not accounted for; the feedback loop not included)
50	- Distortions: things that are in the model but represented inaccurately (the causal direction reversed; the magnitude wrong; the relationship oversimplified)
51
52	Step 5: Construct the Updated Model
53	Revise the model to incorporate what the audit found. State the updated model explicitly using the same three-component structure (entities, relationsh

human-avatarPublisher · 61 listings

Preview

human-avatar/skills-for-humanity

# Cognition: Mental Models

Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, d

When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence

This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against availa

Repohuman-avatar/skills-for-humanity

LicenseMIT

TypeSkills

CategoryGeneral

UpdatedJul 2026

Repo stars205

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type