<div align="center"> <br>

s4h · skills-for-humanity

The methods layer for AI reasoning.

    

<br> </div>

  knowledge   ·   what it knows    ·   training
  tools       ·   what it can do   ·   MCP · APIs
  methods     ·   how it thinks    ·   s4h        ◄── the missing layer

Models gave AI knowledge. MCP gave it tools. s4h adds the missing layer — methods: history's most rigorous thinking, rebuilt as procedures Claude runs.

---

Prompt vs. method

| Ask a raw model | Run the method | |---|---| | "Should I leave my stable role for the startup?" | /s4h-decision-reversibility-analysis | | One balanced-sounding pass, shaped entirely by how you framed it. | Classifies the decision by reversibility → finds the closing window → applies the rigor that class warrants. |

Same model. A different quality of thought.

---

The library

5 clusters · 34 domains · 200+ methods

| | | |---|---| | Think Sharper | /logic /probability /decision /constraint /game-theory /epistemology /investigation /economics /information /cognition | | Think Differently | /creativity /analogy /play /evolution /design | | Think About People | /communication /social /emotional /ethics /identity /narrative /psychology /mindset /writing /linguistics | | Think in Time & Systems | /systems /temporal /historical /resource /strategy /network /ecology | | See More Clearly | /aesthetic /sensory |

_{Commands are prefixed s4h- — e.g. /s4h-decision. Each domain routes to 4–20 individual methods.}

---

Why a methods layer matters

• Repeatable — the same rigor on any problem, not whatever got improvised.
• Inspectable — you see the moves, not a black box.
• Composable — methods chain: a decision feeds a premortem feeds an incentive map.
• Democratized — the toolkit of history's finest thinkers, on demand.

---

Install & use

npx @human-avatar/skills-for-humanity

/s4h

Describe your situation — it routes to the method. You never need to know which one. Every skill states its read and asks how deep to go before it runs; correct the framing anytime.

_{Lineage · de Bono · Meadows · Altshuller · Minto · Goldratt · Tetlock · Klein · Mill · Kant · Aristotle · Noddings · Rawls · Sun Tzu · Clausewitz · Musashi · Nash · Axelrod · Vickrey · Shapley · Spence · Marshall · Coase · Ostrom · Granovetter · Barabási · Shannon · Norman · Lakoff · Grice · Kahneman · Tansley · Dawkins}

---

<details> <summary><strong>See it think</strong> — worked examples</summary> <br>

Why social media makes discourse worse despite everyone wanting better

Platforms want healthier discourse. Users say they want it. It keeps getting worse. /s4h-systems-feedback-mapping finds the reinforcing loop: engagement-optimised feeds reward content that provokes reaction, which selects for users who engage with provocation, which trains the algorithm to serve more of it. The stated goal and the actual incentive structure point in opposite directions. No individual decision made it this way — the system produced it.

The ethics and game theory of automating 40 jobs

Your company is considering automating a function that currently employs 40 people. /s4h-ethics-council runs five frameworks and surfaces a genuine conflict: utilitarian logic favours the automation, Kantian reasoning flags that treating displaced workers as means rather than ends requires more than an efficiency argument. /s4h-game-theory-mechanism-design then helps design a transition that aligns incentives — rather than announcing a decision and managing the fallout.

Why a new pricing model keeps failing despite making economic sense

The economics look clear: the new pricing model captures more value, aligns incentives, and is objectively fairer. It keeps getting rejected. /s4h-economics-incentive-mapping finds the problem: the people who must approve it face short-term losses even though the organisation wins long-term. /s4h-economics-coordination then diagnoses the collective action failure — each approver is waiting for someone else to absorb the transition cost first.

Why a product keeps winning technically and losing commercially

Engineers ship a product that outperforms competitors on every measurable dimension. It keeps underperforming in the market. /s4h-design-user-needs finds the gap: the features being optimised are the ones engineers care about, not the ones that determine adoption decisions. /s4h-cognition-mental-models then surfaces the mental model users bring to the product — and shows the product is being built against a different model than the one users actually hold.

Why a platform grows explosively then stalls at the same threshold

A consumer app hit 100,000 users fast, then plateaued. Growth tactics aren't working. /s4h-network-effects diagnoses the type of network effect at play — local, not global — which means the platform reaches saturation within clusters long before it reaches market saturation. /s4h-network-weak-ties then identifies the bridge connections that could carry growth across cluster boundaries.

What a startup's fundraising pitch is actually communicating

A founder's pitch deck is clear and well-structured. Investors keep passing without giving substantive reasons. /s4h-linguistics-framing finds the issue: the deck frames the company as solving a problem investors already think is solved, which pre-loads skepticism before a single number is scrutinised. The facts haven't changed — the frame has been working against the argument the whole time.

The political landscape through game theory

The current political climate feels like everyone is acting against their own interests. /s4h-game-theory-iterated maps the repeated-game structure: parties face short-term defection incentives even when cooperation would benefit everyone long-run, and a shrinking shadow of the future (declining expected gains from future cooperation) explains why moderation keeps losing even when most people say they want it. The equilibrium is stable — not because of irrationality, but because of it.

Whether the current wave of nationalism is unprecedented

The political nationalism of the 2020s feels like something new. /s4h-historical-cycle-detection finds four structural analogues — late-19th-century nativist movements, 1930s economic retrenchment, post-colonial identity politics, 1970s stagflation politics — and maps where the current situation matches the pattern and where it doesn't. More useful than "this has happened before" or "this time is different."

A career pivot with a closing window

You're considering leaving a stable senior role for an early-stage company. The question feels like yes or no. /s4h-strategy-positioning maps how your options change if you wait two years versus going now. /s4h-decision-reversibility-analysis finds the move is partially reversible in the medium term — but with a specific window that closes as you get further from hands-on execution. The pairing surfaces a time constraint neither skill would have found alone.

Whether a dominant tech company's position is actually durable

The company looks unassailable: massive market share, capital, talent. /s4h-ecology-keystone-species maps the dependencies — which other players rely on it and which the platform itself relies on — and finds two suppliers with quietly disproportionate leverage. /s4h-ecology-succession then models what the ecosystem looks like in the next developmental stage, and whether the current dominant player is positioned for it or optimised for conditions that are already passing.

How a species analogy reveals the flaw in a market entry strategy

A company plans to enter a mature market by doing what the market leader does, but cheaper. /s4h-evolution-fitness-landscape maps the landscape: the incumbent occupies a local optimum that is genuinely hard to displace incrementally — competing on the same dimensions means fighting on the incumbent's terms. The analysis points toward a different peak entirely: a niche the incumbent has structurally abandoned.

The hidden cost in every information-rich environment

A team drowns in data but keeps making the same avoidable mistakes. /s4h-information-signal-noise finds that the most decision-relevant signals are buried in low-frequency, low-urgency reports that nobody reads — while high-frequency, high-urgency signals (email, Slack, dashboards) carry almost no information about the actual problem. The team isn't uninformed; it's overloaded with noise while the signal sits unread.

</details> <details> <summary><strong>Where to reach for what</strong></summary> <br>

Decisions — /s4h-decision for structure, /s4h-decision-premortem-analysis to stress-test before committing, /s4h-constraint-hardness-testing to separate real obstacles from assumed ones.

Complex situations — /s4h-systems to map why something keeps producing the same outcome, /s4h-game-theory for the incentive structure underneath, /s4h-historical for the pattern it's an instance of.

Creative work — /s4h-creativity-brainstorm for multi-method exploration, /s4h-constraint-rule-inversion to make limits generative, /s4h-aesthetic-elegance-testing to find what's unnecessary.

Communication — /s4h-communication-objection-mapping to anticipate resistance, /s4h-narrative-tension-mapping to find what earns attention, `/s4h-w