Open-source thinking-framework skills that make rigorous reasoning executable for AI agents.
163 composable mental models — packaged as installable Agent Skills. Each turns a reasoning method that usually lives in a book into a step-by-step process an AI agent can actually run, with worked historical examples and cited sources.
Add all 163 skills:
npx skills add deciqAI/knowledge-skillsList what's inside, or grab a single skill:
npx skills add deciqAI/knowledge-skills --list
npx skills add deciqAI/knowledge-skills --skill first-principlesEach folder is also a self-contained SKILL.md with examples/ and references/ — copy it into your agent's skills directory directly if you prefer.
| Skill | Live | What it does ||---|---|---|| 10 10 10 | ↗ | Faced with a non-trivial decision, ask three questions: How will I feel in 10 minutes? In 10 months? In 10 years? The three horizons are spaced an order of magnitude apart to surfa | | Aarrr Pirate Metrics | ↗ | A startup's growth is a sequential funnel — each stage gates the next. | | Abductive Reasoning | ↗ | Abduction — inference to the best explanation — is the only mode of reasoning that introduces new ideas. | | Anchoring | ↗ | When people estimate an unknown quantity they start from a reference point — an anchor — and adjust. | | Ansoff Matrix | ↗ | Every growth option a firm has falls into one of four quadrants defined by two axes: existing vs. | | Antifragile | ↗ | Nassim Nicholas Taleb (2012) identified a third response to stress beyond fragile/robust: antifragile — systems that gain from disorder, with bounded downside and unbounded upside. | | Authority Bias | ↗ | Authority bias is the automatic tendency to comply with directives from authority figures — often overriding one's own judgment, ethics, or evidence. | | Availability Heuristic | ↗ | The availability heuristic: people estimate probability by how easily examples come to mind. | | Batna Zopa | ↗ | BATNA (Best Alternative to a Negotiated Agreement) is the value of your best fallback if no deal happens — the floor below which you walk away. | | Bayesian Reasoning | ↗ | Bayes' theorem: Posterior odds = Prior odds × Likelihood ratio. | | Bcg Matrix | ↗ | Maps each business unit on a 2×2 grid of market growth rate vs. | | Black Swan | ↗ | Taleb (2007): a black swan is (1) outside all prior expectations, (2) extreme impact, (3) obvious in hindsight only. | | Blue Ocean Strategy | ↗ | Most competitive strategy assumes industry boundaries are fixed. | | Business Model Canvas | ↗ | A business creates, delivers, and captures value through nine interlocking blocks (Customer Segments, Value Propositions, Channels, Customer Relationships, Revenue Streams, Key Res | | Change And Constants | ↗ | Every strategy contains elements that must change and elements that must not. | | Checklist | ↗ | A checklist is a short written list of must-not-skip steps for a complex repeated operation. | | Chestertons Fence | ↗ | Before removing a rule, process, code path, or institution — you must understand why it was put there. | | Circle Of Competence | ↗ | Every decision-maker has a domain where judgments are reliable (inside the circle) and one where they are not (outside). | | Cognitive Evolution Stages | ↗ | Most learning models treat acquisition as the final destination. | | Cognitive Load Theory | ↗ | Working memory holds ~4 chunks of novel information — a hard limit. | | Cognitive Science Landscape | ↗ | Eight interconnected domains constitute human cognition: (1) Perception & Attention, (2) Memory, (3) Language & Thought, (4) Decision Making & Judgment, (5) Metacognition, (6) Emot | | Commitment Consistency | ↗ | Small commitments today dramatically raise the probability of large commitments tomorrow — people have a strong drive to behave consistently with prior choices, especially ones tha | | Comparative Advantage | ↗ | Mutually beneficial specialization depends on relative productivity, not absolute. | | Compound Interest | ↗ | Compound interest: a quantity grows at a rate proportional to its current size — growth itself grows — producing exponential accumulation. | | Confirmation Bias | ↗ | Confirmation bias is the systematic tendency to seek, interpret, remember, and weight evidence in ways that support existing beliefs — and to correspondingly miss disconfirming evi | | Critical Thinking | ↗ | Critical thinking evaluates a conclusion by explicitly testing it against alternative interpretations — the conclusion that survives the most disconfirmation attempts is the one to | | Cross Disciplinary Creativity | ↗ | Importing an actual mechanism from a foreign domain and applying it structurally to a home-domain problem — producing a configuration no expert in either field could conceive alone | | Curiosity Learning Curve | ↗ | Biological learning capacity remains measurable into the 70s and 80s. | | Customer Relationship Ladder | ↗ | Most B2B teams treat relationship deepening as an attitude problem — be friendlier, schedule more QBRs. | | Cynefin | ↗ | Cynefin (pronounced "kuh-NEV-in"; Welsh for "habitat") is a sense-making framework by Dave Snowden (IBM, 1999). | | Death Spiral | ↗ | A death spiral is a self-reinforcing negative feedback loop in competitive markets. | | Decision Tree | ↗ | A decision tree maps a multi-stage decision: decision nodes (squares) for choices you control, chance nodes (circles) for outcomes you don't, probabilities on every branch, payoffs | | Deep Work | ↗ | Cal Newport's framework (2016): deep work = undistracted, cognitively demanding activity that creates hard-to-replicate value; shallow work = logistical, responsive, easy-to-replic | | Deliberate Practice | ↗ | Most people confuse repetition with learning — they accumulate years of experience and plateau. | | Demand Leadership | ↗ | The highest-value market position is not to fulfill demand but to define it — to become the entity whose framing of the problem the customer adopts as their own. | | Design Thinking | ↗ | Design thinking — formalized by Tim Brown at IDEO and Stanford's d.school, grounded in Simon (1969) and Rittel's "wicked problems" — replaces assumption-driven decisions with evide | | Dichotomy Of Control | ↗ | Separate what is within your power (judgments, intentions, voluntary actions) from what is not (outcomes, others' actions, external events) — then direct effort to the first and ac | | Disruptive Innovation | ↗ | Most incumbents fail not because they make bad decisions, but because they make good ones. | | Door In The Face | ↗ | Ask for something large (expect refusal), then retreat to the smaller request you actually wanted. | | Dual System Thinking | ↗ | Two parallel modes: System 1 — fast, automatic, effortless (pattern recognition, gut feel). | | Dunbars Number | ↗ | Dunbar's number (~150) is the cognitive limit on stable social groups the human neocortex can sustain, with nested layers at ~5, ~15, ~50, then outer bands at ~500 and ~1,500. | | Dunning Kruger | ↗ | The Dunning-Kruger effect is the systematic self-assessment asymmetry demonstrated by Kruger & Dunning (1999): bottom-quartile performers overestimate rank by ~50 percentile points | | Dynamic Core Competence | ↗ | Core competence (Prahalad & Hamel, 1990) becomes dynamic when you recognize that competences decay, markets change what they reward, and building sequence matters. | | Economic Moat | ↗ | An economic moat is the durable, structural competitive advantage that protects a business's returns on capital from being competed away. | | Economies Of Scale | ↗ | Average cost per unit falls as output rises — fixed costs spread thinner, specialization deepens, and learning compounds. | | Emergence | ↗ | Emergence: many interacting parts produce whole-level properties that cannot be predicted from the parts alone. | | Endowment Effect | ↗ | People demand roughly 2× more to give up something they own than they would pay to acquire the identical thing — purely because they own it. | | Expected Value And Kelly | ↗ | Two questions decide most repeated bets: is this bet good? (EV) and how big? (Kelly). | | Falsifiability | ↗ | A meaningful empirical claim must specify what observations would refute it. | | Feedback Loops | ↗ | A system has a feedback loop when its output circles back as input to the next cycle. | | Feynman Technique | ↗ | The Feynman Technique tests whether understanding is genuine (can reproduce, predict, extend) or surface (can recognize, recall jargon). | | First Mover Advantage | ↗ | Lieberman and Montgomery's 1988 landmark paper established both the mechanisms of first-mover advantage and, with equal rigor, the mechanisms of first-mover disadvantage that make | | First Principles | ↗ | Most reasoning is reasoning by analogy: X resembles Y, so do what Y does. | | Founder Mindset | ↗ | A specific cognitive mode for running an early-stage company — different from manager mindset (optimizing known systems) and employee mindset (executing within fixed scope). | | Founder Trajectory Matrix | ↗ | Founders diverge along two behavioral axes: (1) actively seeking mentors vs. | | Framing Effect | ↗ | The framing effect: logically equivalent descriptions of the same decision produce different choices depending on whether outcomes are cast as gains or losses. | | Fundamental Attribution Error | ↗ | The fundamental attribution error (FAE) is the systematic tendency to over-weight character factors and under-weight situational factors when explaining others' behavior — while re | | Goodharts Law | ↗ | Goodhart's Law: when a metric controls behavior, people optimize the metric rather than the underlying goal. | | Gravity Field Empowerment | ↗ | Most improvement frameworks measure interventions by immediate effect — quarter-over-quarter lift, year-one ROI. | | Halo Effect | ↗ | A single positive or negative impression biases judgments of all unrelated attributes. | | Hanlons Razor | ↗ | Before assuming someone hurt you on purpose, construct the version where they made a mistake — and see how much evidence it explains. | | Herzberg Two Factor | ↗ | Herzberg's 1959 Pittsburgh study found satisfaction and dissatisfaction are two independent axes. | | Hidden Elite Advantages | ↗ | Top performers' results stem from nine hidden advantage dimensions — not visible actions. | | Hindsight Bias | ↗ | Hindsight bias — the "I knew it all along" effect — is the tendency, after learning an outcome, to misremember your prior judgment as having been closer to that outcome than it act | | Hyperbolic Discounting | ↗ | People discount the near future far more steeply than the distant future, producing dynamically inconsistent preferences: patient choices for next month reverse when next month arr | | Incentive Design | ↗ | Behavior follows incentives more reliably than character, intent, or training. | | Incremental Vs Leap Growth | ↗ | The most common strategic error is applying the wrong growth mode to a goal. | | Industry Learning Sprint | ↗ | A structured 3-step process (financial reports → expert dialogue → unique view) for building a working industry mental model in approximately one week. | | Intrinsic Drive | ↗ | Intrinsic motivation is a portfolio of distinct sources — not a binary switch. | | Inversion | ↗ | Most planning asks "how do I win?" and runs forward from there. | | Jobs To Be Done | ↗ | People don't buy products — they hire products to do a job (make progress in a specific circumstance, across functional, emotional, and social dimensions). | | K Factor Viral | ↗ | K = i × c, where i = average invites per existing user, c = conversion rate into new activated users. | | Knowing And Doing As One | ↗ | When you say "I know I should but I just don't do it," the standard explanation is a failure of willpower. | | Kotter Change | ↗ | John Kotter built this model from studying one hundred corporate transformations — most failed. | | Lateral Thinking | ↗ | Lateral thinking is the discipline of solving problems by approaching them from unexpected angles — not by going deeper along an existing logical path but by moving sideways to a n | | Latticework | ↗ | Latticework is the practice of cross-wiring mental models from multiple disciplines on the same situation. | | Lean Startup | ↗ | A startup is a temporary organization searching for a repeatable, scalable business model under extreme uncertainty (Steve Blank). | | Lifestage Value Curve | ↗ | Different life stages create different competitive advantages and demand different investments. | | Lindy Effect | ↗ | For non-perishable items — ideas, books, technologies, institutions, practices — life expectancy is proportional to current age. | | Logical Fallacies | ↗ | A fallacy is an argument that looks like it works but doesn't. | | Loss Aversion Prospect Theory | ↗ | People evaluate outcomes relative to a reference point (not absolute wealth), weight losses ~2.25x as heavily as equivalent gains, are risk-averse in gain frames and risk-seeking i | | Manager Development Spectrum | ↗ | Most leadership programs target skill acquisition. | | Map Is Not The Territory | ↗ | Any representation — metric, model, strategy deck, org chart, or process manual — is a selective, simplified, aging abstraction. | | Margin Of Safety | ↗ | Benjamin Graham introduced margin of safety in Security Analysis (1934) as the founding principle of value investing: buy assets at prices substantially below your estimate of intr | | Maslow Hierarchy | ↗ | Maslow's Hierarchy proposes needs organize into levels of prepotency — lower needs must be at least partially met before higher needs become motivationally dominant. | | Mece | ↗ | MECE is a decomposition principle: break a problem, set of options, or population into sub-groups that are Mutually Exclusive (no overlap) and Collectively Exhaustive (no gaps) — e | | Metacognition | ↗ | Metacognition is the live monitoring loop during reasoning — "am I doing this right now; what strategy am I using; should I switch?" — not after-the-fact reflection. | | Middle Way | ↗ | 中庸 (Zhongyong) is Confucian philosophy attributed to Zisi (c. | | Minsky Moment | ↗ | A Minsky Moment is the point at which a leveraged financial system tips from apparent stability into rapid self-reinforcing collapse — caused by the internal dynamic of debt accumu | | Momentum And Form | ↗ | Competitive advantage is two distinct things, not one: form (形, xíng) — the structural stock built before any contest (capital, distribution, brand, product, org capability) — and | | Mr Market | ↗ | Mr. | | Mvp | ↗ | An MVP is not a small version of your product — it is a test instrument: the smallest artifact that produces trustworthy evidence about one specific demand-side assumption, with th | | Narrative Fallacy | ↗ | The narrative fallacy is the tendency to construct retrospective causal stories that make past events seem inevitable — even when those events were largely random or contingent. | | Narrow Gate Strategy | ↗ | The narrow gate is the path that is genuinely difficult, genuinely right, and genuinely compounding — avoided by most who prefer immediate legibility over long-term leverage. | | Nash Equilibrium | ↗ | A Nash equilibrium is a stable point in multi-player interaction: a combination of strategies where no player can improve their payoff by unilaterally changing their own strategy, | | Network Effects | ↗ | Some products get more valuable the more people use them — not because the company gets cheaper at scale, but because each user makes the product more useful to every other user. | | Neurological Levels | ↗ | Robert Dilts' Neurological Levels maps how change propagates through a 6-level hierarchy (grounded in Bateson 1972): change at a HIGHER level cascades down automatically; change at | | Nine Level Cognitive Tower | ↗ | The Nine-Level Cognitive Tower (九层塔) disaggregates cognitive development into nine distinct operating levels, each with observable behavioral signatures. | | Non Consensus Thinking | ↗ | Every market — capital, talent, customers, ideas — prices the consensus view into its current state. | | Non Zero Sum | ↗ | A non-zero-sum interaction is one where mutual gain (or mutual loss) is possible — the parties' outcomes do not simply cancel each other out. | | North Star Metric | ↗ | The North Star Metric (NSM) is the single metric that most directly measures value delivered to customers and predicts revenue over time. | | Nudge Theory | ↗ | People procrastinate on retirement savings, skip vaccine appointments, and leave privacy settings on dangerous defaults — not from ignorance, but because the choice environment wor | | Occams Razor | ↗ | When several explanations all fit the evidence, prefer the one that assumes the least. | | Okr Goal Setting | ↗ | OKRs separate ambition from measurement: an Objective is qualitative and aspirational; Key Results (3-5) are quantitative outcomes proving the objective was reached. | | Ooda Loop | ↗ | Colonel John Boyd (1927-1997) derived the OODA Loop from Korean War air-combat data: the F-86 Sabre achieved a ~10:1 kill ratio over the technically superior MiG-15 because better | | Opportunity Cost | ↗ | Opportunity cost is the true cost of any choice: the value of the next-best alternative you give up. | | Organic Plus Extension Growth | ↗ | Organic growth builds value from within (product, operations, retention, unit economics). | | Overseas Expansion Framework | ↗ | International expansion forks into two models: Spirit Expansion (精神出海) — product/IP travels digitally or via exported goods, no local presence required — and Physical Expansion (实体 | | Pareto Principle | ↗ | In most real systems, a small fraction of inputs produces the majority of outputs. | | Peak End Rule | ↗ | People remember experiences not by averaging all moments but by sampling two: the peak (highest emotional intensity) and the end. | | Pmf Crossing The Chasm | ↗ | Two distinct questions decide early-stage growth: (1) PMF — do enough users love the product they'd be very disappointed without it? (2) Chasm — can you move from early adopters (t | | Point Line Plane Solid | ↗ | Maps competitive position across four strategic dimensions: Point (one capability, easily copied) → Line (integrated pipeline, integration is the asset) → Plane (platform/ecosystem | | Porters Five Forces | ↗ | Some industries earn 30%+ margins decade after decade; others fail to earn their cost of capital despite intelligent, well-funded firms. | | Power Law Distribution | ↗ | A power-law distribution is a statistical distribution where probability of size x is proportional to x^(−α): large events are rare but far more probable than a Gaussian model pred | | Premortem | ↗ | Before committing to a plan, the team imagines that plan has already failed catastrophically, then works backward to enumerate causes. | | Pricing Strategy | ↗ | Price is a structural decision, not a calculated number. | | Principal Agent | ↗ | One party (the principal) delegates to another (the agent) whose interests differ and whose actions can't be fully observed — producing agency cost: monitoring spend + agent bondin | | Prisoners Dilemma | ↗ | Whatever the other party does, each player is individually better off defecting — so both defect, and both end up worse than mutual cooperation. | | Probabilistic Thinking | ↗ | Most reasoning is binary: will it happen, or won't it? That framing discards the most useful information — the degree of confidence — and produces predictions that cannot be checke | | Reciprocity | ↗ | The rule of reciprocity — if someone gives you something, you owe them something back — recurs across virtually every documented human culture (Mauss 1925; Gouldner 1960). | | Red Queen Effect | ↗ | The Red Queen Effect: competitors must continuously improve just to maintain relative position — because everyone else is improving simultaneously. | | Regression To The Mean | ↗ | Regression to the mean is the statistical regularity that any noisy measurement producing an extreme value tends to be followed on retest by a less-extreme value — because the extr | | Regret Minimization | ↗ | Most frameworks optimize expected value — pick the highest probability-weighted payoff. | | Repeated Games Reputation | ↗ | When parties repeat — or third parties observe — defection costs tomorrow's cooperation, flipping the Prisoner's Dilemma. | | Representativeness Heuristic | ↗ | The representativeness heuristic is judging probability by how closely something resembles a prototype — overriding actual base rates. | | Resource Integration Hierarchy | ↗ | Most organizations operate well below their potential resource access. | | Resource Time Compression | ↗ | Most plans estimate how long each step takes and add them up — producing a multi-year sequential path that reflects a solo, resource-constrained default. | | S Curve Technology Adoption | ↗ | Innovations spread on a sigmoid (S-shaped) curve: slow → accelerating → leveling off at saturation. | | Scenario Planning | ↗ | Scenario planning accepts that certain futures are genuinely unknowable and prepares for several of them rather than betting on one forecast. | | Second Curve | ↗ | Every business follows an S-curve: slow start, steep growth, peak, then decline. | | Second Order Thinking | ↗ | First-level thinking asks "what will happen?" and stops. | | Self Evolution 3d | ↗ | Treats personal growth as three orthogonal dimensions — Height (mission vantage), Width (perspective breadth), Depth (self-awareness accuracy) — each with a distinct mechanism and | | Self Renewal | ↗ | Self-renewal is the structured practice of identifying which mental models have passed their expiry date and genuinely updating — not merely annotating — them. | | Shi Momentum | ↗ | 势 (shì) is the propensity of a situation to evolve in a direction — a wave you read and ride, not power you exert. | | Signaling Games | ↗ | One party knows something the other cannot verify. | | Situational Leadership | ↗ | Match your leadership style to each person's development level on each specific task — cycling through four styles (Directing, Coaching, Supporting, Delegating) as competence and c | | Six Thinking Hats | ↗ | Six Thinking Hats (Edward de Bono, 1985) prevents the most common meeting failure: different thinking modes colliding simultaneously. | | Social Proof | ↗ | Social proof: we judge what is correct, normal, or worth doing by observing what others — especially similar others — are doing. | | Status Quo Bias | ↗ | Status quo bias is the systematic preference for the current state over available alternatives — even when alternatives are objectively superior by the person's own values. | | Strategic Commitment | ↗ | Strategic commitment converts "I might do X" into "I will do X" — not through rhetoric but by changing payoff structure so follow-through is the rational move. | | Strategic Execution 3d9 | ↗ | Execution failure is the most expensive strategy problem in organizations — not because strategies are wrong, but because organizations underinvest in the capability infrastructure | | Strategic Spiral Momentum | ↗ | Strategic Spiral Momentum maps organizational strategy as a 10-phase cyclical spiral: 谋势 (plan) → 蓄势 (store) → 造势 (create) → 借势 (leverage) → 起势 (launch) → 乘势 (ride) → 定势 (stabilize | | Strategy Execution Levers | ↗ | Most organizations apply a single intervention — a town hall, a kickoff — then diagnose failure as a communication problem. | | Structured Communication | ↗ | Most communication failure is a failure of sequence and mode — not information. | | Sunk Cost Fallacy | ↗ | The sunk-cost fallacy is the tendency to let prior, irrecoverable investments (money, time, effort, reputation) distort current decisions. | | Survivorship Bias | ↗ | Survivorship bias is drawing conclusions from a sample pre-filtered by survival — treating survivor traits as the cause of survival when non-survivors (absent from data by definiti | | Switching Costs | ↗ | Switching costs are everything a customer must pay, learn, redo, or risk to move from one product to another — financial, learning, data migration, integration, process, relational | | Swot Analysis | ↗ | SWOT maps internal Strengths/Weaknesses against external Opportunities/Threats, then generates strategies via TOWS cross-matrix (SO/ST/WO/WT). | | T Shaped Connector | ↗ | The T-shaped metaphor (deep vertical + broad horizontal) is widely used but rarely validated. | | Theory Of Constraints | ↗ | Theory of Constraints (TOC) — Eliyahu Goldratt, 1984: throughput of any multi-step system is determined by its single bottleneck. | | Thought Experiment | ↗ | A thought experiment is structured reasoning: construct a scenario, trace logical consequences of explicit premises, examine the result for contradiction, hidden assumptions, or ne | | Three Radius Model | ↗ | Three distinct circles govern performance: what you understand (cognition radius), what you can do (capability radius), and what you actually do (action radius). | | Thucydides Trap | ↗ | Thucydides's Trap is the structural danger that emerges when a rising power threatens to displace a ruling power — producing fear in the established power that makes conflict more | | Timing Action Matrix | ↗ | Most frameworks ask: "Is this the right action?" Timing is an independent variable of equal weight — a brilliant action at the wrong time fails because of timing, not the action. | | Tipping Point | ↗ | A tipping point is the threshold at which gradually accumulating change produces a sudden, self-reinforcing reorganization of a system. | | Tragedy Of The Commons | ↗ | When a shared resource has individual access but no individual responsibility for preservation, rational users extract private benefit while the cost of overuse is shared — leading | | Trust Brand Architecture | ↗ | Brand trust builds through three sequential layers: Functional Trust (does the product do what it claims?) → Emotional Trust (does this brand handle problems with empathy?) → Ident | | Tunnel Vision Slack | ↗ | When urgent demands consume all your bandwidth, the future becomes cognitively inaccessible — not a choice, but a structural block. | | User Insight Engine | ↗ | User research produces data. | | Utilitarianism | ↗ | Utilitarianism holds that the right action produces the greatest net well-being across all affected parties, weighted by magnitude and probability. | | Value Chain Analysis | ↗ | Porter (1985) separates firm activities into primary (inbound logistics, operations, outbound logistics, marketing/sales, service) and support (firm infrastructure, HR management, | | Wu Wei | ↗ | Wu wei (无为) — Daoist principle (Daodejing, ~4th century BCE): act without forcing, not without acting. | | Zero Sum Game | ↗ | Zero-sum means total value is fixed — one player's gain is another's exact loss. |
These are the same 163 skills wired into every deciqAI agent — which runs them autonomously to operate your company.