Claude

Translates beliefs (probabilities) into optimal actions (bet/pass/hedge) using quantitative frameworks including edge calculation, Kelly Criterion bet sizing, forecast extremizing, and Brier score optimization. Use when converting probabilities into decisions, calculating edge against market odds, sizing bets optimally, extremizing aggregated forecasts, improving Brier scores, or when user mentions betting strategy, Kelly Criterion, edge calculation, Brier score, extremizing, or translating belief into action.

Runs the hard gate on invention in fact-based narrative — a bright-line refusal sweep, an interior-state provenance ladder ([A] said-so / [B] contemporaneous document / [C] behavioural inference / [D] unsourced, where any [D] blocks publication), an LLM-specific fabrication red-flag scan, a three-altitude "How do you know?" prosecution at sentence, paragraph and passage level, a subtraction-log set review, and a note on sources generated from the deviation log. Use before shipping any narrative built on real evidence — market history, incident post-mortem, biography, ML writeup, supply-chain reconstruction, science writing — or when the user mentions fact-check, fidelity audit, fabrication check, invented detail, sourcing pass, did I make this up, composite scene, note on sources, or is this defensible.

Builds a four-corner opposition web for narrative nonfiction and stops the writer from casting whoever lost as the villain. Runs Truby's four-corner worksheet (shared central moral problem, per-corner value clusters, distinct routes of attack, corner-to-corner conflict), the best-possible-opponent audit (same goal, necessity, relentlessness, value conflict, the double, power parity, justification in the opponent's own voice), the Opponent Warrant evidence test that demotes undocumented antagonists to rivals or constraints, and a drive-section collapse check that catches a web that was decorative. Use when planning a piece with competing parties, when an antagonist feels flat or cartoonish, when the protagonist is a system rather than a person, or when user mentions opposition web, four-corner opposition, antagonist, opponent, villain, steelman the other side, character web, who is the bad guy here.

Prices options for valuation work — Black-Scholes with a cost-of-delay yield, binomial trees that allow early exercise, dilution-adjusted employee options for the equity bridge, equity in a heavily levered firm valued as a call on firm value, and implied volatility. Use when employee options or warrants must be subtracted before computing value per share, when a distressed or negative-earnings company's equity still trades above zero, when testing whether a patent, licence, undeveloped reserve or expansion right is a real option that deserves a premium, or when early exercise makes a European formula wrong. Triggers on option pricing, Black-Scholes, binomial tree, real options, option to delay, patent as an option, equity as a call option, distress and default probability, employee stock options, dilution, warrants, implied volatility, put-call parity.

Detects and removes cognitive biases from reasoning using Julia Galef's Scout Mindset framework. Provides reversal tests, scope sensitivity checks, status quo bias tests, confidence interval audits, and full bias audits. Use when a prediction feels emotional, stuck at 50/50, or when validating forecasting process. Use when user mentions scout mindset, soldier mindset, bias check, reversal test, scope sensitivity, or cognitive distortions.

Values companies the standard DCF cannot handle, across five branches — distress (failure probability from a bond price or rating, blended with the distress-sale outcome), financial service firms (equity excess return and FCFE against regulatory capital, since a bank gets no FCFF and no optimal debt ratio), private companies (total beta for an undiversified owner, Silber and bid-ask illiquidity discounts), cyclical and commodity firms (mid-cycle normalized earnings), and young negative-earnings firms (a revenue and margin path plus survival odds, emitted as a dcf-valuation-engine payload). Also walks a private owner's value to an IPO offer price line by line. Use when valuing a bank, insurer, startup, distressed firm, private business, miner or deep cyclical, when pricing an IPO or a sale to a public buyer, or when asked about probability of distress, total beta, illiquidity discount, excess return models, normalized earnings, or negative-earnings valuation.

Scans a taxable brokerage account for individual lots with unrealized losses above a configurable threshold, identifies wash-sale risks by checking recent buys and forward planned buys of substantially identical securities (across all household accounts including spousal), and proposes harvest pairs (sell-for-loss + immediate buy of a similar-but-not-identical replacement). Use for year-end tax planning, monthly TLH scans, after market drawdowns, or when user mentions tax-loss harvesting, TLH, wash sale, or harvest candidates.

Detects and removes duplicate transactions across overlapping bank, credit-card, and brokerage statement imports using a stable composite key (account_id, date ±1d, amount_cents, description_normalized). Emits a list of new transactions to commit, a list of suppressed duplicates with their reasons, and a list of suspicious near-duplicates that need human review. Use when ingesting financial statements that may overlap prior drops, merging multiple export sources for the same account, or when user mentions duplicate transactions, deduping a transaction file, or reconciling overlapping statements.

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Guides the creation of career documents for academic advancement including research statements, teaching statements, diversity statements, CVs, and biosketches. Combines strategic positioning, narrative coherence, and institutional alignment with authentic representation of contributions and vision. Use when writing or reviewing faculty applications, fellowship statements, promotion packages, award applications, or when user mentions research statement, teaching philosophy, diversity statement, biosketch, academic CV, or career narrative.

Detects and prevents visual misleads, cognitive biases, and data integrity violations in visualizations, dashboards, reports, and presentations. Audits charts for honesty, diagnoses misinterpretation causes, and provides specific fixes. Invoke when user mentions chartjunk, misleading chart, truncated axis, data integrity, visual deception, 3D chart problems, cherry-picking data, or needs to audit visualizations for accuracy. For general design evaluation, use `design-evaluation-audit`. For cognitive foundations, use `cognitive-design`.

Designs embedding strategies that combine semantic (text-based) and structural (graph-based) information at node, edge, path, and subgraph levels for knowledge graphs. Use when selecting embedding granularity, choosing complementary semantic and structural approaches, designing fusion strategies (concatenation, attention, contrastive alignment), or when user mentions node embeddings, embedding fusion, vector representations for graphs, or combining text and graph signals.

Provides practical frameworks for fast decision-making through mental shortcuts (heuristics) and systematic error prevention through structured checklists. Guides through designing effective heuristics, creating checklists for complex procedures, and recognizing when shortcuts lead to biases. Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions heuristics, rules of thumb, mental models, checklists, error prevention, cognitive biases, satisficing, or standard operating procedures.

Creates evidence-based learning plans that maximize long-term retention through spaced repetition, retrieval practice, interleaving, and elaboration. Guides through goal definition, material breakdown, review scheduling, and progress tracking. Use when long-term knowledge retention is needed, studying for exams or certifications, learning new job skills or technology, mastering substantial material, combating forgetting, or when user mentions studying, memorizing, learning plans, spaced repetition, flashcards, active recall, or durable learning.

Builds the evidence ledger that narrative work is allowed to be built on, before any structure is chosen. Locks the frame (unit, denominator, window, population boundary), atomizes material into findings with evidence classes A-F and re-findable pointers, triages every causal claim L1 MECHANISM to L5 CONJECTURE with permitted and banned verb sets, runs one-way promotion from finding to claim to beat, and keeps a DEAD column of everything a veto killed. Use before outlining or drafting any evidence-based narrative, when auditing whether a draft's claims are actually sourced, when a piece needs a provenance layer for handoff, or when user mentions evidence ledger, claim ledger, provenance, sourcing, causal grading, denominator lock, cherry-picking, or circular citation.

Evaluates whether substacker has the four preconditions for launching a paid tier — enough subs, healthy engagement, a clear candidate section, writer capacity. Produces readiness score (not-ready / close / ready) with named gaps. Used when the "should we launch paid?" question is selected or at writer's explicit request. Trigger keywords — paid tier, paid readiness, monetization, Substack paid, launch paid, 1000 subscribers.

Identifies recurring charges (subscriptions, monthly bills, biweekly paychecks) from a transaction history by clustering same-merchant transactions of similar amount on a regular cadence, requiring at least 3 confirming occurrences before promoting a candidate to active status. Detects new recurring charges, dormant subscriptions (missed expected dates), and amount drift, and computes annualized cost. Use when auditing subscriptions, building a recurring bills calendar, computing cash-flow forecast inputs, or when user mentions subscription audit, recurring detection, dormant subscription, or annualized cost.

Facilitates structured team reflection through retrospectives, post-mortems, after-action reviews, and weekly/quarterly reviews, producing root cause analysis and SMART action items with psychological safety. Use when conducting sprint retrospectives, project post-mortems, weekly reviews, quarterly reflections, after-action reviews (AARs), or when user mentions "retro", "retrospective", "what went well", "lessons learned", "reflection", or "how can we improve".

Maps identified symmetries to mathematical groups (cyclic, dihedral, symmetric, SO(3), SE(3), E(3)) for equivariant neural network architecture design, using taxonomy and foundations from Visual Group Theory. Use when candidate symmetries have been identified and need formalization into group theory language, or when user mentions cyclic groups, dihedral groups, Lie groups, SO(3), SE(3), or permutation groups.

Provides empirical test protocols and metrics to validate whether hypothesized symmetries actually hold in data or models before committing to equivariant architecture. Includes invariance/equivariance testing, group structure verification, and distribution analysis under transforms. Use when testing invariance, validating equivariance, checking symmetry assumptions, debugging symmetry-related model failures, or needing data-driven validation before architecture decisions.

Finds high-leverage intervention points in complex systems by mapping feedback loops, identifying system archetypes (fixes that fail, shifting the burden, tragedy of the commons, limits to growth), and ranking interventions by Meadows' leverage hierarchy. Use when problems involve interconnected components with feedback loops, delays, or emergent behavior; when past solutions failed or caused unintended consequences; when identifying where to push for maximum effect; or when user mentions systems thinking, leverage points, feedback loops, causal loop diagrams, stocks and flows, or complex systems.

Guides writing architecture planning using McPhee's structural diagramming method, helping select from 8 structure types (list, chronological, circular, dual/triple profile, pyramid, parallel, custom), create visual diagrams, and place gold-coin moments for engagement. Use when planning or organizing writing structure, outlining before drafting, restructuring disorganized drafts, or when user mentions outlining, organizing ideas, structure planning, article architecture, narrative flow.

Constructs a structured narrative linking a company's qualitative business story to quantitative valuation drivers (revenue growth, target margin, reinvestment efficiency, cost of capital, failure risk). Classifies the company within a 6-stage corporate life cycle and sizes the total addressable market. Use when starting a company analysis, building a valuation narrative, assessing competitive position, sizing TAM, or when user mentions business narrative, story to numbers, life cycle stage, or company analysis.

Transforms analysis, data, and complex information into clear, persuasive narratives tailored to specific audiences — executives, customers, investors, or non-technical stakeholders. Provides story structures (Hero's Journey, Problem-Solution-Benefit, Situation-Complication-Resolution) and audience adaptation techniques. Use when presenting findings, explaining technical concepts to non-technical audiences, writing announcements, or when user mentions "write this for", "explain to", "present findings", "make this compelling", or "audience is".

Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.

Runs a vault learning module as a Kolb experiential cycle (Concrete Experience -> Reflective Observation -> Abstract Conceptualization -> Active Experimentation) instead of a lecture. Opens with an experience, withholds the explanation, draws the claim out of the learner with Socratic question ladders scaled by Bloom level, routes the earned claim to an evergreen note, and closes with a retrieval check. Enforces desirable-difficulty discipline — never summarize for the learner, never name the concept before they have reconstructed its mechanism. Use when tutoring a genomics/ML module, designing a Kolb session, or deciding whether to explain or to ask. Trigger keywords — Kolb cycle, experiential teaching, tutor a module, desirable difficulty, never summarize, Socratic ladder, run a session.

Presents a math or ML concept simultaneously in geometric form (picture, transformation, region, surface) and algebraic form (formula, matrix, derivation), then writes the explicit one-sentence bridge that says "these are the same thing because…". The signature 3Blue1Brown move applied to any vector/matrix concept. Use when a learner has one view but not the other ("I understand the formula but not what it means" or "I see the picture but can't write it down"), when introducing a concept that genuinely needs both views to land (eigendecomposition, SVD, dot product, attention, gradient, covariance), or when the user mentions "geometric meaning", "intuition behind", "picture for", or "why does the formula look like that".

Diagnoses where a learner's 3D geometric intuition is misleading them in a high-dimensional context (concentration of measure, Gaussian shells, distance-metric breakdown, manifold hypothesis, volume-in-corners, random-projection preservation), then surgically replaces the false picture with the correct one. Use when the user is reasoning about high-dim spaces (embeddings, latent vectors, neural net activations, large-scale data clouds, optimization landscapes) and either makes a claim that's true in 3D but false in 1000D, or expresses confusion at a high-dim phenomenon that "shouldn't" happen.

Verifies that implemented neural network models correctly respect their intended symmetries through systematic equivariance testing, layer-wise isolation, and gradient analysis. Use when testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if a model is actually equivariant, or diagnosing why an equivariant model isn't working.

Defines and validates the machine-readable contract that passes a narrative architecture between a structural agent and a drafting agent — architecture.json with evidence-backed slots, capped scene tags, gap dispositions, a DEAD column, and an escalation object for sending defects back upward. Ships a validator script so the rules are enforced rather than requested. Use when two agents or two sessions must hand narrative work to each other, when an architecture needs checking before drafting begins, when a draft must report a defect it cannot fix at its own layer, or when the user mentions handoff, contract, schema, validator, architecture.json, escalation, or "the outline and the draft have drifted apart".

Aggregates investment holdings across taxable brokerage, 401k, and HSA into a single asset-allocation view, computes drift versus a target allocation, and produces a tax-efficient rebalance proposal that prefers tax-advantaged accounts for the trades and never executes. Flags drift over 5 percentage points and free-money issues like missed 401k employer match. Use when reviewing portfolio allocation, planning a rebalance, computing drift, or when user mentions asset allocation, drift, rebalancing proposal, or 401k match.

Creates strategic portfolio roadmaps that size and sequence initiative bets across time horizons (H1/H2/H3), balance risk profiles (core/adjacent/transformational), and set clear exit/scale criteria for disciplined resource allocation. Use when managing multiple initiatives across time horizons, balancing risk vs return across portfolio, sizing and sequencing bets with dependencies, setting exit/scale criteria for experiments, allocating resources across innovation types, or when user mentions portfolio planning, roadmap horizons, betting framework, initiative prioritization, innovation portfolio, or resource allocation across horizons.

Prices a company against peers and the market with multiples — builds PE, PEG, PBV, EV/EBITDA, EV/EBIT, EV/Sales and EV/Invested Capital with the numerator/denominator consistency rule enforced, computes peer medians and quartiles, fits an ordinary-least-squares regression of a multiple on its companion variables for a sector or the whole market, reports predicted versus actual under and over valuation, and derives the intrinsic multiple from DCF fundamentals. Prices a conglomerate division by division with a sum of the parts, and values cross-holdings and minority interests. Bundles Damodaran's regional pricing regressions and multiple distributions. Use for relative valuation, comparable company analysis, trading comps, sector or market multiple regressions, justified multiples, PEG screens, sum-of-the-parts or break-up analysis, conglomerate discounts, cross-holdings and minority interests, or when asked whether a stock is cheap on its multiple.

Reviews scientific documents for logical clarity, argument soundness, and rigor by auditing hypothesis-data alignment, claim-evidence chains, quantitative precision, hedging calibration, and terminology consistency across any document type. Use when reviewing scientific argumentation, checking claims vs evidence, auditing terminology, or when user mentions check clarity, review logic, scientific soundness, hypothesis-data alignment, or claims vs evidence.

Given a current win probability and a downside asymmetry flag, recommends a variance-seeking, neutral, or variance-minimizing posture and emits a numeric multiplier (typically 0.8-1.3) for downstream consumers to apply to boom-bust scores, position sizes, or bet sizes. Favorites minimize variance; underdogs maximize it. Reusable across fantasy sports lineup construction, portfolio allocation, poker bankroll decisions, racing strategy, and any decision where the agent controls a variance knob. Use when user mentions variance strategy, underdog variance, variance seeking, variance minimizing, risk posture, boom bust, must-win variance, favorite strategy, or when a decision module needs a single scalar to bias toward or away from high-variance options.

Transforms data into compelling visual narratives by applying narrative structure, annotation techniques, scrollytelling patterns, and honest framing to data journalism, presentations, and infographics. Use when creating data-driven articles or reports, designing infographics with narrative, building scrollytelling experiences, annotating charts to guide interpretation, or when user mentions data storytelling, presentation design, annotated chart, narrative visualization.

Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.

Creates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.

Computes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.

Applies structured divergent-convergent thinking to generate many creative options, organize them into meaningful clusters, then systematically evaluate and narrow to the strongest choices. Balances creative exploration with disciplined decision-making. Use when exploring product ideas, solving open-ended problems, generating strategic alternatives, developing research questions, designing experiments, or when user mentions brainstorming, ideation, divergent thinking, generating options, or evaluating alternatives.

Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms. Distinguishes genuine causation from spurious associations, tests competing explanations, and designs interventions addressing underlying drivers. Use when investigating why something happened, debugging systems, analyzing failures, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"

The multi-agent communication and orchestration discipline for a staged pipeline whose stages each carry calibrated uncertainty. Agents talk through files with defined schemas and status fields (never free text); the orchestrator passes input paths plus an explicit output path plus a return contract, verifies each artifact's confidence before advancing a stage gate, holds and integrates worker outputs rather than passing them through, freezes its protected control logic against a checksum, maintains a diversity floor, hardens the fragile handoffs not the resilient hubs, and names the substitution effect every optimized score produces. Conference-agnostic; preloaded by a pipeline orchestrator. Use when coordinating a staged agent pipeline, designing the orchestrator-worker contract, or deciding when to advance, reconcile, or escalate. Trigger keywords - pipeline orchestration, stage gates, structured agent communication, invariant guard, confidence propagation, conflict surfacing.

Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.

Turns limitations into creative fuel by strategically imposing constraints that force novel thinking, break habitual patterns, and reveal unexpected solutions. Covers resource constraints (budget/time/tools), format constraints (length/medium), rule-based constraints, and perspective constraints. Use when brainstorming feels stuck or generates obvious ideas, working with limited resources, designing with specific limitations, or when user mentions "think outside the box", "we're stuck", "same old ideas", "tight constraints", or "limited budget/time".

Computes P(we win at least K of N categories) for a head-to-head categorical matchup via Monte-Carlo simulation or Poisson-binomial approximation. Domain-neutral — works for any fantasy sport with H2H Categories scoring (MLB, NBA, NHL) or any zero-sum per-category competition. Use when you need matchup_win_probability, per_cat_win_probability, expected_cats_won, or variance_estimate; or when user mentions "matchup win probability", "head to head simulation", "Monte Carlo matchup", "Poisson binomial matchup", "P win 6 of 10", "category matchup simulation", or "weekly win probability".

Derives a document's structure out of its own corpus instead of picking one off a menu, using John McPhee's coding-and-sorting procedure - cold read, short topic codes one per card, a strict chronology sort run against a strict theme sort, a logged list of every disagreement resolved toward chronology, candidate juxtapositions gated by a state-and-footnote test, a named shape, and an invisibility test. Use when you hold researched material and have no structure yet, when a draft has turned into concept-named sections full of time-scrambled evidence, when deciding whether a flashback is earned, or when user mentions McPhee, coding pass, index cards, deriving structure, chronology versus theme, structure from material, or "what shape is this piece".

Computes the weekly category state for a Yahoo H2H Categories matchup across all 10 scoring categories (R, HR, RBI, SB, OBP, K, ERA, WHIP, QS, SV). Pulls current totals from Yahoo, builds rest-of-week per-cat projections from roster + schedule, then DELEGATES matchup/per-cat win-probability math to `matchup-win-probability-sim`. Consumes the sim's `per_cat_win_probability` and `matchup_win_probability` to derive cat_position, cat_pressure, cat_reachability, and cat_punt_score, and emits a "push 6, punt N" plan that drives waiver, streaming, and lineup decisions. Use when user asks about "category state", "where am I winning", "should I punt", "matchup score", "cat pressure", weekly category planning, or which cats to push vs. concede.

Explores solution spaces systematically through morphological analysis (parameter-option matrices) and resolves technical contradictions using TRIZ inventive principles to generate novel, non-obvious solutions. Use when exploring all feasible design alternatives before prototyping, resolving technical contradictions (speed vs precision, strength vs weight, cost vs quality), generating novel product configurations, finding inventive solutions to engineering problems, identifying patent opportunities, or when user mentions morphological analysis, Zwicky box, TRIZ, inventive principles, systematic innovation, or design space exploration.

Domain-neutral methodology for autonomously extracting structured notes from a single academic paper via three escalating passes. Pass 1 (inspectional, ~10-15 min) reads title, abstract, intro, section headings, conclusion, references at a glance, then applies the Five Cs framework (Category, Context, Correctness, Contributions, Clarity). Pass 2 (content grasp, ~30-60 min) reads the full paper skipping proofs, answers main-argument / Big-Question / hypotheses / figure-by-figure / references / confusions. Pass 3 (deep understanding, ~1-4 hours, reserved for important papers) virtually re-implements, challenges every assumption, identifies what is NOT said, asks the falsifiability question. The methodology is internal to the agent applying it - questions are answered against the paper's content, never asked of the operator. Use when an extraction agent needs to convert dense academic prose into structured machine-and-human-readable notes - bio papers, CS papers, ML papers, statistics, math, any field.

Evaluates a discrete investment, project or acquisition from its cash flow stream — NPV, IRR with every root reported when the stream has more than one, MIRR, profitability index and project selection under a capital budget, equivalent annuities and replication for unequal lives, payback and discounted payback, project return on capital and EVA, synergy value with the ceiling price it supports, the value of control and its expected value, the four-number acid test for a deal, and control premiums and minority discounts. Use when deciding whether to take a project, ranking competing projects, comparing projects with different lives, sizing a capital budget, testing whether a stream is truly incremental, valuing synergy or control, pricing a majority or minority stake, or setting the maximum price for an acquisition.

Anchors predictions in historical reality by identifying a class of similar past events and using their statistical frequency as a baseline (outside view) before analyzing case-specific details. Use when starting a forecast, establishing base rates, testing "this time is different" claims, or when user mentions reference classes, outside view, base rates, or starting a new prediction.

Guides learners to discover knowledge through strategic Socratic questioning and progressive scaffolding removal. Combines question ladders, misconception detectors, Feynman explanations, and worked-example fading to build durable understanding. Use when teaching complex concepts, correcting misconceptions, onboarding team members, mentoring problem-solving, or designing self-paced learning. Use when user mentions "teach me", "help me understand", "explain like I'm", "learning path", "guided discovery", or "Socratic method".

The recombination operator for the FIFA World Cup Fantasy evolution engine. Crosses elite candidate squads/plans at BUILDING-BLOCK boundaries (Captain Core, Clean-Sheet Spine, Mid-Engine, Differential Pod, Enabler Bench; or for matchday plans the XI/captain-ladder/bench/sub/chip blocks) — harvesting the strongest module from each parent rather than swapping individual players — then runs a feasibility REPAIR operator (budget, nation cap, formation, 15-man shape) that restores legality from the cheapest block first and never guts a value-bearing block. Records block lineage (which parent each block came from). Implements the Evolution document's central lesson that naive crossover destroys good building blocks. Use in the recombine stage after fitness selection.

Generates structured scaffolds (frameworks, checklists, templates) for technical work — TDD test suites, exploratory data analysis plans, statistical analysis designs, causal vs predictive modeling objectives, and validation checklists. Use when starting technical work that needs systematic planning before execution. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", "design an A/B test", or when technical work needs scaffolding before execution.

Breaks complex systems into atomic components, maps their relationships, and reconstructs them in optimized configurations to identify bottlenecks, critical failure points, and redesign opportunities. Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, or when optimization requires understanding how parts interact.

Derives a draft per-section voice overlay (deltas against substacker global voice-profile) once a section reaches ≥3 published posts with shared voice tells. Writes to shared-context/voices/{slug}.md. Writer reviews and commits. Overlay expresses only the DELTA from global voice — not a full rewrite. Use when a section crosses the 3-post threshold. Trigger keywords — voice overlay, section voice, overlay delta, per-section voice.

Designs structured interview guides, survey instruments, and JTBD probes to learn from users while avoiding common research biases (leading questions, confirmation bias, selection bias). Use when validating product assumptions before building, discovering unmet user needs, understanding customer problems and workflows, testing concepts or positioning, researching target markets, identifying jobs-to-be-done and hiring triggers, or uncovering pain points and workarounds.

Designs and builds knowledge graphs from unstructured or semi-structured data sources. Guides through data model selection (LPG, RDF, hypergraph, temporal), schema design, entity/relation extraction pipelines, and layered architecture construction. Use when designing knowledge graphs, choosing between LPG vs RDF, planning entity extraction, designing graph schemas, aligning ontologies, building a KG for RAG, or when user mentions knowledge graph construction.

Defines concepts, quality criteria, and boundaries by showing what they are NOT -- using anti-goals, near-miss examples, and failure patterns to create crisp decision criteria where positive definitions alone are ambiguous. Use when clarifying fuzzy boundaries, defining quality criteria, teaching by counterexample, preventing common mistakes, setting design guardrails, disambiguating similar concepts, refining requirements through anti-patterns, or when user mentions near-miss examples, anti-goals, what not to do, negative examples, counterexamples, or boundary clarification.

Transforms overwhelming backlogs into clear, actionable priorities by mapping items on a 2x2 effort-vs-impact matrix, identifying quick wins (high impact, low effort), big bets, time sinks, and fill-ins. Use when ranking backlogs, deciding what to do first, prioritizing feature roadmaps, triaging bugs or technical debt, allocating resources across initiatives, identifying low-hanging fruit, evaluating strategic options, or when user mentions prioritization, quick wins, effort-impact matrix, high-impact low-effort, big bets, or "what should we do first?".