yogsoth-ai
- 1.8k skills
- 0 followers
- 512 repo stars
- yesterday last updated
- ▌ Portfolio Optimization · yogsoth-aiFormalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.
- ▌ Project Future Reality · yogsoth-aiProject the downstream consequences of a proposed constraint-breaking intervention and detect new undesirable effects.
- ▌ Update Pairwise Rating · yogsoth-aiUpdate candidate latent ratings and uncertainty from sequential pairwise outcomes using an explicitly chosen Bradley-Terry/Elo/Glicko/TrueSkill-style update model.
- ▌ Verify Reproducibility · yogsoth-aiAssess reproducibility across reruns/replications using the predeclared reproducibility target and suitable agreement/variance metrics.
- ▌ Assess Goal Feasibility · yogsoth-aiCross-check goal branches against resources, obstacles, and timeline; label feasible/stretch/infeasible and propose OR alternatives.
- ▌ Assess Publication Bias · yogsoth-aiAssess or plan tests for publication/reporting/time-lag/citation/language bias using appropriate diagnostics.
- ▌ Assess Question Quality · yogsoth-aiAudit a research question for scope and FINER-style quality; return targeted repairs.
- ▌ Audit Reporting Quality · yogsoth-aiAudit whether a research/evaluation artifact reports the information needed for interpretation and reproduction, using a domain-appropriate checklist.
- ▌ Construct Design Matrix · yogsoth-aiConstruct a balanced/randomized/orthogonal experimental design matrix appropriate to the chosen design mode.
- ▌ Decompose Research Goal · yogsoth-aiTurn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations.
- ▌ Enumerate Failure Modes · yogsoth-aiConvert functions/process steps/scenarios into explicit failure modes.
- ▌ Evaluate Falsifiability · yogsoth-aiDetermine what observation would falsify a hypothesis and flag unfalsifiable formulations.
- ▌ Extract Evidence Record · yogsoth-aiExtract a schema-declared evidence record from a source, including methods, datasets, metrics/results, conditions, limitations, provenance, and explicitly missing/ambiguous fields.
- ▌ Generate Counterexample · yogsoth-aiGenerate a concrete counterexample candidate that satisfies the target claim's stated scope while violating its conclusion or claimed structural property; record whether exclusion would be principled or ad hoc.
- ▌ Identify Critical Chain · yogsoth-aiIdentify the longest/limiting dependency path while accounting for resource contention and convergence points.
- ▌ Identify Dominant Frame · yogsoth-aiIdentify the dominant framing/paradigm or governing variable constraining the current problem representation.
- ▌ Map Ablation Components · yogsoth-aiMap system structure into ablatable units, dependencies, legal removal/replacement operations, and expected contribution hypotheses.
- ▌ Map Productive Polarity · yogsoth-aiMap a persistent two-pole tension where both poles contain value: upsides/downsides of over-focusing each pole, warning signs, and practices that manage the polarity rather than falsely resolving it.
- ▌ Adjust Abstraction Scope · yogsoth-aiMove a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful explanatory and experimental leverage.
- ▌ Adversarial Deliberation · yogsoth-aiRun structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth, loser-resurrection, and steelman/winner-stress modes are parameters; role execution is runtime-agnostic.
- ▌ Generate Subquestions · yogsoth-aiDecompose a research question into MECE subquestions with coverage and independence arguments.
- ▌ Map Validity Envelope · yogsoth-aiMap where a claim, method, or design remains valid by defining variation axes, probing systematic or adversarial/boundary values, detecting breakpoints, and constructing a multidimensional validity envelope. Critical-case selection is an optional inference-maximizing mode.
- ▌ Mine Patent Landscape · yogsoth-aiMap a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a patent provider.
- ▌ Propagate Uncertainty · yogsoth-aiPropagate input/parameter uncertainty through a model or reasoning chain to estimate output distributions, tail behavior, and uncertainty contributions.
- ▌ Quantify Resource Gap · yogsoth-aiQuantify resource demand, available supply, gap, severity, and uncertainty for a research/experiment plan.
- ▌ Run Convergence Round · yogsoth-aiRun one structured revision round that updates arguments/evidence rather than merely averaging opinions.
- ▌ Test Risky Prediction · yogsoth-aiDerive a risky/nontrivial prediction uniquely or strongly implied by an explanation and test whether available evidence supports it; distinguish post-hoc accommodation from prospective constraint.
- ▌ Validate Research Gap · yogsoth-aiTest whether an apparent gap is real, persistent, and not an evidence-acquisition artifact, keeping every candidate rejected as closed on record. Tool choice is left to the host AI.
- ▌ Analyze Scaling Regime · yogsoth-aiAnalyze how conclusions/performance change across scale and identify regime shifts, saturation, power-law/log-law behavior, or frontier transitions.
- ▌ Assess System Boundary · yogsoth-aiDefine and challenge the system boundary: what actors, processes, externalities, timescales, and value assumptions are included or excluded.
- ▌ Construct Argument Map · yogsoth-aiAtomize claims, expose premises and counterclaims, attach evidence/defeaters, score claim strength, and construct an inspectable argument graph independent of storage format.
- ▌ Construct Causal Model · yogsoth-aiConstruct and validate an explicit causal model with measurable variables, mechanism edges, evidence links, feedback loops, interventions, counterevidence, and confidence.
- ▌ Construct Input Spaces · yogsoth-aiDefine the structured input spaces for conceptual blending: entities, relations, goals, constraints, and salient dynamics in each source.
- ▌ Design Data Extraction · yogsoth-aiDefine a structured extraction form, field semantics, coding rules, and missing-data handling for evidence synthesis.
- ▌ Design Study Inclusion · yogsoth-aiDefine study inclusion/exclusion criteria and explicit rules for borderline cases.
- ▌ Enumerate Combinations · yogsoth-aiConstruct combinations across dimensions/values without prematurely judging them.
- ▌ Evaluate Compatibility · yogsoth-aiEvaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions.
- ▌ Generate Attack Vector · yogsoth-aiGenerate a concrete executable attack/probe against a chosen threat surface.
- ▌ Identify Shared Priors · yogsoth-aiTrace supposedly independent evidence/reasoning paths to shared priors, datasets, models, prompts, framings, assumptions, or upstream sources that induce correlated errors.
- ▌ Map Patent White Space · yogsoth-aiMap protected feature combinations and identify technically meaningful, plausibly unprotected white space.
- ▌ Map Research Landscape · yogsoth-aiMap candidate research fields or subfields, their maturity, competition, entry barriers, and opportunity structure. Evidence/tool acquisition is host-selected.
- ▌ Detect Feedback Loop · yogsoth-aiDetect and characterize reinforcing/balancing feedback loops, participating variables, delays, and possible breakpoints.
- ▌ Estimate Sample Size · yogsoth-aiEstimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.
- ▌ Evaluate Optionality · yogsoth-aiEvaluate the value of staging, deferral, reversible commitment, and information-gathering options under uncertainty; return decision-relevant option value and trigger conditions.
- ▌ Formulate Hypotheses · yogsoth-aiGenerate testable hypotheses from theory, empirical regularity, anomaly, or explicit explanatory competition. Deductive, inductive, abductive, and competing-hypothesis generation are modes; discriminating predictions and comparison are activated in competing mode.
- ▌ Generate Provocation · yogsoth-aiGenerate a deliberate pattern-breaking perturbation: PO, reversal, negation, random stimulus, exaggeration, or distortion.
- ▌ Instantiate Transfer · yogsoth-aiTurn an abstract transferred principle into a concrete target-domain design/mechanism.
- ▌ Map Stakeholder Jobs · yogsoth-aiRepresent stakeholder jobs, desired outcomes, pains, gains, dependencies, and conflicts relevant to the research target.
- ▌ Select Critical Case · yogsoth-aiSelect most-likely, least-likely, or otherwise inference-maximizing cases that can decisively support/refute a claim under explicit case-selection logic.
- ▌ Select From Frontier · yogsoth-aiSelect a preferred frontier point/portfolio and state the sacrificed alternatives/tradeoffs.
- ▌ Select Seed Evidence · yogsoth-aiSelect and rank high-information seed sources for iterative evidence expansion using quality, recency, relevance, and network position.
- ▌ Sensitivity Analysis · yogsoth-aiQuantify which parameters, assumptions, interactions, or uncertainties dominate the conclusion; select Morris/Sobol/perturbation/Monte-Carlo as modes.
- ▌ Specify Relationship · yogsoth-aiSpecify direction, functional form, and theoretical basis of relationships among variables.
- ▌ Validate Causal Link · yogsoth-aiAudit a causal relation for clarity, existence, sufficiency, and logical completeness using CLR-style checks.
- ▌ Analyze Heterogeneity · yogsoth-aiIdentify clinical, methodological, and statistical heterogeneity sources and prioritize subgroup/meta-regression/outlier investigation.
- ▌ Build Domain Ontology · yogsoth-aiConstruct a tool-independent domain ontology: scope the domain, atomize concepts, type relations, build hierarchy, audit consistency, detect gaps, and refine confidence.
- ▌ Classify Research Gap · yogsoth-aiClassify a candidate research gap by type (evidence, method, mechanism, population, theory, measurement, contradiction, boundary, translation, etc.) and record implications for next actions.
- ▌ Decompose And Or Goal · yogsoth-aiRecursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
- ▌ Document Counterclaim · yogsoth-aiConstruct a counterclaim, identify its target claim, contradiction type, assumptions, and supporting evidence requirements.
- ▌ Execute Research Spec · yogsoth-aiExecute the approved Research Spec phase by phase, producing checkpointed research state and a final summary.
- ▌ Extract Core Conflict · yogsoth-aiRepresent a core constraint conflict in an Evaporating-Cloud-like structure with explicit assumptions on every dependency.
- ▌ Extract Generic Space · yogsoth-aiInfer the shared abstract relational structure that is common across conceptual-blend input spaces.
- ▌ Classify Constraint · yogsoth-aiClassify constraints as hard, soft, or assumption-like after explicit identification.
- ▌ Conceptual Blending · yogsoth-aiConstruct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone.
- ▌ Construct Hierarchy · yogsoth-aiConstruct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints.
- ▌ Derive Consequences · yogsoth-aiTrace logically valid consequences from an altered premise, provocation, or negated claim.
- ▌ Detect Coverage Gap · yogsoth-aiGiven an explicit coverage representation (matrix, graph, taxonomy, IP feature space), identify absent, thin, disconnected, or weakly covered regions and characterize why they matter.
- ▌ Identify Bottleneck · yogsoth-aiIdentify the limiting dimension or dependency currently constraining progress.
- ▌ Robustness Analysis · yogsoth-aiGenerate plausible model variants and test whether conclusions converge across assumption/model choices.
- ▌ Search Minimal Flip · yogsoth-aiSearch for the smallest change to variables/assumptions/conditions that flips a target conclusion, decision, or causal claim.
- ▌ Structured Red Team · yogsoth-aiMap attack surfaces, generate attack vectors, execute probes, and aggregate weaknesses into a resilience picture.
- ▌ Surface Assumptions · yogsoth-aiEnumerate explicit and implicit assumptions in a claim, model, method, decision, or design.
- ▌ Trace Patent Family · yogsoth-aiTrace priority, family membership, forward/backward citations, and continuation relationships until relevant family structure stabilizes.
- ▌ Transform Component · yogsoth-aiApply an explicit structural/function operator such as remove, substitute, combine, divide, redirect, redistribute, or reverse.
- ▌ Write Research Spec · yogsoth-aiConvert a confirmed North Star, ResearchBrief, and user constraints into an executable multi-stage Research Spec.
- ▌ Analogical Discovery · yogsoth-aiAbstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
- ▌ Analyze Intervention · yogsoth-aiApply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.
- ▌ Appreciative Reframe · yogsoth-aiReframe a problem around functioning exceptions, existing strengths, positive deviance, and conditions under which desired behavior already occurs.
- ▌ Audit Study Validity · yogsoth-aiAudit a study against an appropriate methodological-quality and risk-of-bias rubric; return domain-level judgments, evidence, and overall confidence.
- ▌ Challenge Assumption · yogsoth-aiConstruct a strong countercase or alternative to an assumption and assess consequence if it fails.
- ▌ Characterize Anomaly · yogsoth-aiPrecisely characterize an anomaly by contrasting observation with expectation, quantifying deviation where possible, recording conditions, and excluding obvious/trivial explanations before generating hypotheses.
- ▌ Decompose Components · yogsoth-aiDecompose a system into components/functions and record dependencies relevant to transformation.
- ▌ Destructive Ideation · yogsoth-aiBreak fixation by surfacing assumptions and applying deliberate provocation modes (reversal, negation, random entry, exaggeration, extreme/zero-resource constraint, distortion), then extract constructive movement and synthesize candidate directions.
- ▌ Detect Contradiction · yogsoth-aiDetect an explicit contradiction in logical derivations, claims, or evidence relations; classify whether it is formal, empirical, scope-dependent, or unresolved.
- ▌ Abstract Structure · yogsoth-aiRemove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
- ▌ Apply Perturbation · yogsoth-aiApply a controlled change to an assumption, factor, component, parameter, or condition and record response.
- ▌ Assess Sensitivity · yogsoth-aiPerturb a specified input, assumption, model choice, analysis choice, or weight and measure sensitivity of a specified output; report convergence/instability, unstable regions, and dominant drivers.
- ▌ Compare Hypotheses · yogsoth-aiBuild an explicit comparison matrix over hypotheses, predictions, and evidence.
- ▌ Construct Critique · yogsoth-aiConstruct the strongest structured attack on a claim/artifact, grounded in explicit reasons/evidence.
- ▌ Construct Scenario · yogsoth-aiConstruct a scenario across key uncertainties with explicit assumptions and plausibility. Modes include baseline/narrative, counterfactual, and extreme-but-plausible worst-case with breaking point, failure cascade, recovery assumptions, and distinguishing observables.
- ▌ Decompose Ishikawa · yogsoth-aiBuild an Ishikawa-style causal decomposition across relevant cause families.
- ▌ Fmea Risk Analysis · yogsoth-aiEnumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.
- ▌
- ▌ Map Coverage Space · yogsoth-aiMap a set of methods/assets/evidence items against a typed problem, capability, condition, or design space to expose redundancy, coverage structure, and the strength of support in each occupied region.
- ▌ Map Threat Surface · yogsoth-aiEnumerate attackable dimensions of an artifact and rate exposure/accessibility.
- ▌ Parse Patent Claim · yogsoth-aiParse independent/dependent claim structure, extract elements, and map claim features to technical functions/domains.
- ▌ Rotate Perspective · yogsoth-aiApply one perspective at a time to reinterpret the same target while holding the underlying evidence/object fixed; record changed assumptions, objectives, risks, and opportunities.
- ▌ Specify Boundaries · yogsoth-aiState applicability assumptions, scope, and known boundary conditions.
- ▌ Trace Causal Chain · yogsoth-aiTrace ordered causal chains including intermediate nodes, branches, and loops with explicit because/mechanism links.
- ▌ Validate Goal Tree · yogsoth-aiCheck leaf specificity, testability, coverage of the parent goal, logical completeness, and dependency consistency.