All authors
Claude Skills by yogsoth-ai
github.com/yogsoth-ai1,223 skills7 installs1,449 views
- Design Discriminating PredictionConstruct a prediction that yields different outcomes under competing hypotheses.Votes: 0GitHub stars: 499
- Design ExperimentTranslate a falsifiable hypothesis into a statistically defensible experiment. Factorial, ablation, comparison, scaling, and robustness designs are modes, not strategy nodes.Votes: 0GitHub stars: 499
- Design Falsification TestSpecify a concrete observation, computation, intervention, counterexample, or measurement that would count against the sharpened claim, prioritizing cheap high-information tests.Votes: 0GitHub stars: 499
- Design MitigationDesign an intervention that prevents, detects, responds to, removes, or relaxes a failure mode/constraint; state residual risk and validation evidence.Votes: 0GitHub stars: 499
- Design Randomness ProtocolIdentify randomness sources and define seed/repetition/propagation rules sufficient for the intended reproducibility level.Votes: 0GitHub stars: 499
- Design Study InclusionDefine study inclusion/exclusion criteria and explicit rules for borderline cases.Votes: 0GitHub stars: 499
- Destructive IdeationBreak 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.Votes: 0GitHub stars: 499
- Detect BreakpointLocate the point or region where performance/validity changes regime or the claim flips.Votes: 0GitHub stars: 499
- Detect ContradictionDetect an explicit contradiction in logical derivations, claims, or evidence relations; classify whether it is formal, empirical, scope-dependent, or unresolved.Votes: 0GitHub stars: 499
- Detect Coverage GapGiven an explicit coverage representation (matrix, graph, taxonomy, IP feature space), identify absent, thin, disconnected, or weakly covered regions and characterize why they matter.Votes: 0GitHub stars: 499
- Detect Feedback LoopDetect and characterize reinforcing/balancing feedback loops, participating variables, delays, and possible breakpoints.Votes: 0GitHub stars: 499
- Detect Pass By ConstructionIdentify cases where the validator is structurally unable to reject the target because acceptance follows from assumptions copied from the target theory or construction process.Votes: 0GitHub stars: 499
- Detect Performance DiscrepancyDetect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences.Votes: 0GitHub stars: 499
- Discover Biological AnalogIdentify biological systems that achieve the target function under comparable constraints, without assuming surface similarity.Votes: 0GitHub stars: 499
- Document CounterclaimConstruct a counterclaim, identify its target claim, contradiction type, assumptions, and supporting evidence requirements.Votes: 0GitHub stars: 499
- Downgrade Equivalence ClaimWhen full equivalence fails, downgrade to the strongest defensible relation (e.g. substructure, homomorphism, shared invariant, analogy) and record exactly what ceased to be preserved.Votes: 0GitHub stars: 499
- Drill Five WhysIteratively ask why, evidence-checking each causal step, to move from symptom toward root cause.Votes: 0GitHub stars: 499
- Drill Root CausesMove from symptoms to causal structure using complementary root-cause representations and causal-validity checks.Votes: 0GitHub stars: 499
- Elicit WeightsProduce a normalized criterion-weight vector using a selected elicitation method.Votes: 0GitHub stars: 499
- Enumerate CombinationsConstruct combinations across dimensions/values without prematurely judging them.Votes: 0GitHub stars: 499
- Enumerate Dimension ValuesEnumerate meaningful values/levels for a dimension or factor. Mode controls representative, experimental, boundary, pathological, or adversarial coverage.Votes: 0GitHub stars: 499
- Enumerate Failure ModesConvert functions/process steps/scenarios into explicit failure modes.Votes: 0GitHub stars: 499
- Enumerate Validator AssumptionsEnumerate assumptions embedded in a validator/test/sandbox, including data-generation, measurement, simulator, oracle, metric, initialization, and acceptance assumptions.Votes: 0GitHub stars: 499
- Establish Empirical BaselineEstablish a fair empirical baseline by inventorying methods, extracting comparable performance, normalizing conditions/compute, checking discrepancies, and estimating progress/headroom.Votes: 0GitHub stars: 499
- Estimate Effective Evidence CountEstimate an effective number of independent evidence/reasoning paths after discounting dependence/correlation; report nominal N, dependence structure, and N_eff.Votes: 0GitHub stars: 499
- Estimate Performance HeadroomEstimate practical/human/theoretical ceilings and remaining performance headroom under stated assumptions.Votes: 0GitHub stars: 499
- Estimate Sample SizeEstimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.Votes: 0GitHub stars: 499
- Evaluate CompatibilityEvaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions.Votes: 0GitHub stars: 499
- Evaluate FalsifiabilityDetermine what observation would falsify a hypothesis and flag unfalsifiable formulations.Votes: 0GitHub stars: 499
- Evaluate Necessity SufficiencyTest whether a proposed cause/mechanism is necessary and/or sufficient under controlled counterfactual or intervention comparisons.Votes: 0GitHub stars: 499
- Evaluate OptionalityEvaluate the value of staging, deferral, reversible commitment, and information-gathering options under uncertainty; return decision-relevant option value and trigger conditions.Votes: 0GitHub stars: 499
- Evaluate Scenario ImpactEvaluate a fixed candidate, research path, or portfolio under one explicit scenario using stable criteria and return impact, tradeoffs, and failure triggers.Votes: 0GitHub stars: 499
- Evaluate Scenario RobustnessAggregate a candidate, strategy, or portfolio across explicit scenarios under a declared robust-decision rule such as worst-case score, minimax regret, maximin, threshold survival, or pivot-trigger analysis.Votes: 0GitHub stars: 499
- Evolve Solution PopulationMaintain a diverse population of candidate solutions, mutate/recombine variants, select under explicit fitness and novelty criteria, and iterate while preserving useful niches rather than collapsing prematurely to one winner.Votes: 0GitHub stars: 499
- Execute ProbeExecute one test/attack and record outcome, evidence, and severity. Tool use is runtime-selected.Votes: 0GitHub stars: 499
- Execute Research SpecExecute the approved Research Spec phase by phase, producing checkpointed research state and a final summary.Votes: 0GitHub stars: 499
- Explore Dimensional SpaceRepresent a problem/research space as validated dimensions and values, enumerate compatible combinations, and optionally map occupancy, detect gaps, prioritize regions, or synthesize candidate questions/ideas.Votes: 0GitHub stars: 499
- Extract Biological StrategyExtract the causal strategy/mechanism by which a biological analog achieves its function, including boundary conditions and trade-offs.Votes: 0GitHub stars: 499
- Extract Causal StructureExtract causal structure from source material at requested granularity: individual causal claims, ordered mechanism chains, mediators, assumptions, and stated boundary conditions.Votes: 0GitHub stars: 499
- Extract ConceptsExtract candidate concepts from evidence with explicit source provenance and precision/recall posture.Votes: 0GitHub stars: 499
- Extract Constructive MovementConvert an initially absurd/destructive provocation into concrete useful directions.Votes: 0GitHub stars: 499
- Extract Core ConflictRepresent a core constraint conflict in an Evaporating-Cloud-like structure with explicit assumptions on every dependency.Votes: 0GitHub stars: 499
- Extract Empirical RegularityExtract a repeatable empirical pattern from observations, state its support and exceptions, and generalize cautiously without importing an unsupported mechanism.Votes: 0GitHub stars: 499
- Extract Evaluation ProtocolExtract evaluation-protocol elements from a source and mark unstated or ambiguous parameters.Votes: 0GitHub stars: 499
- Extract Evidence RecordExtract a schema-declared evidence record from a source, including methods, datasets, metrics/results, conditions, limitations, provenance, and explicitly missing/ambiguous fields.Votes: 0GitHub stars: 499
- Extract Generic SpaceInfer the shared abstract relational structure that is common across conceptual-blend input spaces.Votes: 0GitHub stars: 499
- Extract Structural MappingConstruct an explicit source↔target mapping over objects, relations, operations, constraints, and invariants for a claimed structural equivalence.Votes: 0GitHub stars: 499
- Falsification First AuditConvert a sharp scientific claim into the cheapest decisive falsification program. Steelman the claim into a precise testable form, specify observations/computations that could break it, execute the most informative probes first, and return only BROKEN, CORROBORATED, or UNFALSIFIABLE rather than a resilience score.Votes: 0GitHub stars: 499
- Filter False GapDistinguish a real knowledge gap from search failure, questions that prior work closes, and intrinsically unanswerable formulations. Prior work that touches a question without closing it leaves the gap open.Votes: 0GitHub stars: 499
- Fmea Risk AnalysisEnumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.Votes: 0GitHub stars: 499