abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Build an explicit comparison matrix over hypotheses, predictions, and evidence.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill compare-hypotheses --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/compare-hypothesesContext preview
The summary Claude sees to decide when to auto-load this skill.
Build an explicit comparison matrix over hypotheses, predictions, and evidence.
name: compare-hypotheses description: "Build an explicit comparison matrix over hypotheses, predictions, and evidence."
Compare competing hypotheses against shared evidence, predictions, assumptions, and explanatory scope.
required: [hypotheses, evidence_records, comparison_criteria] optional: [priors, discriminating_predictions, model_constraints] constraints: [criteria and evidence must be applied symmetrically]
1. Normalize hypotheses to comparable claims and assumptions. 2. Map each hypothesis to predictions and supporting or conflicting evidence. 3. Compare explanatory coverage, residual anomalies, and required assumptions. 4. Record relative support and evidence that would change the comparison.
produces: [hypothesis_comparison, prediction_matrix, support_profile, discriminating_evidence] delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]
Do not choose the simplest-sounding hypothesis without comparing predictive adequacy and assumptions.
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.