abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Generate a plausible model variant by relaxing, replacing, or generalizing assumptions.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-alternative-model --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/generate-alternative-modelContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate a plausible model variant by relaxing, replacing, or generalizing assumptions.
name: generate-alternative-model description: "Generate a plausible model variant by relaxing, replacing, or generalizing assumptions."
Generate a plausible model variant by relaxing, replacing, or generalizing assumptions.
required: [base_model, load_bearing_assumptions] optional: [observations, model_constraints, variant_operations] constraints: [each variant names the changed assumption and retained predictions]
1. Identify assumptions that constrain the base model. 2. Relax, replace, or generalize one assumption at a time. 3. Re-derive the model structure and compare predictions or implications.
produces: [model_variants, changed_assumptions, prediction_comparison] delta_fields: [findings, hypothesis_updates, uncertainties, decisions]
Reject variants that change multiple assumptions without attribution or that cannot produce testable implications.
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.