abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Generate mechanism-distinct explanations rather than superficial paraphrases.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-competing-hypotheses --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/generate-competing-hypothesesContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate mechanism-distinct explanations rather than superficial paraphrases.
name: generate-competing-hypotheses description: "Generate mechanism-distinct explanations rather than superficial paraphrases."
Generate distinct, testable hypotheses that explain a target observation or research problem.
required: [problem_statement, observations, scope_constraints] optional: [existing_theories, analogies, anomaly_records] constraints: [each hypothesis must imply a differentiating prediction or assumption]
1. Extract the target phenomenon and unresolved explanatory gap. 2. Generate mechanismally distinct explanations, including a null or status-quo hypothesis. 3. Translate each explanation into predictions, assumptions, and disconfirming observations. 4. Deduplicate equivalent explanations and retain the comparison set.
If competing hypotheses have explicit predictions and evidence links, consider `score-object` as the next tactic.
produces: [hypothesis_set, mechanism_descriptions, prediction_set, assumption_register] delta_fields: [hypothesis_updates, uncertainties, open_questions, recommended_jumps]
Do not generate unfalsifiable narratives or discard inconvenient hypotheses before comparison.
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.