abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Audit pairwise/ranking coherence and identify inconsistent cycles/triads.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-ranking-consistency --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/assess-ranking-consistencyContext preview
The summary Claude sees to decide when to auto-load this skill.
Audit pairwise/ranking coherence and identify inconsistent cycles/triads.
name: assess-ranking-consistency description: "Audit pairwise/ranking coherence and identify inconsistent cycles/triads."
Audit pairwise and aggregate rankings for incoherent cycles, reversals, and unsupported rank transitions.
required: [ranked_items, pairwise_judgments, comparison_criteria] optional: [weights, tie_policy, prior_consistency_report] constraints: [judgments identify compared items, direction, confidence, and criterion]
1. Reconstruct the directed comparison graph and normalize ties and missing edges. 2. Search triads and longer cycles for violations of declared transitivity or criterion direction. 3. Compare aggregate order with its supporting pairwise judgments and flag reversals or low-support placements. 4. Return inconsistency records, affected items, and the minimum judgments requiring review.
produces: [comparison_graph, inconsistency_records, review_set] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
Do not call a sparse graph inconsistent merely because it lacks a comparison. Distinguish missing edges from contradictory edges.
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.