abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Represent where perspectives/arguments agree, disagree, and why.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-disagreement --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/map-disagreementContext preview
The summary Claude sees to decide when to auto-load this skill.
Represent where perspectives/arguments agree, disagree, and why.
name: map-disagreement description: "Represent where perspectives/arguments agree, disagree, and why."
Represent where perspectives or arguments agree, disagree, and why.
required: [perspectives, claims_or_arguments, comparison_dimensions] optional: [evidence, clustering_rule, convergence_measure] constraints: [agreement and disagreement are tied to the same proposition and comparison dimension; preserve minority positions]
1. Normalize perspectives, propositions, and evidence. 2. Cluster equivalent positions and separate agreement from disagreement. 3. Attribute each disagreement to evidence, assumptions, scope, values, or definitions. 4. Report convergence trends and unresolved fault lines.
produces: [agreement_map, disagreement_register, cluster_arguments, convergence_trends] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
The caller must provide perspective schema, proposition identity, comparison dimensions, agreement rule, disagreement rule, evidence links, and the population represented by any percentages.
Reject comparisons across different propositions or scopes, and reject consensus claims when the denominator of perspectives is absent.
| source | physical line | kind | source criterion | |---|---:|---|---| | stress-test/divergence-detection | 14 | percentage | Consensus is >70%; disagreement is >50%; identify convergence trends. |
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.