abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill evaluate-compatibility --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/evaluate-compatibilityContext preview
The summary Claude sees to decide when to auto-load this skill.
Evaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions.
name: evaluate-compatibility description: "Evaluate logical/empirical/normative compatibility of a candidate combination and prune invalid regions."
Evaluate logical, empirical, and normative compatibility of a candidate combination and prune invalid regions.
required: [candidate_combination, component_schema, compatibility_rules, evidence] optional: [matrix, consistency_judgments, feasibility_criteria, novelty_criteria] constraints: [each incompatibility is tied to an explicit rule or evidence item; preserve distinct logical, empirical, and normative judgments]
1. Normalize the combination and component schemas. 2. Apply each compatibility rule pairwise and at the full-combination level. 3. Record conflicts, supporting evidence, and unresolved judgments. 4. Prune only combinations that violate an explicit rule; retain near-boundary cases with rationale. 5. Return surviving combinations and a compatibility report.
produces: [surviving_combinations, incompatibility_register, compatibility_judgments, pruning_rationale] delta_fields: [findings, evidence_updates, decisions, uncertainties]
The caller must provide component/object schemas, the combination representation, compatibility dimensions and rules, evidence for each judgment, and whether the decision is logical, empirical, normative, or mixed. If CCA is used, provide the full matrix and pairwise consistency judgments.
Reject when compatibility rules are absent, evidence is untraceable, or a normative preference is presented as a logical contradiction. Do not remove a combination solely because it is unfamiliar.
| source | physical line | kind | source criterion | |---|---:|---|---| | creative-ideation/solution-space-reduction | 11 | gate | Apply CCA to remove inconsistent combinations from the supplied matrix using consistency judgments. | | creative-ideation/combination-evaluation | 11 | gate | Evaluate proposed combinations for feasibility, novelty, and implementation difficulty. |
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.