abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Construct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill conceptual-blending --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/conceptual-blendingContext preview
The summary Claude sees to decide when to auto-load this skill.
Construct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone.
name: conceptual-blending description: "Construct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone."
Blend multiple input spaces through a generic space and selective projection to generate emergent research ideas.
mode_contracts:
two-space-blend: &blending_input
required: [input_spaces]
optional: [compatibility_constraints]
constraints: [each_input_space_must_have_explicit_entities_and_relations]
multi-space-blend: *blending_input
emergent-property-search: *blending_inputDo not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `construct-input-spaces` to construct the input spaces. 2. You MUST load skill `extract-generic-space` to extract the generic space. 3. You MUST load skill `simulate-emergent-properties` to simulate emergent properties. 4. You MUST load skill `evaluate-compatibility` to check compatibility. 5. You MUST load skill `synthesize-idea` to synthesize the blend. If the blend should be explored across a systematic combination space, consider `explore-dimensional-space`. If its claimed structural transfer needs formal testing, consider `audit-structural-equivalence`. Deviation: two-space and multi-space modes change only the number of inputs; generic-space extraction is mandatory.
mode_contracts:
two-space-blend: &space_blend_output
produces: [input_space_set, generic_space, blend_candidates, idea_set]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]
multi-space-blend: *space_blend_output
emergent-property-search:
produces: [input_space_set, blend_candidates, emergent_property_report, idea_set]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]Reject mere juxtaposition, unsupported emergence claims, and blends with unresolved relation conflicts.
Append source-space changes, projected relations, emergence claims, compatibility findings, and selected ideas.
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.