abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Identify approximately independent dimensions/axes that span the relevant problem, design, or validity space and define their semantics.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-analysis-dimensions --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/define-analysis-dimensionsContext preview
The summary Claude sees to decide when to auto-load this skill.
Identify approximately independent dimensions/axes that span the relevant problem, design, or validity space and define their semantics.
name: define-analysis-dimensions description: "Identify approximately independent dimensions/axes that span the relevant problem, design, or validity space and define their semantics."
Define approximately independent, measurable axes that span a problem, design, or validity space.
required: [problem_or_artifact, target_outcome, dimension_ontology] optional: [candidate_axes, domain_constraints, measurement_plan] constraints: [each axis has semantics, type, direction, and measurement rule; correlated axes are flagged]
1. Extract factors and conditions relevant to the target outcome. 2. Group candidates into dimensions and test approximate independence. 3. Define each dimension's domain, units, direction, and observability. 4. Return the dimension set with exclusions and unresolved dependencies.
If each analysis dimension has a clear meaning and admissible type, consider `enumerate-dimension-values` as the next tactic.
produces: [dimension_set, axis_definitions, independence_notes, coverage_scope] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
The caller must provide the target problem, outcome, axis ontology, candidate factors, domain bounds, measurement units, and independence criterion.
Reject duplicate axes, dimensions with no observable values, or an independence claim unsupported by a comparison.
| source | physical line | kind | source criterion | |---|---:|---|---| | deep-insight/variation-axis-definition | 14 | structural | Identify orthogonal axes, ensuring they are independent, measurable, and span the parameter space. |
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.