abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Audit a claimed isomorphism/equivalence by constructing an explicit mapping, testing which structures/operations/invariants are preserved, searching counterexamples, and downgrading the claim to the strongest defensible relation when full isomorphism fails.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill audit-structural-equivalence --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/audit-structural-equivalenceContext preview
The summary Claude sees to decide when to auto-load this skill.
Audit a claimed isomorphism/equivalence by constructing an explicit mapping, testing which structures/operations/invariants are preserved, searching counterexamples, and downgrading the claim to the strongest defensible relation when full isomorphism fails.
name: audit-structural-equivalence description: "Audit a claimed isomorphism/equivalence by constructing an explicit mapping, testing which structures/operations/invariants are preserved, searching counterexamples, and downgrading the claim to the strongest defensible relation when full isomorphism fails."
Audit a claimed isomorphism or equivalence and downgrade it to the strongest defensible relation when preservation fails.
mode_contracts:
isomorphism: &structural_audit_input
required: [source_structure, target_structure, equivalence_claim]
optional: [required_invariants, operations, constraints]
constraints: [mapping_domains_and_preservation_obligations_must_be_explicit]
substructure: *structural_audit_input
homomorphism: *structural_audit_input
shared-invariant: *structural_audit_input
analogy: *structural_audit_inputDo not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `extract-structural-mapping` to construct the object, relation, operation, and invariant mapping. 2. You MUST load skill `test-structure-preservation` to test preservation. You MUST load skill `generate-counterexample` to search minimal counterexamples. 3. You MUST load skill `downgrade-equivalence-claim` to downgrade the claim and record lost invariants. Deviation: if the claim is only analogy by scope, run the analogy branch and do not report isomorphism.
mode_contracts:
isomorphism: &structural_audit_output
produces: [claimed_sides, maps_attempted, monsters_found, dimension_count_result, highest_defended_rung, required_wording_change]
delta_fields: [findings, evidence_updates, uncertainties, decisions]
substructure: *structural_audit_output
homomorphism: *structural_audit_output
shared-invariant: *structural_audit_output
analogy: *structural_audit_outputDo not infer equivalence from surface similarity. Exclusions introduced only after a counterexample are ad hoc unless independently justified.
| source | source line | kind | source criterion | |---|---:|---|---| | v4 architecture | node desc | textual | Preserve structures/operations/invariants; downgrade when full equivalence fails. |
Append mapping, tested invariants, counterexamples, and final relation.
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.