abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Decompose a research question into MECE subquestions with coverage and independence arguments.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-subquestions --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/generate-subquestionsContext preview
The summary Claude sees to decide when to auto-load this skill.
Decompose a research question into MECE subquestions with coverage and independence arguments.
name: generate-subquestions description: "Decompose a research question into MECE subquestions with coverage and independence arguments."
Decompose a research question into MECE subquestions with coverage and independence arguments.
required: [main_research_question, scope_statement] optional: [evidence_map, dependency_constraints, desired_granularity] constraints: [question must be scoped and complex enough to decompose]
1. Parse the main question into objects, mechanisms, conditions, and outcomes. 2. Generate candidate subquestions and assign coverage domains. 3. Remove overlap, test independence, and map dependencies. 4. Return the MECE set with unresolved gaps.
produces: [subquestion_set, coverage_map, independence_arguments, dependency_notes] delta_fields: [findings, open_questions, uncertainties]
Caller supplies question schema, scope test, MECE policy, granularity, and dependency representation.
Reject decompositions that merely restate the main question or leave domains without a coverage rationale.
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.