abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-patent-citation-network --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/analyze-patent-citation-networkContext preview
The summary Claude sees to decide when to auto-load this skill.
Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies.
name: analyze-patent-citation-network description: "Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies."
Analyze patent citation and family relationships to identify central prior art, lineages, clusters, bridge patents, and citation anomalies.
required: [patent_records, citation_edges, family_keys] optional: [classification_schema, assignee_keys, time_window] constraints: [edge direction, source, jurisdiction, and date must be retained]
1. Deduplicate patents and family members while preserving jurisdictional edges. 2. Build directed citation and priority/family graphs. 3. Identify central, bridging, clustered, and anomalous records. 4. Interpret technical lineage with classification and source evidence.
produces: [citation_graph, lineage_map, cluster_summary, bridge_patents, anomaly_report] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
Do not equate citation count with technical importance, and do not infer absence of prior art from an incomplete graph.
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.