abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Map protected feature combinations and identify technically meaningful, plausibly unprotected white space.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-patent-white-space --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/map-patent-white-spaceContext preview
The summary Claude sees to decide when to auto-load this skill.
Map protected feature combinations and identify technically meaningful, plausibly unprotected white space.
name: map-patent-white-space description: "Map protected feature combinations and identify technically meaningful, plausibly unprotected white space."
Map protected feature combinations and identify technically meaningful, plausibly unprotected white space.
required: [patent_records, feature_schema, jurisdiction_scope] optional: [claim_element_maps, family_map, technical_constraints] constraints: [feature provenance and claim scope must be retained, unprotected means not evidenced as protected within the declared scope]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `parse-patent-claim` to parse claims into comparable elements. 2. You MUST load skill `trace-patent-family` to align family and jurisdiction evidence. 3. You MUST load skill `detect-coverage-gap` to identify absent, thin, or disconnected feature combinations.
Deviation: If claim records are already normalized, reuse them and skip reparsing. If family evidence is incomplete, label the white-space candidate provisional rather than treating absence as freedom to operate.
produces: [feature_cross_matrix, protected_combinations, white_space_candidates, coverage_uncertainties] delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
Do not infer unprotected status from an empty search result, a single family, or an unmatched synonym. Preserve alternative feature decompositions when the claim language is ambiguous.
| source | source line | kind | source criterion | |---|---:|---|---| | none retained | - | - | No source numeric/textual criterion retained after normalization. |
Append feature cells, cited claims, family/jurisdiction coverage, candidate gaps, and unresolved interpretation questions.
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.