abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Map a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a patent provider.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill mine-patent-landscape -a windsurf -y
name: mine-patent-landscape description: "Map a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a patent provider."
Map a patent landscape using families, classifications, assignees, filing dynamics, quality, and technical-domain coverage without prescribing a provider.
required: [technical_domain, jurisdiction_scope, patent_records] optional: [seed_families, assignee_schema, time_window] constraints: [family identity, classification, assignee, date, and source provenance must be retained]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `trace-patent-family` to trace priority, family, and citation relationships. 2. You MUST load skill `navigate-patent-classification` to expand or delimit the technical neighborhood. 3. You MUST load skill `canonicalize-entity` to canonicalize assignees and entities. 4. You MUST load skill `analyze-temporal-trajectory` to analyze filing dynamics and temporal regimes. 5. You MUST load skill `detect-coverage-gap` to identify coverage gaps. You MUST load skill `analyze-patent-citation-network` to analyze the citation structure. If the landscape is ready for claim-level white-space analysis, consider `map-patent-white-space` as the next tactic.
Deviation: Skip entity canonicalization when records already carry a stable canonical key. Skip temporal analysis when no time field exists, and mark the missing dimension instead of imputing it.
produces: [patent_family_map, classification_neighborhood, assignee_profile, filing_trajectory, coverage_gaps, citation_network] delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
Do not count family members as independent inventions, equate assignee name variants without provenance, or treat an uncited classification gap as unprotected space.
| source | source line | kind | source criterion | |---|---:|---|---| | none retained | - | - | No source numeric/textual criterion retained after normalization. |
Append family deduplication, classification paths, canonical entities, trajectory observations, gap cells, citation links, and unresolved records.
A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.
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,…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target,…
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.
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…