abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analogical-discovery -a windsurf -y
name: analogical-discovery description: "Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms."
Transfer a validated relational structure from a source domain into a target research problem.
required: [target_problem, source_domain] optional: [candidate_sources, transfer_constraints] constraints: [source and target roles must be explicit]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `abstract-structure` to abstract the relational structure. 2. You MUST load skill `map-analogy` to map source relations to the target. 3. You MUST load skill `instantiate-transfer` to instantiate and test the transferred mechanism. If the analogy should be expanded across a typed combination space, consider `explore-dimensional-space`. If biological mechanisms are the relevant source domain, consider `biomimetic-transfer`. If several source structures must be composed, consider `conceptual-blending`. If the claimed mapping requires a formal preservation audit, `audit-structural-equivalence` may be the better next tactic. Deviation: skip source search only when a supplied source is structurally specified; never skip mapping or transfer validation.
produces: [abstract_structure, structural_mapping, transfer_candidate] delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]
Reject transfers whose causal/relational roles do not map, whose target constraints are violated, or whose claimed mechanism is only lexical resemblance.
Append source relations, mapping gaps, transfer assumptions, and validation findings.
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.
Characterize what blocks a research target: readiness dimensions, obstacles, bottlenecks, resource gaps, causal constraints,…
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…