abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Infer the shared abstract relational structure that is common across conceptual-blend input spaces.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill extract-generic-space -a windsurf -y
name: extract-generic-space description: "Infer the shared abstract relational structure that is common across conceptual-blend input spaces."
Infer the shared abstract relational structure common across conceptual-blend input spaces.
required: [input_space_set] optional: [candidate_relations, blend_goal] constraints: [generic relations must be present in at least two input spaces]
1. Compare roles and relations across the input spaces. 2. Keep only shared structure and mark source-specific attributes. 3. Validate the generic space against the blend goal before projection.
If the generic space supports a coherent candidate blend, consider `simulate-emergent-properties` as the next tactic.
produces: [generic_space, shared_relations, excluded_attributes] delta_fields: [findings, hypothesis_updates, uncertainties]
Return no generic space when the inputs share only vocabulary or when relation alignment is ambiguous.
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…