abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Decompose compound concepts into atomic, non-overlapping concepts while preserving parent/part relationships.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill atomize-concept -a windsurf -y
name: atomize-concept description: "Decompose compound concepts into atomic, non-overlapping concepts while preserving parent/part relationships."
Split a broad concept into definitional facets and distinguishable subconstructs.
required: [concept_definition, domain_context] optional: [theory, neighboring_concepts, examples] constraints: [facets must be non-duplicate and retain the parent concept boundary]
1. Extract the concept's necessary, typical, and optional properties. 2. Separate facets by mechanism, function, level, or context. 3. Compare neighboring concepts and mark overlaps or gaps. 4. Emit a facet hierarchy with definitions and boundary examples.
If the atomic concepts are stable enough to connect semantically, consider `type-relation` as the next tactic.
produces: [concept_facets, facet_definitions, overlap_map, boundary_examples] delta_fields: [findings, uncertainties, open_questions]
Do not treat synonyms as distinct facets or split a concept solely by examples.
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…