abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Identify theories relevant to a gap and characterize their applicability. Evidence acquisition is not prescribed.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-theory -a windsurf -y
name: identify-theory description: "Identify theories relevant to a gap and characterize their applicability. Evidence acquisition is not prescribed."
Identify the theory or theoretical family that best organizes a claim, mechanism, or observed regularity.
required: [claim_or_mechanism, construct_definitions, evidence_context] optional: [candidate_theories, domain_scope] constraints: [theory identification requires construct and mechanism correspondence]
1. Extract constructs, relations, boundary conditions, and explanatory target. 2. Compare candidate theories by construct mapping and predicted relations. 3. Record supporting, conflicting, and missing evidence for each mapping. 4. State the selected theory or unresolved alternatives with scope limits.
produces: [theory_candidates, construct_mapping, relation_mapping, theory_assessment, scope_limits] delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]
Do not infer theoretical identity from shared vocabulary or force a theory when only a local mechanism is supported.
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…