abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Represent a problem/research space as validated dimensions and values, enumerate compatible combinations, and optionally map occupancy, detect gaps, prioritize regions, or synthesize candidate questions/ideas.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill explore-dimensional-space -a windsurf -y
name: explore-dimensional-space description: "Represent a problem/research space as validated dimensions and values, enumerate compatible combinations, and optionally map occupancy, detect gaps, prioritize regions, or synthesize candidate questions/ideas."
Represent a problem space as validated dimensions and values, enumerate compatible combinations, map occupancy, detect gaps, and synthesize candidate questions or ideas.
mode_contracts:
morphological-generation: &dimensional_input
required: [target_space, dimensions, values]
optional: [coverage_matrix, compatibility_rules, objective]
constraints: [dimension_semantics_and_independence_posture_must_be_declared]
research-space-mapping: *dimensional_input
gap-mapping: *dimensional_inputDo not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `define-analysis-dimensions` to define the exploration axes. You MUST load skill `enumerate-dimension-values` to enumerate meaningful values. 2. Apply the selected mode's combination, compatibility, and coverage operations. 3. Retain axis dependencies and uncovered regions exposed by the selected mode. 4. When the task is not descriptive mapping, You MUST load skill `score-object` to score the retained regions. When a research question is in scope, You MUST load skill `generate-subquestions` to derive questions from those regions. If deliberate disruption is needed to escape the declared axes, consider `destructive-ideation`. If the main objective becomes systematic coverage repair, `coverage-white-space-search` may be the better next tactic. Deviation: skip scoring when the task is descriptive mapping; skip subquestions when no research question is in scope.
mode_contracts:
morphological-generation:
produces: [dimension_schema, value_catalog, combination_map, compatibility_report]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions, recommended_jumps]
research-space-mapping:
produces: [dimension_schema, value_catalog, coverage_gaps, prioritized_regions, subquestions]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions, recommended_jumps]
gap-mapping:
produces: [coverage_gaps, prioritized_regions, subquestions]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties, decisions, recommended_jumps]Do not call a sparse matrix a white space until compatibility and coverage semantics are checked. Merge redundant axes rather than double-counting them.
| source | source line | kind | source criterion | |---|---:|---|---| | v4 architecture | node desc | textual | Enumerate compatible combinations, validate axes, map occupancy and detect gaps. |
Append dimensions, values, combinations, pruned regions, gaps, scores, and derived questions.
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…