abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Map known methods against problem/parameter space and generate candidates from uncovered and weakly covered intersections. Acquisition mechanism is runtime-selected.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill coverage-white-space-search -a windsurf -y
name: coverage-white-space-search description: "Map known methods against problem/parameter space and generate candidates from uncovered and weakly covered intersections. Acquisition mechanism is runtime-selected."
Map known methods against a problem space and generate candidates from intersections that are uncovered or covered without being closed.
required: [reference_items, coverage_dimensions] optional: [performance_records, eligibility_rules] constraints: [reference items and dimension values must be identifiable]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `inventory-reference-items` to inventory references. 2. You MUST load skill `map-coverage-space` to map coverage and grade its strength. 3. You MUST load skill `detect-coverage-gap` to detect uncovered and weakly covered regions. 4. You MUST load skill `synthesize-idea` to synthesize candidates. If a candidate gap is ready to become a testable explanation, consider `formulate-hypotheses`. If the gap itself still requires evidence validation, consider `validate-research-gap`. Deviation: acquisition is runtime-selected; do not infer coverage from missing records.
produces: [reference_inventory, coverage_map, white_space_gaps, candidate_ideas] delta_fields: [findings, evidence_updates, hypothesis_updates, decisions, open_questions]
Do not label a region white space when it is merely unsearched, incomparable, or outside the declared universe, and do not treat a region as closed because items occupy it.
Append inventory additions, occupied cells with strength grades, gap definitions, exclusions, and generated candidates.
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…