abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Distinguish a real knowledge gap from search failure, questions that prior work closes, and intrinsically unanswerable formulations. Prior work that touches a question without closing it leaves the gap open.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill filter-false-gap -a windsurf -y
name: filter-false-gap description: "Distinguish a real knowledge gap from search failure, questions that prior work closes, and intrinsically unanswerable formulations. Prior work that touches a question without closing it leaves the gap open."
Distinguish a real knowledge gap from search failure, closed questions, or unanswerable formulations, judging prior work by whether it closes the question rather than by whether it exists.
required: [gap_claim, search_record, evidence_scope] optional: [prior_findings, answerability_constraints] constraints: [absence claims must be tied to a declared search and scope; a closure verdict cites the work that closes the question]
1. Check whether the search covered the declared evidence scope. 2. Compare the claim with prior findings. Prior work closes the question only when it is independently replicated, measures the construct directly, holds across the scope the claim names, and faces no unresolved contrary result; name each condition that fails and the work it applies to. 3. For a region no prior work touches, state why it is empty: unsearched, incoherent as a combination, unmeasurable, infeasible to study, or open. 4. Test whether the formulation is answerable under stated constraints. 5. Label `open`, `touched_not_closed`, `search_failure`, `resolved`, or `unanswerable` with rationale.
produces: [gap_verdict, search_adequacy, closure_assessment, answerability_note] delta_fields: [findings, evidence_updates, uncertainties, decisions]
Do not confirm a gap from an under-scoped search, reject a gap merely because evidence is inconvenient, or treat publication in a region as closure of its question.
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…