abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Audit a research question for scope and FINER-style quality; return targeted repairs.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality -a windsurf -y
name: assess-question-quality description: "Audit a research question for scope and FINER-style quality; return targeted repairs."
Assess whether a research question is clear, focused, answerable, relevant, and appropriately scoped.
required: [research_question, intended_use] optional: [constraints, evidence_context, stakeholder_needs] constraints: [each quality judgment requires a criterion and textual evidence]
1. Evaluate clarity, focus, answerability, relevance, and scope fit. 2. Identify ambiguity, hidden assumptions, and unbounded terms. 3. Propose the smallest wording changes that resolve material defects. 4. Return a scored or categorical assessment with unresolved issues.
produces: [quality_assessment, criterion_evidence, revision_candidates, unresolved_issues] delta_fields: [findings, decisions, uncertainties, open_questions]
Do not reward complexity as rigor or call a question answerable when its outcome cannot be observed.
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…