abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Construct a strong countercase or alternative to an assumption and assess consequence if it fails.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill challenge-assumption -a windsurf -y
name: challenge-assumption description: "Construct a strong countercase or alternative to an assumption and assess consequence if it fails."
Construct a strong countercase or alternative to an assumption and assess the consequence if it fails.
required: [assumption, claim_or_decision, supporting_evidence] optional: [alternative_worlds, dependency_graph, challenge_mode] constraints: [separate assumption, countercase, evidence, and impact]
1. State the assumption's role and dependencies in the target claim. 2. Build the strongest evidence-backed countercase and at least one alternative assumption. 3. Propagate consequences through dependent claims and identify discriminating observations. 4. Rate threat severity and confidence using the caller's scale.
produces: [countercase, alternative_assumptions, consequence_analysis, discriminating_tests] delta_fields: [findings, evidence_updates, uncertainties, recommended_jumps]
Caller supplies assumption schema, evidence standard, challenge mode, consequence model, severity/confidence scales, and test budget.
Reject a challenge that merely negates the assumption without mechanism or evidence.
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…