abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Locate the point or region where performance/validity changes regime or the claim flips.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-breakpoint --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/detect-breakpointContext preview
The summary Claude sees to decide when to auto-load this skill.
Locate the point or region where performance/validity changes regime or the claim flips.
name: detect-breakpoint description: "Locate the point or region where performance/validity changes regime or the claim flips."
Locate the point or region where performance, validity, or a claim changes regime.
required: [ordered_observations, target_metric, flip_or_regime_rule] optional: [candidate_axis, smoothing_rule, uncertainty_bounds] constraints: [ordering and metric direction are explicit]
1. Sort observations along the declared axis and validate comparability. 2. Detect abrupt flips, slope changes, saturation, or regime transitions. 3. Estimate boundary region and attach uncertainty. 4. Return witness observations and follow-up tests.
produces: [breakpoint_region, regime_label, witness_observations, uncertainty, follow_up_tests] delta_fields: [findings, uncertainties, open_questions]
Caller supplies observation schema, axis ordering, metric, flip/regime rule, smoothing, and uncertainty policy.
Reject boundaries inferred from unvalidated ordering, single noisy points, or hidden smoothing.
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
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, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
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.