abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/detect-performance-discrepancyContext preview
The summary Claude sees to decide when to auto-load this skill.
Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences.
name: detect-performance-discrepancy description: "Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences."
Detect material score discrepancies for the same method or task across sources and identify plausible condition differences.
required: [performance_records, method_key, task_key, metric_schema] optional: [protocol_records, condition_schema, uncertainty_estimates] constraints: [comparisons require aligned metric direction and declared conditions]
1. Align records by method, task, metric, and observation context. 2. Quantify score differences with uncertainty and identify materially different pairs. 3. Compare datasets, prompts, evaluators, budgets, and protocol conditions. 4. Rank plausible explanations and retain unresolved alternatives.
produces: [discrepancy_pairs, condition_difference_map, explanation_candidates, residual_uncertainties] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
Do not call rounding noise a discrepancy or infer a method improvement from non-equivalent evaluation conditions.
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.