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.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy -a windsurf -y
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.
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…