Skip to content
Automation
Skill

/detect-performance-discrepancy

Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences.

From plugin
de-anthropocentric-research-engine
499200 skills
Install
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill detect-performance-discrepancy --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/detect-performance-discrepancy

Context 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.

SKILL.md

detect-performance-discrepancy.SKILL.md
name: detect-performance-discrepancy
description: "Detect material score discrepancies for the same method/task across sources and propose likely explanatory condition differences."

detect-performance-discrepancy

Purpose

Detect material score discrepancies for the same method or task across sources and identify plausible condition differences.

Input contract

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]

Procedure

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.

Output contract

produces: [discrepancy_pairs, condition_difference_map, explanation_candidates, residual_uncertainties]
delta_fields: [findings, evidence_updates, uncertainties, open_questions]

Quality gates

  • Materiality uses a declared comparison basis.
  • Protocol mismatch is separated from method change.

Failure and counterexamples

Do not call rounding noise a discrepancy or infer a method improvement from non-equivalent evaluation conditions.

Provenance map

  • `resolved: discrepancy-identification`
  • `resolved: discrepancy-analysis`
Read more
Ships withde-anthropocentric-research-engine

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.

Get the whole plugin
Stats
499
Stars
41
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
8h ago
Last commit
7mo ago
Created

Repo: yogsoth-ai/de-anthropocentric-research-engine