threshold-sweep

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/threshold-sweep

Generates a threshold-consensus curve by evaluating consensus status across multiple thresholds

  • Identifies robust and fragile consensus items across a dataset
  • Uses judgments and a threshold range as input parameters
  • Computes consensus classification at each threshold level
  • Returns a threshold_curve with at least 5 data points

SKILL.md

.github/skills/threshold-sweepView on GitHub ↗
---
name: threshold-sweep
description: Compute consensus status at multiple threshold levels to produce a threshold-consensus curve.
execution: subagent
prompt: ./prompt.md
input: judgments[], threshold_range
used-by: structured-consensus
---

# Threshold Sweep

Systematically compute consensus status at multiple threshold levels across a specified range. Produces a curve showing how many items achieve consensus as the threshold varies, revealing robust vs. fragile consensus items.

## Execution

Spawn a subagent that takes judgments and a threshold range, then computes consensus classification at each threshold level to produce the curve.

## Why Subagent

- Sweep computation is a bounded, parallelizable task
- Produces a standardized curve structure
- Keeps orchestration context clean

## HARD-GATE

Output MUST contain: `threshold_curve` with at least 5 data points, each showing threshold value and number of consensus items. Curve must span the full input range.

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
ablation-component-mappingMap system architecture to ablatable units for ablation studies
ablation-designDesign ablation studies to isolate component contributions in ML systems
ablation-executionRemove components one by one from a system, record the response/impact of each removal.
abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
abstraction-ladderPerform bisociation at multiple abstraction levels
abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.