re-scoring

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/re-scoring

Re-evaluates S/O/D scores after mitigation to validate risk reduction

  • Validates whether implemented mitigations effectively reduce risk
  • Uses subagent execution to avoid bias from original scores
  • Compares new scores against original to assess mitigation effectiveness
  • Returns updated scores, effectiveness metrics, and high-risk modes

SKILL.md

.github/skills/re-scoringView on GitHub ↗
---
name: re-scoring
description: Re-evaluate S/O/D scores after mitigation measures are in place. Validates that mitigations actually reduce risk as expected.
execution: subagent
prompt: ./prompt.md
input: failure_modes (string), mitigations (string), original_scores (string)
used-by: [failure-anticipation]
---

# Re-Scoring

Re-evaluates Severity, Occurrence, and Detection scores after mitigations are applied.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Why Subagent

Re-scoring requires fresh evaluation without anchoring to original scores. Isolated context prevents confirmation bias toward expected improvement.

## Input

- **failure_modes**: Original failure mode descriptions
- **mitigations**: Proposed mitigation measures
- **original_scores**: Pre-mitigation S/O/D scores for comparison

## Output

- **new_scores**: Post-mitigation S, O, D, and RPN for each mode
- **effectiveness**: Comparison with original scores
- **still_high**: Modes that remain H-priority after mitigation

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.