severity-scoring

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

Rates failure modes' severity on a 1-10 scale based on end-effect impact

  • Identifies and categorizes failure modes for severity assessment.
  • Deploys AIAG-VDA severity scale calibrated for research artifacts.
  • Analyzes cause-mode-effect chains to determine the end-effect impact of each mode.
  • Generates a list of scores with justification for each failure mode.

SKILL.md

.github/skills/severity-scoringView on GitHub ↗
---
name: severity-scoring
description: Rate failure mode severity 1-10 based on end-effect impact. Follows AIAG-VDA severity scale calibrated for research artifacts.
execution: subagent
prompt: ./prompt.md
input: failure_modes (string), chains (string)
used-by: [failure-anticipation]
---

# Severity Scoring

Rates each failure mode's severity on a 1-10 scale based on end-effect impact.

## Execution

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

## Why Subagent

Severity assessment requires consistent calibration across all modes. Isolated context prevents anchoring bias from occurrence or detection considerations.

## Input

- **failure_modes**: Failure mode catalog
- **chains**: Cause-mode-effect chains (for end-effect reference)

## Output

- **scores**: List of (failure_mode_id, severity_score, justification)
- **calibration_notes**: Any scoring edge cases or assumptions

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.