edge-case-generation

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/edge-case-generation

Systematically generate edge cases for failure analysis

  • Identifies and generates boundary values, adversarial inputs, distribution shifts, rare combinations, and scale extremes.
  • Deploys systematic methods to explore system limits and potential failures under various conditions.
  • Uses domain knowledge and algorithmic approaches to decide which edge cases are most relevant for analysis.
  • Delivers generated edge cases directly to the user or agent for further investigation and testing.

SKILL.md

.github/skills/edge-case-generationView on GitHub ↗
---
name: edge-case-generation
description: Systematically generate boundary inputs — boundary values, adversarial constructions, distribution shifts, rare combinations, scale extremes.
execution: subagent
prompt: ./prompt.md
input: method_description (string), domain (string)
used-by: failure-mode-analysis
---

# Edge Case Generation

Generate systematic edge cases to probe failures.

## Execution

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

## Budget

One unit = one edge case generation pass (minimum 20 cases).

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.