alternative-analysis
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/alternative-analysisGenerates competing scenarios to challenge dominant narratives and assumptions
- Solves the problem of anchoring on a single explanation by exploring alternatives
- Uses structured analysis methods like what-if analysis and four ways of seeing
- Decides based on evidence testing and diagnostic indicators across scenarios
- Delivers results through scenario comparison and resilience scoring
SKILL.md
.github/skills/alternative-analysisView on GitHub ↗
---
name: alternative-analysis
description: "Strategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing — generate competing explanations and scenarios to challenge the dominant narrative."
type: strategy
used-by: [red-teaming]
tactics: [structured-attack-campaign, adversarial-roleplay]
---
# Alternative Analysis Strategy
CIA SAT alternative analysis: generate multiple competing interpretations to prevent anchoring on a single explanation.
## Method
1. **alternative-futures** builds 2-4 divergent scenarios from the same evidence base
2. What-If Analysis: systematically vary key variables to explore outcome sensitivity
3. Four Ways of Seeing: examine artifact through lenses of opportunity, risk, structure, and agency
4. **probe-execution** tests each alternative against available evidence
5. Diagnostic indicators identified that would discriminate between alternatives
6. **finding-aggregation** compares explanatory power across alternatives
## Budget Table
| Parameter | S | M | L |
|---|---|---|---|
| Attack vectors | 5 | 12 | 20 |
| Probing rounds | 3 | 6 | 10 |
| Personas | 2 | 4 | 6 |
| Assumption checks | 5 | 10 | 20 |
## Orchestration
```
threat-surface-mapping → [identify variable dimensions]
→ alternative-futures (generate 2-4 scenarios)
→ [for each alternative]:
attack-vector-generation (find discriminating tests)
→ probe-execution (test alternative)
→ finding-aggregation → attack-resilience-scoring
```
## Subagents
- threat-surface-mapping (dimension identification)
- alternative-futures (scenario generation)
- attack-vector-generation (discriminating test design)
- probe-execution (alternative testing)
- finding-aggregation (comparative synthesis)
More from yogsoth-ai/de-anthropocentric-research-engine
- 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.