Skip to content
Back to skills

Thought Experiment

ASecurity

Strategy: Williamson-style precise thought experiments — construct carefully specified counterfactual scenarios to test whether conclusions depend on contingent features.

  • 417 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
researchtesting

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill thought-experiment --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thought Experiment?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Thought Experiment
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-thought-experiment/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-thought-experiment)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: thought-experiment
description: "Strategy: Williamson-style precise thought experiments — construct carefully specified counterfactual scenarios to test whether conclusions depend on contingent features."
type: strategy
used-by: [counterfactual-probing]
tactics: [minimal-change-search, causal-necessity-testing]
---

# Thought Experiment Strategy

Williamson methodology: construct precise, well-specified counterfactual scenarios that isolate individual variables.

## Method

1. **causal-claim-extraction** identifies the conclusion and its dependencies
2. **factor-enumeration** identifies contingent vs. essential features
3. **counterfactual-scenario-construction** builds precise thought experiments
4. **flip-point-detection** identifies which scenario variations flip the conclusion
5. **necessity-evaluation** determines if flipped factors are genuinely necessary
6. **load-bearing-identification** distinguishes essential from contingent support

## Design Principles

- Scenarios must be internally consistent (no impossible worlds)
- Changes must be minimal and precisely specified
- Background conditions must be held fixed except the target variable
- Conclusions must follow from the scenario, not from intuition pumps

## Budget Table

| Parameter | S | M | L |
|---|---|---|---|
| Thought experiments | 3 | 8 | 15 |
| Variables isolated | 3 | 6 | 12 |
| Scenario precision checks | 1 | 3 | 6 |

## Orchestration

```
causal-claim-extraction → factor-enumeration
→ [for each contingent feature]:
    counterfactual-scenario-construction (precise scenario)
    → flip-point-detection (does conclusion hold?)
    → necessity-evaluation (is this genuinely necessary?)
→ load-bearing-identification (essential vs contingent)
```

## Subagents

- causal-claim-extraction (dependency identification)
- factor-enumeration (contingent feature detection)
- counterfactual-scenario-construction (scenario design)
- flip-point-detection (conclusion testing)
- necessity-evaluation (necessity judgment)
- load-bearing-identification (classification)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.