Skill329 repo starsupdated 5d ago

assumption-perturbation

assumption-perturbation systematically identifies load-bearing assumptions in research arguments by extracting implicit premises, replacing each with its strongest plausible alternative, re-deriving conclusions under each negation, and ranking by sensitivity. Use this skill when evaluating the robustness of a theoretical framework, experimental design, or empirical claim to determine which foundational assumptions most critically drive the stated conclusions.

View source Repository: de-anthropocentric-research-engine

Install in Claude Code

Copy

git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/assumption-perturbation && cp -r /tmp/assumption-perturbation/skills/assumption-perturbation ~/.claude/skills/assumption-perturbation

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Assumption Perturbation

Systematically perturb assumptions to identify which are load-bearing.

## Operations

assumption-extraction → negation-definition → re-derivation → conclusion-sensitivity-measurement

## Available SOPs

**Subagent:** assumption-extraction, negation-definition, re-derivation, conclusion-sensitivity-measurement
**Shared:** assumption-surfacing
**Import:** paper-research

## Execution Guidance

Extract all assumptions (use shared SOP for initial surfacing), define weakest plausible alternative for each, re-derive the conclusion under each alternative, measure change magnitude and direction. Rank by sensitivity.

Key principle: negation is not logical NOT — it is the strongest plausible alternative. "Data is normally distributed" negates to "data follows a heavy-tailed distribution" not "data is not normally distributed."

## Minimum Yield

```
<HARD-GATE>
- Assumptions extracted: >= 5
- Negations defined: >= 5
- Re-derivations completed: >= 4
- Sensitivity rankings produced: >= 1 complete ranking
</HARD-GATE>
```