Assumption Stress Test

SkillSecurity

Lets your agent surface hidden assumptions in a plan or claim and rank which ones are most fragile.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Assumption Stress Test skill

About this capability

Systematic stress testing of assumptions, surface, classify by vulnerability,

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/assumption-stress-test/SKILL.md and read by ahel’s review.

Systematically stress-test assumptions to find dangerous ones.

Operations

  • assumption-surfacing (shared) — extract all implicit assumptions
  • abp-vulnerability-classification — classify by load-bearing × vulnerable
  • clr-validation — validate causal logic of critical assumptions

Available SOPs

Shared: assumption-surfacing Subagent: abp-vulnerability-classification, clr-validation Import: paper-research

Execution Guidance

Surface all assumptions (shared SOP). Classify each by load-bearing × vulnerable matrix. Validate causal logic of most critical assumptions (High-Load × High-Vulnerable quadrant).

Minimum Yield

<HARD-GATE>
- assumptions surfaced: >= 5
- vulnerability classifications: >= 5
- CLR validations on critical assumptions: >= 2
- dangerous assumptions identified: >= 1
</HARD-GATE>

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOPWhen to use
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.
clr-validationApply Goldratt's 8 Categories of Legitimate Reservation to validate causal claims. Tests clarity, existence, sufficiency, and logical integrity.
deep-insight-assumption-surfacingSystematically extract implicit assumptions from methods, frameworks, or arguments. Identifies what is taken for granted without explicit justification.
deep-insight-paper-researchFull-text paper reading via three-pass Keshav method. Import of literature-engine/literature-research skill. Authoritative source for claims about paper content.

Signals

GitHub stars
481
Forks
37
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
assumption-stress-test
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine