WorldThreatModelHarness

Stress-tests ideas and strategies against 11 persistent world models spanning 6 months to 50 years.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/Kaleb-Rupe/aurora --skill worldthreatmodelharness-kaleb-rupe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: WorldThreatModelHarness
Source: https://github.com/Kaleb-Rupe/aurora/tree/main/claude/skills/Thinking/WorldThreatModelHarness
Command: npx skills add https://github.com/Kaleb-Rupe/aurora --skill worldthreatmodelharness-kaleb-rupe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Evaluating whether an idea, strategy, or investment will survive changing geopolitical, technological, and economic conditions over time is difficult without structured long-range analysis. This Skill maintains 11 persistent world models (6 months to 50 years) and tests any idea against all of them simultaneously using adversarial analysis. ## Core Features & Use Cases - Multi-Horizon Stress Testing: Tests ideas against 11 world model documents covering geopolitics, technology, economics, society, environment, security, and wildcards, with per-horizon verdicts and confidence ratings. - Tiered Analysis Depth: Fast (~2 min single-agent), Standard (~10 min with 11 parallel agents plus RedTeam and FirstPrinciples), and Deep (up to 1 hour with Research, RedTeam, and Council debate) execution tiers. - World Model Management: Creates, updates, and views persistent world model documents stored in ~/.claude/MEMORY/RESEARCH/WorldModels/ with freshness tracking and an INDEX.md summary. - Use Case: A founder considering a hardware startup asks "test this idea deep" and receives per-horizon verdicts, adversarial attack vectors, assumption challenges, and a council debate on 50-year viability. ## Quick Start Ask the assistant to test your idea or strategy against the world threat models, optionally specifying fast or deep for the analysis tier.

Frequently Asked Questions about WorldThreatModelHarness

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stress test a business idea against future scenarios?

Run the TestIdea workflow by asking to test your idea, strategy, or investment. The skill evaluates it against 11 world models from 6 months to 50 years, returning per-horizon verdicts, key factors, and adversarial findings.

What is the difference between Fast, Standard, and Deep analysis tiers?

Fast uses a single agent for a ~2 minute gut-check with abbreviated verdicts. Standard runs 11 parallel agents plus RedTeam and FirstPrinciples in ~10 minutes. Deep adds per-horizon research and a Council debate, taking up to an hour.

How do I create or update the world models?

Say "update world models" to run the UpdateModels workflow. It uses research agents to write or refresh each horizon document following the ModelTemplate structure, then updates the INDEX.md with dates, versions, and confidence levels.

What happens if the world models do not exist yet?

The TestIdea workflow checks for all 11 model files first and prompts you to run "update world models" before testing. Models older than 30 days trigger a staleness warning but analysis still proceeds.

Can I view or compare specific world model horizons?

Yes, the ViewModels workflow shows an overview table with freshness indicators, a single horizon's full document, or a side-by-side comparison of selected horizons such as near-term versus long-term trends.