Back to resources

SKILL

what-if-oracle

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/what-if-oracle
Use with an agent

SUMMARY

What it does

This Agent Skill, named 'what-if-oracle', provides a structured methodology for exploring uncertain futures through multi-branch scenario analysis. It guides the user through phases: framing the question, mapping 4-6 scenario branches (best, likely, worst, wild card, contrarian, second-order), analyzing each branch with probability, timeframe, confidence, narrative, assumptions, triggers, consequences, required response, and non-obvious insights, and synthesizing results with probability distribution, robust actions, hedge actions, decision triggers, and a 1% insight. It includes modes like Quick Oracle, Deep Oracle, Scenario Chain, Reverse Oracle, and Competitive Oracle. The skill is based on the What-If Paradigm and references published research DOIs. It is designed for speculative questions, strategic planning, contingency planning, and stress-testing decisions. The source is a SKILL.md file from a GitHub repository, inspected and verified for content.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

analyze.scenarioweight 100 · confidence 90generate.insightsweight 80 · confidence 80plan.contingencyweight 70 · confidence 70

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.