skills/what-if-oracle/SKILL.md
# What-If Oracle Skill — Full Content Extract ## Overview The What-If Oracle is a structured scenario analysis tool designed to explore uncertain futures through multi-branch possibility mapping. It activates when users ask speculative questions about futures, decisions, risks, or consequences. ## Core Framework: 0·IF·1 The system operates on three elements: - **0**: The unexpressed potential state - **1**: The expressed current reality - **IF**: The conditional transformation between them T
npx skillsauth add lamm-mit/scienceclaw skills/what-if-oracleInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The What-If Oracle is a structured scenario analysis tool designed to explore uncertain futures through multi-branch possibility mapping. It activates when users ask speculative questions about futures, decisions, risks, or consequences.
The system operates on three elements:
The precision of the IF determines analysis quality. Vague questions yield vague results; specific variables produce actionable intelligence.
Phase 1 — Frame: Sharpen vague What-Ifs by decomposing into variable, magnitude, timeframe, and context. Present the refined question for confirmation.
Phase 2 — Map: Generate 4-6 scenario branches:
Phase 3 — Analyze: For each branch, detail probability, narrative, key assumptions, trigger conditions, consequences timeline, required responses, and overlooked insights.
Phase 4 — Synthesize: Provide probability distribution, identify robust cross-branch actions, define decision triggers, and surface the "1% insight" most analysis overlooks.
Allocate attention: 61.8% to primary scenario, 38.2% to alternatives—matching natural branching patterns.
License: MIT | Author: AHK Strategies
tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.