reference-class-forecasting

Establish statistical baselines by identifying reference classes and historical data.

142|20|Updated Oct 22, 2025

Search Tags:#decision making #forecasting #bias mitigation #base rate #statistical thinking #outside view

Ready to run

npx skills add https://github.com/lyndonkl/claude --skill reference-class-forecasting

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reference-class-forecasting
Source: https://github.com/lyndonkl/claude/tree/main/skills/reference-class-forecasting
Command: npx skills add https://github.com/lyndonkl/claude --skill reference-class-forecasting

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you establish a statistical baseline (base rate) for any forecast, preventing the common biases of overconfidence and "this time is different" thinking.

Core Features & Use Cases

Establish Base Rates: Identify a relevant historical class of similar events and find their statistical outcomes.
Challenge Uniqueness Claims: Systematically test if a current situation is truly exceptional or just appears so.
Calculate Funnel Probabilities: Model multi-stage processes where no single base rate exists.
Validate Reference Classes: Ensure your chosen comparison set is appropriate and data-rich.
Use Case: Before predicting the success of a new startup, use this Skill to find the historical success rate of similar startups (e.g., seed-stage B2B SaaS in fintech) to set a realistic starting probability.

Quick Start

Use the reference-class-forecasting skill to find the base rate for a new software project launch.

Frequently Asked Questions about reference-class-forecasting

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

FAQPage Schema

How do I use base rates to improve forecasting accuracy?▼

Base rates improve forecasting by establishing a statistical baseline from a historical reference class before predicting a specific outcome. This framework mitigates overconfidence and inside view bias by ensuring your prediction starts with historical reality rather than optimistic assumptions.

What is the best way to challenge assumptions of uniqueness in a forecast?▼

To challenge assumptions of uniqueness, systematically test whether your current situation is truly exceptional or merely appears so. This Skill provides a structured framework to validate reference classes and identify how your specific case compares to historical data.

How do I calculate funnel probabilities for multi-stage processes?▼

Funnel probabilities are calculated by modeling multi-stage processes where no single historical base rate exists. This Skill supports breaking down the process into distinct sequential stages and deriving probabilities for each step to reach an overall likelihood.

When should I use outside view forecasting over inside view thinking?▼

Outside view forecasting should be used whenever you need to mitigate base rate neglect and prevent this time is different thinking. It is essential for establishing statistical baselines and validating that your chosen reference class is appropriate and data-rich before finalizing predictions.

How do I validate a reference class for statistical thinking?▼

You validate a reference class by ensuring your chosen comparison set is appropriate and data-rich. This Skill guides you through testing the relevance of historical data sets to confirm they accurately represent the current situation you are forecasting.