Produce an updateable probability or distribution for a resolvable future event using base rates, explicit assumptions, and a declared resolution source. Use when the user asks for a forecast, probability, confidence, or calibration. Do not use to estimate a past causal effect, register an experiment, or critique a present explanation.
Installs into .claude/skills of the current project.
Are you the author of Forecast With Calibration?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/sylphxai-forecast-with-calibration)
---
name: forecast-with-calibration
description: "Produce an updateable probability or distribution for a resolvable future event using base rates, explicit assumptions, and a declared resolution source. Use when the user asks for a forecast, probability, confidence, or calibration. Do not use to estimate a past causal effect, register an experiment, or critique a present explanation."
---
# Forecast With Calibration
A forecast that cannot resolve is a vibe. Write the event, deadline, resolution source, and ambiguity rule before the number. Start from a relevant base rate; the inside view updates that rate, it does not erase it.
One hit or miss is not calibration. Score a comparable set with a proper scoring rule declared before the outcome. Extreme confidence needs extreme evidence; multiplying dependent sub-events manufactures false precision.
Open [probabilistic forecasting methods](references/probabilistic-forecasting-methods.md) for elicitation, aggregation, scoring, and update cadence.
Use `analyze-causal-inference` for whether a past change caused an outcome. Use `design-product-experiment` when assignment can answer the question. Use `analyze-critically` for confidence in a present explanation.
