forecasting-decompositionlisted
Install: claude install-skill copyleftdev/superforecasting-skills-pack
# Decomposing Forecasts without Independence Errors
Use the research-informed procedure below without claiming professional Superforecaster status or empirically demonstrated calibration.
## Workflow
1. Define the parent event and list the components needed to answer it.
2. Choose the correct structure: conjunction, union, mutually exclusive scenario partition, or dimensional quantity model.
3. Label every number as marginal, joint, or conditional; document which variables have already been observed.
4. Calculate with the chain rule or total probability. Assume independence only with a defensible rationale.
5. Check omitted pathways, shared causes and probability bounds. Compare to a direct outside-view estimate as a diagnostic, not a second independent observation.
6. Vary consequential uncertain inputs and return the model, result, sensitivity and unsupported assumptions.
## Detailed resources
- Read [method](references/method.md) when applying this technique to a substantive task; it contains assumptions, equations and edge cases.
- Read [worked examples](references/examples.md) for a comparable case or to verify interpretation.
- Read [provenance](references/provenance.md) for original authors, source attribution an