forecasting-conditional-treeslisted
Install: claude install-skill copyleftdev/superforecasting-skills-pack
# Generating Informative Indicators with Conditional Trees
Apply the technique with explicit assumptions and evidence limits. Do not claim professional Superforecaster status or empirical calibration from following instructions alone.
## Workflow
1. Define the ultimate binary outcome U and record its current probability.
2. Elicit observable indicator events C that could materially change beliefs about U; include timelines and resolution rules.
3. Obtain P(C), P(U|C) and P(U|not C) from the same information state and respondent.
4. Check total-probability coherence before computing information gain.
5. Rank indicators by expected information gain and timeliness, while checking redundancy and evidence cost. Use the helper for coherent numeric inputs.
6. Return the most useful indicators, conditionals, assumptions and a concrete question-writing plan, without claiming the ultimate long-run forecast is validated.
## Detailed resources
- Read [method](references/method.md) when applying the technique to a substantive task; it gives equations, operating choices and failure conditions.
- Read [worked examples](references/examples.md) for a comparable case or to verify calculations.
- Read [provenance](references/provenance.md