futures-calibration
Skill2 starsChanged 6 months agoApache-2.0View on GitHub
Aggregate probability judgments across perspectives using Real-Time Delphi or prediction market mechanisms.
In this repository119 other files it gives its agents.
- adaptive-pair-selectionSkill
- adversarial-debate-protocolSkill
- advocate-constructionSkill
- aggregation-methodSkill
- alternative-scoringSkill
- appropriateness-boundingSkill
- argument-crystallizationSkill
- argument-extractionSkill
- assumption-challengeSkill
- assumption-excavationSkill
- assumption-extractionSkill
- ballot-collectionSkill
- best-option-selectionSkill
- bottleneck-identificationSkill
- category-sortingSkill
- cluster-analysisSkill
- coherence-diagnosisSkill
- collective-adjudicationSkill
- comparative-feasibility-rankingSkill
- comparison-executorSkill
- conclusion-sensitivitySkill
- conjunctive-filterSkill
- consensus-classificationSkill
- consensus-measurementSkill
- consensus-synthesisSkill
- consistency-audit-loopSkill
- constraint-classificationSkill
- constraint-drillingSkill
- constraint-identificationSkill
- constraint-identification-sopSkill
- convergence-checkSkill
- convergence-distillationSkill
- counter-thesis-constructionSkill
- coverage-scoringSkill
- criteria-interrogationSkill
- criterion-definitionSkill
- critic-attackSkill
- cycle-detectionSkill
- deliberative-calibrationSkill
- dimension-assessmentSkill
- disagreement-cartographySkill
- disagreement-mappingSkill
- disagreement-visualizationSkill
- diversity-maximizationSkill
- dominance-checkSkill
- dynamic-trackingSkill
- efficient-explorationSkill
- feasibility-assessmentSkill
- feasibility-synthesisSkill
- feedback-distributionSkill
- full-rankingSkill
- gate-criteria-definitionSkill
- gate-judgmentSkill
- inconsistency-localizationSkill
- iterative-convergence-roundSkill
- judge-verdictSkill
- judgment-collectionSkill
- maturation-pathway-designSkill
- maturity-diagnosisSkill
- method-sensitivity-reportSkill
- The first 60 shown.
The file
Files
Futures Calibration
Purpose: Aggregate probabilistic forecasts from multiple perspectives into calibrated predictions. Uses Real-Time Delphi continuous updating or prediction market scoring to produce well-calibrated probability estimates for future events.
When to use:
- Technology timeline estimation
- Market forecasts requiring multiple expert inputs
- Risk probability assessment
- Any question framed as "what is the probability that X by time T?"
Budget
| Parameter | Constraint |
| Rounds | 2–3 (continuous updating preferred) |
| Perspectives | ≥4 independent forecasters |
| Calibration target | Brier score improvement across rounds |
State Ledger
| Key | Type | Description |
| question | string | The forecasting question |
| time_horizon | string | When the event would resolve |
| perspectives | array | List of forecaster perspectives |
| rounds | array | History of probability estimates |
| current_aggregate | float | Current aggregated probability |
| calibration_metrics | object | Brier score, log score tracking |
Available Tactics
- iterative-convergence-round — Adapted for probability estimates
- threshold-calibration — Determine confidence bands
Available SOPs
- judgment-collection
- feedback-distribution
- consensus-measurement
- round-decision
- threshold-sweep
- consensus-synthesis
Execution Guidance
- Frame question with clear resolution criteria and time horizon
- Collect initial probability estimates with reasoning
- Share aggregate and reasoning (anonymized) each round
- Track whether estimates are converging or polarizing
- Report final calibrated estimate with confidence interval
Output Format
forecast_question: <question>
time_horizon: <date/period>
calibrated_probability: <float 0-1>
confidence_interval: [lower, upper]
rounds_completed: <int>
convergence_pattern: converging/stable/polarizing
key_considerations: [...]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.