Menu
Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Anomaly detection for AI agents. Z-score, IQR, and streaming detection. Find outliers in data instantly. Sub-millisecond response. Works on single values or full datasets.
A/B testing and feature optimization for AI agents. Pick the best option automatically using Multi-Armed Bandits and Contextual Bandits (LinUCB). No data warehouse needed — works from request
Bayesian inference engine for AI agents. Update beliefs with new evidence. Prior + evidence = posterior. Multi-factor prediction with calibration tracking.
CMA-ES continuous optimization for AI agents. State-of-the-art derivative-free optimizer. 10-100x more sample-efficient than genetic algorithms on continuous problems. Hyperparameter tuning, portfolio optimization, parameter calibration.
Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.
Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by historical accuracy.
| name | oraclaw-calibrate |
| description | Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree. |
| version | 1.0.0 |
| metadata | {"openclaw":{"requires":{"env":["ORACLAW_API_KEY"]},"primaryEnv":"ORACLAW_API_KEY","emoji":"📊","homepage":"https://web-olive-one-89.vercel.app/calibrate","tags":["calibration","forecasting","prediction","accuracy","scoring","convergence","brier-score"],"price":0.02,"currency":"USDC"}} |
You are a calibration agent that scores prediction accuracy and detects when information sources disagree.
Use this when you need to:
score_calibration — Accuracy ScoringInput: arrays of predictions (0-1) and outcomes (0 or 1). Output: Brier score (0=perfect, 1=worst) and log score.
score_convergence — Multi-Source AgreementInput: array of prediction sources with probabilities. Output: convergence score (0-1), outlier detection, consensus probability, spread.
{
"predictions": [0.80, 0.65, 0.30, 0.90, 0.55],
"outcomes": [1, 1, 0, 1, 0]
}
Response: brier_score: 0.082 — excellent calibration.
$0.02 per scoring call (USDC on Base via x402). Free tier: 3,000 calls/month with API key.