Prediction skills for AI agents
20 practitioner-grade prediction skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 20 skills
- Bayesian Forecasting
Bayesian forecasting treats predictions as probability distributions that update as new evidence arrives. Rather than producing a single point estimate, the…
620 lines - Calibration and Accuracy
A forecaster who says "70% chance" should be right about 70% of the time they say that. This is calibration — the alignment between stated confidence and…
617 lines - Crowd Wisdom Aggregation
Crowd wisdom aggregation transforms individual judgments from diverse forecasters into collective predictions that consistently outperform any individual. This…
674 lines - Demand Forecasting
Demand forecasting predicts future customer demand for products and services, enabling optimized inventory management, production planning, workforce…
663 lines - Ensemble Prediction Methods
Ensemble prediction combines multiple forecasting models or forecasters to produce predictions that are more accurate and better calibrated than any individual…
690 lines - Financial Market Prediction
Financial market prediction combines technical analysis (price patterns), fundamental analysis (intrinsic value), sentiment analysis (market psychology), and…
577 lines - Geopolitical Forecasting
Geopolitical forecasting applies structured analytical techniques to predict political events, conflicts, policy changes, and their cascading effects on…
673 lines - Knowledge Graph Prediction
Knowledge graph prediction uses structured representations of entities and their relationships to forecast future events, discover hidden connections, and…
638 lines - Monte Carlo Simulation
Monte Carlo simulation uses repeated random sampling to estimate the probability distributions of uncertain outcomes. Named after the famous casino, the method…
592 lines - Multi-Agent Simulation for Prediction
Multi-agent simulation spawns thousands or millions of autonomous AI agents — each with unique personalities, knowledge, and decision-making patterns — and…
727 lines - Prediction Evaluation Metrics
Measuring forecast quality is as important as making forecasts. Without rigorous evaluation, you cannot distinguish skill from luck, identify systematic…
818 lines - Prediction Market Trading
Prediction market trading applies trading strategies, arbitrage detection, market making, and risk management techniques specifically to binary and categorical…
682 lines - Prediction Markets Fundamentals
Prediction markets are exchange-traded markets where participants buy and sell contracts whose payoffs are tied to the outcomes of future events. They function…
456 lines - Scenario Planning
Scenario planning is a structured methodology for exploring multiple plausible futures rather than predicting a single one. Developed at Royal Dutch Shell in…
545 lines - Simulation World Building
Simulation world building constructs rich digital environments populated by AI agents for the purpose of prediction and analysis. Inspired by approaches like…
837 lines - Social Dynamics Modeling
Social dynamics modeling simulates how opinions, behaviors, and information spread through populations. By modeling individuals as agents embedded in social…
715 lines - Swarm Intelligence Forecasting
Swarm intelligence forecasting harnesses the collective decision-making behavior observed in biological swarms (bees, fish, birds) and applies it to human and…
507 lines - Technology Trend Forecasting
Technology trend forecasting predicts the trajectory, timing, and impact of emerging technologies using frameworks like S-curves, the Gartner Hype Cycle, and…
655 lines - Time Series Forecasting
Time series forecasting predicts future values based on historically ordered observations. From stock prices to server load to disease spread, time series data…
660 lines - Weather and Climate Prediction
Weather and climate prediction represents one of humanity's most successful forecasting endeavors, blending physics-based numerical models, ensemble methods…
628 lines