demand-forecaster
Demand forecasting skill with quantitative and qualitative methods, accuracy measurement, and bias correction
npx skills add a5c-ai/babysitter --skill demand-forecaster --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Demand Forecaster ## Overview The Demand Forecaster skill provides comprehensive capabilities for generating and managing demand forecasts. It supports multiple forecasting methods, accuracy measurement, bias correction, and integration of statistical and judgmental inputs. ## Capabilities - Time series forecasting (ARIMA, exponential smoothing) - Causal modeling - Machine learning forecasts - Forecast accuracy metrics (MAPE, MAE, bias) - Collaborative forecasting - Demand sensing - Seasonality adjustment - New product forecasting ## Used By Processes - CAP-004: Demand Forecasting and Analysis - CAP-003: Sales and Operations Planning - CAP-001: Capacity Requirements Planning ## Tools and Libraries - Python statsmodels - Prophet - ML libraries (scikit-learn, TensorFlow) - Demand planning systems ## Usage ```yaml skill: demand-forecaster inputs: historical_data: - period: "2025-01" demand: 10500 - period: "2025-02" demand: 11200 # ... additional history forecast_horizon: 12 # months method: "auto" # auto | arima | exponential | ml | ensemble external_factors: - name: "gdp_growth" coefficient: 0.5 - name: "marketing_spend" coefficient: 0.3 adjustments: - period: "2026-06" type: "pro
- Overview
- Capabilities
- Used By Processes
- Tools and Libraries
- Usage
- Forecasting Methods
- Time Series Methods
- Causal Methods
- Accuracy Metrics
- Accuracy Benchmarks
- Forecast Value Added (FVA)
- Integration Points
What does the demand-forecaster skill do?
Demand forecasting skill with quantitative and qualitative methods, accuracy measurement, and bias correction
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill demand-forecaster --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.