Demand forecasting skill with quantitative and qualitative methods, accuracy measurement, and bias correction
Generates demand forecasts using statistical and machine learning methods with accuracy measurement and bias correction.
npx claudepluginhub a5c-ai/babysitterThis skill is limited to using the following tools:
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.
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: "promotion"
lift: 15 # percent
outputs:
- point_forecast
- confidence_intervals
- accuracy_metrics
- bias_analysis
- seasonality_factors
- recommendations
| Method | Best For | Complexity |
|---|---|---|
| Moving Average | Stable demand | Low |
| Exponential Smoothing | Trends and seasonality | Medium |
| ARIMA | Complex patterns | High |
| Prophet | Multiple seasonalities | Medium |
| Method | Use Case |
|---|---|
| Regression | Known drivers |
| Econometric | Market factors |
| Machine Learning | Complex relationships |
MAPE = (1/n) x Sum(|Actual - Forecast| / Actual) x 100
MAE = (1/n) x Sum(|Actual - Forecast|)
Bias = (1/n) x Sum(Forecast - Actual)
| MAPE | Interpretation |
|---|---|
| < 10% | Excellent |
| 10-20% | Good |
| 20-30% | Acceptable |
| 30-50% | Poor |
| > 50% | Very poor |
Compare accuracy at each step:
Only keep adjustments that improve accuracy.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.