forecast-accuracy-analyzer
Forecast accuracy measurement and improvement skill with error decomposition
npx skills add a5c-ai/babysitter --skill forecast-accuracy-analyzer --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.
# Forecast Accuracy Analyzer ## Overview The Forecast Accuracy Analyzer provides comprehensive forecast accuracy measurement, error decomposition, and improvement recommendation capabilities. It supports continuous forecast quality improvement through root cause analysis and model performance comparison. ## Capabilities - **MAPE, WMAPE, Bias Calculation**: Standard accuracy metrics - **Forecast Error Decomposition**: Breakdown by error source - **SKU-Level Accuracy Tracking**: Granular accuracy monitoring - **Forecast Value-Add (FVA) Analysis**: Contribution of forecast steps - **Root Cause Categorization**: Error driver classification - **Model Performance Comparison**: Multi-model accuracy benchmarking - **Improvement Recommendation Generation**: Data-driven suggestions - **Accuracy Trend Monitoring**: Historical accuracy tracking ## Input Schema ```yaml forecast_accuracy_request: forecast_data: forecasts: array - sku_id: string period: string forecast_value: float forecast_source: string period_range: start: date end: date actual_data: actuals: array - sku_id: string period: string actual_value: float analysis_parameters: metrics: array # MAPE, WMAPE, Bias, etc. aggregation_leve
- Overview
- Capabilities
- Input Schema
- Output Schema
- Usage
- Monthly Accuracy Review
- Forecast Value-Add Analysis
- Root Cause Investigation
- Integration Points
- Process Dependencies
- Best Practices
What does the forecast-accuracy-analyzer skill do?
Forecast accuracy measurement and improvement skill with error decomposition
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill forecast-accuracy-analyzer --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.