demand-forecasting
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.
npx skills add majiayu000/claude-skill-registry --skill demand-forecasting-kishorkukreja-awesome-supply-chain --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.
What it does
Describes an expert who helps build accurate forecasting models and improve forecast accuracy for demand planning, sales forecasting, time series, and related areas. It emphasizes understanding business context, data availability, demand characteristics, and current state before modeling.
How it works
- Performs an initial assessment covering business context, data availability, demand characteristics, and current forecasting state.
- Provides a Forecasting Framework with patterns identification (stable, trend, seasonal, intermittent, promotional).
- Details Forecasting Methods across Time Series (Moving Average, Exponential Smoothing, Holt's methods, Holt-Winters, ARIMA, SARIMA, Prophet) and Machine Learning/CAUSAL approaches (Linear Regression with features, Random Forest, XGBoost, LSTM, Prophet).
- Lists Intermittent Demand Methods (Croston, TSB, Bootstrapping).
- Defines Forecast Process steps: data preparation, model selection logic, baseline forecast generation with confidence intervals, forecast enrichment with promotions and external signals, collaborative review, consensus forecast with weighted blending, and performance tracking.
- Outlines Advanced Techniques: Hierarchical Forecasting (Top-Down, Bottom-Up, Middle-Out, MinT), Forecast Value Added (FVA), and Demand Sensing with real-time signals.
- Enumerates Tools & Libraries (statsmodels, pmdarima, Prophet, sktime, scikit-learn, xgboost, TensorFlow/PyTorch, pandas, numpy, visualization libs) and Commercial Software (SAP IBP, Oracle Demantra, Blue Yonder, Kinaxis, Anaplan, o9).
- Highlights Common Challenges with suggested solutions like high volatility and new product forecasting.
When to use it
The skill is intended for forecasting tasks when the user seeks demand planning, sales forecasting, time series analysis, forecast accuracy improvement, demand sensing, or predictive analytics. It suggests capacity planning and S&OP integration contexts but does not specify execution outside forecasting scope.
What it can touch
- Mentions tools and libraries under Python ecosystems for statistical, ML, and DL forecasting.
- References commercial planning systems and Excel add-ins as relevant touchpoints for implementation and deployment.
Caveats
- The content presents a comprehensive framework and code templates, but does not guarantee forecasting performance; results depend on data quality, feature engineering, and model selection.
- License is MIT as per metadata, but no explicit license statements appear in the text beyond that.
# Demand Forecasting You are an expert in demand forecasting and planning. Your goal is to help build accurate, reliable forecasting models that drive better inventory, production, and supply chain decisions. ## Initial Assessment Before building forecasts, understand: 1. **Business Context** - What products/SKUs need forecasting? - What decisions depend on these forecasts? - What's the planning horizon? (daily, weekly, monthly) - What's the current forecast accuracy (MAPE, bias)? 2. **Data Availability** - Historical sales/demand data available? - Time period covered? (need 2+ years ideally) - Data granularity? (SKU, location, channel) - External factors tracked? (promotions, weather, events) 3. **Demand Characteristics** - Demand patterns? (stable, seasonal, trending, intermittent) - New products vs. mature products? - Promotional vs. baseline demand? - Lead times and reorder cycles? 4. **Current State** - Existing forecasting process? - Tools in use? (Excel, statistical software, ERP) - Known forecast biases or issues? - Forecast override process? --- ## Forecasting Framework ### Demand Patterns Recognition **1. Stable/Level Demand** - Consistent demand with random variation - U
- Initial Assessment
- Forecasting Framework
- Demand Patterns Recognition
- Forecasting Methods
- Time Series Methods
- Causal/Regression Methods
- Machine Learning Methods
- Intermittent Demand Methods
- Forecast Accuracy Metrics
- Key Metrics
- Target Accuracy by Product Category
- Demand Segmentation
- ABC Analysis
- Forecast Process
What does the demand-forecasting skill do?
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill demand-forecasting-kishorkukreja-awesome-supply-chain --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 majiayu000/claude-skill-registry, a repository with 534 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.