# Demand forecasting Human Guide

## What This Is For
Demand forecasting uses historical sales data, seasonal patterns, and lead times to predict how much inventory you'll need and when to reorder. It gives the agent a clearer input/output frame for demand forecasting: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Demand forecasting agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for demand forecasting.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Demand forecasting guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- When chronic stockouts or overstock situations indicate that current reorder points are set incorrectly
- When building automated replenishment recommendations to reduce manual inventory review
- When planning inventory for seasonal peaks (Black Friday, back-to-school, holiday season)
- When you have 12+ months of sales history and want to extract meaningful demand patterns
- When integrating with supplier lead times and purchase order workflows for end-to-end replenishment
- **Ensure cancelled and refunded orders are excluded** from your sales totals — most forecasting tools handle this automatically when connected to your platform
- **Tag promotional periods** — flash sales, holiday spikes, and influencer-driven demand should be flagged as abnormal; they inflate baseline demand estimates if included uncritically
- **You need at least 6 months of history** for basic seasonal pattern detection; 12+ months is required to see year-over-year trends
- Inventory Planner pulls your full Shopify sales history automatically on connection
- Connect your suppliers in Inventory Planner → Suppliers with their lead times (e.g., Supplier A = 14 days, Supplier B = 7 days)
- Set your desired service level (e.g., 95% — meaning you want to have stock for 95% of demand scenarios) in Settings → Forecasting
- Inventory Planner calculates reorder points and recommended order quantities per SKU, updated daily

## Decision Points And Nuance
The original skill emphasizes: Overview, When to Use This Skill, Core Instructions, Step 1: Determine your platform and choose the right forecasting tool, Step 2: Set up sales history data collection, Shopify, WooCommerce, BigCommerce, Step 3: Configure reorder points and safety stock, Step 4: Plan for seasonal demand.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- **You need at least 6 months of history** for basic seasonal pattern detection; 12+ months is required to see year-over-year trends
- Use these as inputs for manual reorder decisions if you don't want to pay for a forecasting app
- Filter by "Critical" (stock-out in fewer days than lead time) and "Warning" (stock-out within 2x lead time)
- urgency: 'critical' | 'warning' | 'ok';
- const urgency = daysOfSupply < leadTimeDays ? 'critical' : daysOfSupply < leadTimeDays * 2 ? 'warning' : 'ok';

## Copy-And-Paste Prompt
```text
Use the Demand forecasting human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the finsilabs/awesome-ecommerce-skills skill entry for `demand-forecasting`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Demand Forecasting

## Overview

Demand forecasting uses historical sales data, seasonal patterns, and lead times to predict how much inventory you'll need and when to reorder. Chronic stockouts or overstock situations are usually a sign that reorder points are based on intuition rather than data. Purpose-built inventory planning tools handle this for most merchants — custom forecasting code is only necessary for unique operational requirements.

## When to Use This Skill

- When chronic stockouts or overstock situations indicate that current reorder points are set incorrectly
- When building automated replenishment recommendations to reduce manual inventory review
- When planning inventory for seasonal peaks (Black Friday, back-to-school, holiday season)
- When you have 12+ months of sales history and want to extract meaningful demand patterns
- When integrating with supplier lead times and purchase order workflows for end-to-end replenishment

## Core Instructions

### Step 1: Determine your platform and choose the right forecasting tool

| Platform | Recommended Tool | Why |
|----------|-----------------|-----|
| **Shopify** | Inventory Planner (Shopify App Store) or Cogsy | Inventory Planner connects directly to Shopify, analyzes 12+ months of sales history, calculates reorder points, and generates purchase orders |
| **WooCommerce** | ATUM Inventory Management (free/premium) or Inventory Planner | ATUM provides reorder point management natively in WooCommerce; Inventory Planner has a WooCommerce connector for advanced forecasting |
| **BigCommerce** | Inventory Planner or Linnworks | Both have BigCommerce native integrations and handle multi-location inventory forecasting |
| **Multi-channel** | Skubana (now Extensiv) or Linnworks | Handles inventory forecasting across Shopify, WooCommerce, Amazon, and eBay from a single dashboard |
| **Custom / Headless** | Build a time-series analysis layer on top of your order database | Use moving averages, seasonal decomposition, and safety stock formulas against your historical sales data |

### Step 2: Set up sales history data collection

Accurate forecasting requires clean historical data. Before running any forecast:

1. **Ensure cancelled and refunded orders are excluded** from your sales totals — most forecasting tools handle this automatically when connected to your platform
2. **Tag promotional periods** — flash sales, holiday spikes, and influencer-driven demand should be flagged as abnormal; they inflate baseline demand estimates if included uncritically
3. **You need at least 6 months of history** for basic seasonal pattern detection; 12+ months is required to see year-over-year trends

#### Shopify

**Using Inventory Planner:**
1. Install **Inventory Planner** from the Shopify App Store (14-day free trial, then $99+/month)
2. Inventory Planner pulls your full Shopify sales history automatically on connection
3. Connect your suppliers in Inventory Planner → Suppliers with their lead times (e.g., Supplier A = 14 days, Supplier B = 7 days)
4. Set your desired service level (e.g., 95% — meaning you want to have stock for 95% of demand scenarios) in Settings → Forecasting
5. Inventory Planner calculates reorder points and recommended order quantities per SKU, updated daily

**Shopify Analytics (built-in, no app needed for basic trends):**
1. Go to **Analytics → Reports → Inventory**
2. The "Days of inventory remaining" report shows how many days of stock you have at current sell-through rate
3. Go to **Analytics → Reports → Sales over time** → group by product to see monthly sales trends
4. Use these as inputs for manual reorder decisions if you don't want to pay for a forecasting app

#### WooCommerce

**Using ATUM Inventory Management (free tier available):**
1. Install **ATUM Inventory Management for WooCommerce** from WordPress.org (free) or purchase the premium version
2. ATUM adds a master inventory list view with real-time stock levels, daily sales rates, and low-stock alerts
3. In ATUM → Settings → Reorder Points, configure your reorder levels and safety stock per SKU
4. ATUM's premium **Purchase Orders** module generates POs automatically when stock hits the reorder point

**Using Inventory Planner for WooCommerce:**
1. Connect Inventory Planner to WooCommerce via their native API connector
2. Same workflow as Shopify — Inventory Planner analyzes your WooCommerce sales history and generates forecasts

#### BigCommerce

**Using Inventory Planner:**
1. Connect Inventory Planner via the BigCommerce API (Inventory Planner → Settings → Connect Store)
2. Inventory Planner pulls sales history from BigCommerce and generates replenishment recommendations

**BigCommerce built-in low-stock alerts:**
1. Go to **Products → [Product] → Inventory**
2. Set "Low stock level" for each product — BigCommerce emails you when stock drops below this threshold
3. This is a simple alert, not a forecast — use it as a backstop while you set up a proper forecasting tool

### Step 3: Configure reorder points and safety stock

Reorder point = demand during lead time + safety stock buffer.

**In Inventory Planner:**
1. Inventory Planner calculates this automatically based on your sales history and supplier lead times
2. Review the recommendations in Inventory Planner → Replenishment — items are sorted by urgency (days of stock remaining vs. lead time)
3. Adjust recommendations manually before creating purchase orders (e.g., if you know a supplier has extra lead time for a specific product)