AutoGineer
Generated banner for Inventory Planner
Generated logo for Inventory Planner

Inventory Planner

AnthropicOfficialPublished by Anthropic

  • Skill
  • Workflow
  • Business and productivity
  • Apache-2.0
  • No issues found
Download ZIP

From the author

Works out what to reorder and when, from what is actually selling: pulls sales history and stock on hand from Shopify, Square, NetSuite, or an uploaded CSV, computes 7-day and 28-day sales velocity per item, projects a conservative stockout date for each, sizes a 60-day reorder quantity, and drafts the purchase orders and vendor emails to cover it. Flags the money sitting still too — overstock, dead stock, and zero-velocity items, reported as slow movers to clear rather than things to buy more of. Seasonality is applied where the history supports it and named where it does not. Nothing is ordered and no vendor is emailed without approval. Reach for this whenever stock comes up — "what do I need to reorder," "am I going to run out," "what should I order this month," "we keep running out of filters," "how much cash is sitting in the warehouse," "what is not moving," or "draft a PO for my supplier."
— the description by Anthropic

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Inventory Planner helps businesses optimize stock levels by analyzing sales history and current inventory. It calculates sales velocity over 7-day and 28-day windows to project stockout dates and determine appropriate reorder quantities. The skill distinguishes between items that need replenishment and those that are stagnant, providing clear visibility into cash tied up in overstock or dead stock. It supports data ingestion from major platforms like Shopify, Square, and NetSuite, or via CSV, and ensures all purchase orders and vendor communications are reviewed and approved by the user before execution.

What it does

  • Computes 7-day and 28-day sales velocity to identify trends.
  • Projects conservative stockout dates based on current inventory and demand.
  • Sizes 60-day reorder quantities while accounting for lead times and inbound stock.
  • Flags overstock, dead stock, and zero-velocity items to improve cash flow.
  • Drafts professional purchase orders and vendor emails for user approval.
  • Applies seasonal adjustments only when sufficient historical data is available.

When to use it

  • When you need to determine which items to reorder to prevent stockouts.
  • When you want to identify stagnant inventory that is tying up cash.
  • When preparing to place orders with suppliers and needing draft documentation.
  • When you need a clear report on warehouse cash value and stock health.

Advantages

  • Prevents lost sales by identifying items nearing stockout status.
  • Reduces capital tied up in dead or slow-moving inventory.
  • Ensures reorder quantities are based on actual sales data rather than guesswork.
  • Provides transparency into the reasoning behind every reorder recommendation.
  • Maintains control by requiring explicit approval for all financial commitments.

Usage examples

“What do I need to reorder this month?”
The agent analyzes your sales history and current stock to present a prioritized list of items to reorder, including quantities and estimated costs.
“How much cash is sitting in the warehouse?”
The agent identifies slow-moving and dead stock, calculating the total dollar value of items that are not currently generating sales.
“Draft a PO for my supplier.”
The agent generates a purchase order and a corresponding vendor email based on your current stock needs for your review and approval.
“Am I going to run out of filters?”
The agent checks the sales velocity and current stock of your filters to report if you are at risk of a stockout and if there is still time to reorder.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/anthropics/inventory-planner/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip inventory-planner.zip -d .agents/skills

Documentation by Anthropic

Inventory Planner

Buy what sells, before it runs out, and stop buying what doesn't.

Stock is cash the owner already spent. Two things go wrong: running out of the item customers came for, and sitting on a pallet of something nobody wants. Both are visible in the sales history well before they become a problem, which is what this skill reads for.

Step 1 — Get sales and stock

Preferred: Shopify for sales and inventory levels. Square and NetSuite work the same way.

Fallback, fully supported: a CSV of sales history plus a stock-on-hand count. Two files, or one with both. This path works with zero connectors and gives the same output. Many businesses count on a clipboard, and that is a legitimate input.

You need, per item: SKU, name, units sold by date, current stock on hand, unit cost, unit price, vendor, and lead time if known. Missing lead time is asked for once and remembered — see reference/data_sources.md.

Say what the count is as of. A stock figure two weeks old produces a stockout date two weeks wrong.

Step 2 — Compute velocity, both windows

For every item, compute:

  • 7-day velocity — units per day over the last week. Catches what is happening now.

  • 28-day velocity — units per day over four weeks. The stable baseline.

Both matter, and disagreement between them is information. An item selling three times its 28-day rate this week is either trending or had one bulk order, and those need different responses. reference/velocity_and_reorder.md covers how to tell them apart.

Exclude one-off distortions from the baseline where you can identify them: a single wholesale order, a returned batch, a stockout period where the item could not sell. A period of zero sales because there was no stock is not zero demand, and treating it as such is how an item gets under-ordered forever.

Step 3 — Project stockout dates, conservatively

Stockout date is stock on hand divided by the daily velocity you trust least — the higher of the two windows. Being early is cheap; being late loses the sale.

Then compare against lead time. The number that matters is not when it runs out, it is whether there is still time to order:

  • Past the point of no return — lead time exceeds days of cover. Already going to stock out. Say so plainly.

  • Order now — cover is within lead time plus a safety buffer.

  • Order soon — comfortable, but on the next cycle.

  • Fine — no action.

Never state a stockout date for an item with no reliable velocity. New items with two weeks of history and items whose sales were interrupted get flagged as "not enough history," by name.

Step 4 — Size the reorder

Default target is 60 days of cover plus the lead time, sized on the 28-day rate — not on the faster of the two. The stock has to last from the day it lands until the next order lands, so leaving the lead time out runs the item short by exactly that many days every cycle. Then adjust for pack size, minimum order quantity, and what is already on order.

The two rates do different jobs and both get named on the line: the higher one says when it runs out, the 28-day one says how much to buy. Sizing a 60-day order off a one-week spike is how cash ends up in a pallet.

Never size a reorder without subtracting inbound stock. Double-ordering a slow item is how a business ends up with three years of it.

Round to the vendor's pack size and say which direction you rounded. Show the dollar cost of every recommendation — the owner is deciding about cash, not units.

Step 5 — Handle the items that are not moving

Zero-velocity and very slow items are a separate list with a separate purpose. They are never reorder candidates.

  • Zero velocity — no units in 28 days. Report as a slow mover with the cash tied up in it. Never compute days of cover for these — nothing is selling, so nothing is running out, and the number is either an error or nonsense. The one exception is an item inside a season the owner has named, which goes on a dated watch list instead of the clear-out list.

  • Overstock — more than 120 days of cover. Report the excess units and the dollars.

  • Dead stock — no movement in 90 days. Suggest clearing, bundling, or discounting.

Total the cash sitting in these. That figure is usually the most surprising number in the whole report and often the most useful one.

Step 6 — Apply seasonality only where history supports it

With at least a year of history, compare the coming period against the same period last year and adjust.

With less than a year, say so and do not adjust. A seasonal multiplier invented from nine months of data is a guess wearing a suit. Ask the owner instead — they know their season better than a short history does. reference/seasonality.md covers both paths.

Step 7 — Present the buy list

Lead with the total dollar amount and the count of items about to stock out. Then: order now, order soon, slow movers, and anything with too little history to judge.

Every line carries the numbers behind it — velocity, days of cover, lead time, quantity, cost. An owner who can see the reasoning approves in a minute; one who cannot rebuilds the whole thing by hand.

Render the buy list as an HTML artifact using the house artifact style (../../shared/artifact-style.md): a stockout table sorted by stockout date with mono tabular-nums numerals, urgency status pills (order now / order soon / fine / past the point of no return), a reorder panel with quantities and dollar totals, and a slow-movers section with the cash tied up in it. The chat summary stays — the artifact is the full picture, not the only one.

Step 8 — Draft POs and vendor emails, with approval

Purchase orders commit money and vendor emails go out under the owner's name, so both wait for an explicit yes.

State the vendor, the line items, and the total before asking. Draft the vendor email in the owner's voice per the shared voice profile. If no profile exists yet, follow that file's "When there is no sample" instruction — ask for three emails they have already sent a supplier. If they would rather not, write the email plain and neutral and say it is not in their voice. Never invent a personality for someone's vendor relationship.

With Google Calendar connected, offer a recurring block for the restock decision — this works far better as a rhythm than as a fire drill. Keep the approved PO document here — this skill owns it. With QuickBooks or NetSuite connected, hand ap-processor the coded memo for each one (vendor, PO number, total, expected date, and the account, class, and job), so the bill three-way-matches against a real record when it arrives. ap-processor reads POs; it does not create them.

Closing offer

Close with one line on what was decided — the total buy and the items about to run out. Then offer the most relevant next step with its exact trigger phrase: "reorder" (/restock) when the owner wants the POs drafted and sent end to end. Up to two more from the router's table, such as "cash forecast" (cash-flow-snapshot) or "pay the bills" (/pay-the-bills). Three offers at most, and never repeat one the owner already declined this session.

What not to do

  • Do not invent a velocity, a lead time, or a stockout date. Too little history is reported by SKU, not smoothed over.

  • Do not treat an out-of-stock period as zero demand. It is suppressed demand and it biases everything downstream.

  • Do not recommend reordering a zero-velocity item. No sales means stop buying, not buy more.

  • Do not size a reorder without subtracting what is already inbound.

  • Do not apply seasonality without a year of history. Ask the owner instead.

  • Do not send a PO or a vendor email without approval. Both spend money or spend goodwill.

  • Do not report units without dollars. The owner thinks in cash.

Reference files

  • reference/data_sources.md — Shopify, Square, NetSuite, and the CSV path, with required fields

  • reference/velocity_and_reorder.md — the 7/28-day math, distortion handling, and reorder sizing

  • reference/seasonality.md — when to adjust, when to ask, and how to say which you did

  • reference/po_drafting.md — purchase order structure and vendor email drafting

  • reference/gotchas.md — the mistakes that stock out a bestseller or bury cash in a pallet

Using a tool that isn't listed

The connectors named in this skill are the tested paths, not a wall. If the owner wants this flow to use a tool that isn't connected or listed, offer build-connector — it checks the connector directory first and connects through Zapier otherwise, never hand-building against a raw API. Once the connection exists, the tool joins this skill like any other optional connector, under the same approval gates.

Files

reference/seasonality.md

Seasonality

When to adjust for the season, when to ask instead, and how to say which you did.

The threshold

Adjust only with at least 400 days of history. That gives a full year plus enough overlap to compare the same weeks year over year.

With less than that, do not compute a multiplier. Ask the owner.

The reason is simple: a seasonal factor derived from nine months of data is arithmetic performed on an assumption. It comes out looking like a real number — "1.6x for June" — and it will be used to buy real stock. The owner already knows their season better than that number does, and asking takes one line.

With a year or more

Compare the upcoming planning window against the same calendar window last year, per item or per category.

seasonal_factor = units_sold(same window, last year) ÷ units_sold(trailing 28d, last year)

Apply the factor to the sizing velocity (the 28-day rate), and to the stockout velocity when projecting into the season. Cap it — anything above 3x or below 0.3x gets shown to the owner rather than applied silently, because factors that extreme usually mean a promotion, a stockout, or a one-time event in last year's data rather than a real season.

Prefer category-level factors for items with thin individual history. A single SKU's year-ago numbers are noisy; the category's are not.

Check for a stockout in last year's comparison window. If the item was out of stock last June, last June's units understate demand, and the factor built from them will under-order this June. Say so instead of applying it.

Without a year

Say what you have and ask one question:

I have 120 days of history, so I cannot see your season in the data. You are heading into summer — do filters and capacitors move differently for you then? Give me a rough multiple and I will size the order to it. Otherwise I will plan on the current rate and we adjust as it moves.

Then use whatever they say and label the buy list with where the number came from:

Sized at 1.8x current velocity per your estimate, not from history.

That label is what lets the owner recalibrate next quarter. An unlabeled adjusted number is indistinguishable from a computed one six weeks later.

When the owner names an end to the season

A season has two dates and the second one does the damage. Sizing 60 days of stock at the busy rate, six weeks before the busy period ends, buys a month of stock for a month that will not happen — and it stays on the shelf until next year at the old cost.

When the owner names an end date, cap the order at the days left in the season. Do not cap silently:

days_left       = season_end_date − expected_arrival_date
target_uncapped = (60 + lead_time_days) × sizing_velocity
target_capped   = days_left × sizing_velocity

Show both numbers and say which one is being ordered:

Ray says the AC season winds down at the end of August — 47 days after this order lands, not 60. At 7.0/day with 20 on hand, that's 309 units, so 8 cases: USD 1,184. The uncapped number would have been 11 cases at USD 1,628 — the extra three cases would sit until next May.

The owner overrides this whenever they want to. Some items are worth carrying over — a filter keeps fine and the price only goes up. Others do not, and a slow tail into the off-season is exactly where the cash gets stuck. Their call, made with both numbers in front of them.

Carrying a few days of tail past the end date is fine when the owner asks for it — say the sentence, do not add it silently.

Where the season ends before the stock could even land, do not order at all. Say so plainly and put the item on the watch list for next season with the decide-by date already on it.

Known-event adjustments

Seasonality is not only the calendar. Ask about, and record:

  • A big job, contract, or event coming up that will draw down stock

  • A promotion or sale planned

  • A vendor price increase announced, which sometimes justifies buying early

  • A vendor shutdown — many suppliers close for a stretch and lead times double around it

These are one-time adjustments, applied to specific items, and always labeled as owner-supplied rather than computed.

Reporting the adjustment

Every seasonally adjusted line shows both numbers:

Compressor, 3-ton                SKU CMP-3T
  Current velocity   0.4/day (28d)
  Seasonal           1.9x — June ran 1.9x the spring rate last year
  Sizing at          0.76/day
  On hand            11 units, 14 days of cover at the seasonal rate
  Status             ORDER NOW

Showing the unadjusted rate next to the adjusted one is what makes the adjustment reviewable. An owner who thinks 1.9x is too hot can say so before the PO goes out.

Worked example

Ray's shop, planning into June.

  • 120 days of history only. No computed factors.

  • Asked Ray directly. His answer: "Filters and capacitors go crazy the first hot week. Compressors maybe double. Everything else is the same."

  • Applied 2.0x to filters, capacitors, and compressors on Ray's estimate. Everything else planned at the current 28-day rate.

  • Buy list labeled: three categories sized on Ray's seasonal estimate, the rest on trailing velocity.

  • Noted for next year: with a full year of history by next spring, these factors can be computed and checked against what he guessed.

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Anthropic
Publisher
Anthropic (Official)
Source
anthropics/knowledge-work-plugins · small-business/skills/inventory-planner · commit e050c2e
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Anthropic or Anthropic.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download inventory-planner.zip