Home

/

Claude Skills

/

Merchandiser

Merchandiser

by

  • MERCHANDISING
  • ASSORTMENT
  • WEEKLY
  • ECOMMERCE
Works with the AI tools you already use
+19 agents

Weekly assortment review for ecommerce teams: rank each SKU on margin, stock cover and sell-through, then set promote, bundle or deprioritize with the reason.

The weekly merchandising meeting usually runs on last week's best sellers, which is a list of what already worked rather than a decision about what to do next. Promoting the top seller is rarely the best available move: it was going to sell anyway, it is often the thinnest margin in the range, and the promotion spends attention that a slower SKU with three months of cover needed more. This skill ranks the assortment on margin, stock cover and sell-through together, then sets promote, bundle or deprioritize per SKU with the reason attached.

What It Does

  • Ranks each SKU on contribution margin rather than on units sold.
  • Reads stock cover so the promotion does not sell out what cannot be replaced.
  • Detects sell-through slowing before the stock position makes it obvious.
  • Finds the pairs that bundle well from actual basket composition.
  • Separates the SKU that needs attention from the one that needs discounting.
  • Sets promote, bundle or deprioritize per SKU, with the reason recorded.

Use Cases

  • Stop promoting the bestseller that would have sold without the placement.
  • Find the high margin SKU sitting on four months of cover.
  • Build a bundle from what customers already buy together rather than from intuition.
  • Give the weekly meeting a decision per SKU instead of a leaderboard.

Example Session

What should we promote this week, and what should we stop pushing?

Your bestseller is the wrong thing to promote. It is 22% margin with three weeks of cover.

  • SKU | Units, 7d | Margin | Cover | Sell-through | Action
  • Core tee, black | 310 | 22% | 21 days | Steady | Deprioritize
  • Jacket, navy | 44 | 61% | 118 days | Slowing | Promote
  • Cap, charcoal | 96 | 54% | 62 days | Steady | Bundle with tee
  • Hoodie, gray heather | 71 | 48% | 34 days | Accelerating | Hold

The navy jacket carries the most margin in the range and nearly four months of stock, which makes it the only SKU where promotion changes anything. The black tee sells itself and will be short in three weeks. The cap bundles because 38% of tee orders already contain one, so the bundle formalizes a basket that exists rather than inventing a reason to discount.

Why This Beats Prompting It Yourself

Units Sold vs Margin And Cover Together: The Hidden Risk

A generic prompt promotes what is selling, because units sold is the ranking every report puts first. Promoting a 22% margin SKU with three weeks of cover spends your homepage on the item least able to absorb the demand and least worth the sale. It also looks like a success afterwards, because the promoted SKU sold well.

When You Still Need The Basket Behind The Bundle

Bundles fail when they are invented. This skill reads that 38% of black tee orders already contain a charcoal cap and proposes the bundle those customers are assembling themselves, which converts without teaching anyone a new behavior. A bundle built from intuition has to create the habit first, and usually funds the attempt with a discount.

Known Limitations

Sell-through trends need several weeks per SKU to be meaningful, so a newly launched product is reported as insufficient history rather than ranked against established ones. Margin depends on landed cost being current, and SKUs whose cost predates a recent freight or duty change will rank optimistically. It sets the merchandising decision and does not update your storefront.

Install It

  • Download the ZIP.
    It is free and there is no account to create.
  • Unzip it into your agent's skills folder.
    Claude Code reads ~/.claude/skills/, which is hidden by default: the command in the folder block opens it. Other agents scan their own directory, so drop the same folder there instead.
  • Ask your agent to use it.
    Restart the agent if it was already running, then it picks the skill up with no config.

skills folder

Copy

~/.claude/skills/merchandiser/
  SKILL.md
  references/assortment-rules.md
  weekly/
  # one file per week, with the decision per SKU

# macOS: create the folder and open it in Finder
mkdir -p ~/.claude/skills && open ~/.claude/skills

# Windows: paste in the Explorer address bar
%USERPROFILE%\.claude\skills\

Frequently asked questions

How is this different from a bestseller report?

A bestseller report ranks by units, which is a description of the past. This ranks by margin, cover and sell-through together and returns an action per SKU, which frequently means deprioritizing the top seller and promoting something in fourth place.

Which agents does the skill run in?

Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision.

What does it need connected to work?

Order lines with quantities, product cost, stock on hand, and inbound purchase orders. Basket composition comes from the order lines, so bundle recommendations need no separate setup.

Why deprioritize something that is selling well?

Because promotion is a finite resource and a SKU that sells without it does not need it. Spending a homepage slot on an item already at capacity produces no incremental revenue and creates a stockout on your most visible product.

Does it recommend discounts?

Rarely, and never as the first move. Promotion, placement and bundling change demand without giving up margin, and the skill exhausts those before it suggests price. Where a discount is genuinely the answer it states the margin given up.

What is included with the skill?

The skill itself, the assortment rules reference, the weekly decision format, and the bundle detection thresholds. It is free and security scanned. We re-publish the ZIP when the rules change, so download it again if your rankings start shifting.

Promote, bundle or deprioritize is a margin and stock call.

Polar joins contribution margin to stock cover on one definition, so the SKUs you push forward are the ones you can profitably ship.

Book a demo

Popular in E-commerce

<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from a bestseller report?","acceptedAnswer":{"@type":"Answer","text":"A bestseller report ranks by units, which is a description of the past. This ranks by margin, cover and sell-through together and returns an action per SKU, which frequently means deprioritizing the top seller and promoting something in fourth place."}},{"@type":"Question","name":"Which agents does the skill run in?","acceptedAnswer":{"@type":"Answer","text":"Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision."}},{"@type":"Question","name":"What does it need connected to work?","acceptedAnswer":{"@type":"Answer","text":"Order lines with quantities, product cost, stock on hand, and inbound purchase orders. Basket composition comes from the order lines, so bundle recommendations need no separate setup."}},{"@type":"Question","name":"Why deprioritize something that is selling well?","acceptedAnswer":{"@type":"Answer","text":"Because promotion is a finite resource and a SKU that sells without it does not need it. Spending a homepage slot on an item already at capacity produces no incremental revenue and creates a stockout on your most visible product."}},{"@type":"Question","name":"Does it recommend discounts?","acceptedAnswer":{"@type":"Answer","text":"Rarely, and never as the first move. Promotion, placement and bundling change demand without giving up margin, and the skill exhausts those before it suggests price. Where a discount is genuinely the answer it states the margin given up."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the assortment rules reference, the weekly decision format, and the bundle detection thresholds. It is free and security scanned. We re-publish the ZIP when the rules change, so download it again if your rankings start shifting."}}]}</script>