Skip to main content

Agent Skills

Agent Skills are SKILL.md guidance files — one per domain — that teach your agent which command to run for each task, along with the domain's fields, boundaries, and safety rules. The CLI works without them, but skills make your agent significantly more accurate.

Install​

One command installs the skills for the agent you already use. For the per-agent commands and how to confirm they loaded, see Get started → Add the Agent Skills.

The same skills are also compiled into the CLI binary, so an agent can read the version that matches the installed CLI without installing anything: shoplazza skills list lists them, and shoplazza skills read <name> prints one (start with shoplazza skills read shoplazza-common). Once the skills are installed in ~/.agents/skills/, shoplazza update refreshes them along with the CLI.

Available skills​

DomainSkillCovers
Foundationshoplazza-commonAuth and profiles, command layers, output envelope, schema introspection, reading filtered lists, and the safety protocol. Every other skill has the agent read it first.
Productsshoplazza-productsCreate / price / stock / tag / publish products, variants, collections, images, gift cards, reviews, locations, suppliers
Discountsshoplazza-discountsTiered rebates, coupon codes, flash sales, buy X get Y, free-shipping codes, coupon campaigns
Ordersshoplazza-ordersSearch, fulfill, refund, update tracking, cancel, mark paid, transactions, fraud risk, shipping zones
Customersshoplazza-customersCustomer profiles, tags, marketing subscription, addresses
Shopshoplazza-shopStore settings, metafields, media, analytics, blogs, pages, redirects, markets, languages
Themesshoplazza-themesPage and card editing, theme settings, app embeds, custom templates, AI-generated blocks, installed themes (not local theme development)
Webhookshoplazza-webhookEvent subscriptions
Billingshoplazza-billingApp charges: one-time, recurring, and usage

How to invoke a skill​

Prefix your request with /shoplazza-<domain>, then describe the task in plain language:

/shoplazza-products Add a new product: Summer print T-shirt, priced 129

The prefix loads that domain's commands and notes into context before the agent acts.

tip

The prefix is not mandatory — each skill also has built-in trigger words — but stating it explicitly is more deterministic. The docs use /shoplazza-<domain> consistently for that reason.

Pick the right domain​

Each skill owns exactly one domain. Match the task to the domain:

TaskSkill
Create / price / restock a product, gift cards/shoplazza-products
Tiered discount, coupon code, flash sale/shoplazza-discounts
Ship, refund, or look up orders/shoplazza-orders
Customer profiles and addresses/shoplazza-customers
Store settings, metafields, media, analytics/shoplazza-shop
Store page and card editing, theme settings, templates/shoplazza-themes
Event subscriptions (webhooks)/shoplazza-webhook
App billing — one-time, recurring, usage/shoplazza-billing

Domain boundaries to watch​

Some tasks sit on a boundary between domains. The skills route them like this:

  • Gift cards live in products, not discounts.
  • Orders by customer email are searched in orders; the customer profile itself is in customers.
  • Buyer refunds live in orders, not billing.
  • Page and card editing lives in themes; the content of custom pages and blogs stays in shop.

The safety protocol​

The foundation skill shoplazza-common sets a safety protocol for destructive (cancel, delete), batch, and money-moving writes such as refunds and charges:

  1. Preview — run the command with --dry-run to print the request without sending it.
  2. Restate — summarize what the operation will change.
  3. Confirm — wait for your explicit confirmation before executing.

Other writes, such as creating a product or discount with a + shortcut, run directly once the required values are confirmed; the agent asks for a missing price or amount instead of inventing one. See the refund and delete examples for the protocol in action.

Next steps​