anthropics/commerce-agents.

catalog-listings

Creating and improving listing content, covering titles, descriptions, attribute completeness, categorization fixes, image callouts written as text, edits written from material the operator supplies, and content-quality audits and bulk fixes across many listings. Not needed for questions about how a listing is performing.

commerce-architecture

How the reference commerce agents of either role are structured, covering the loop, where each rule lives, skills, the backend interface, delegates, and model fields. Load when designing or reviewing the structure of a shopping or merchant agent.

commerce-evals

Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures. Load when writing eval cases or rubrics or deciding how a suite runs.

commerce-merchant-operations

The reference merchant agent, covering its flows, staged changes and host approval, metrics grounding, the analysis delegate, store memory, components, and marketplace rules. Load when building or reviewing an agent for the operators of a store, property, subscriber base, or venue.

commerce-prompt-caching

The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are prompt bytes, and verification. Load when writing or reviewing a commerce agent's prompt assembly, when cache reads are zero, or when a turn's latency or cost is the question.

commerce-trust-safety

The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules. Load when handling untrusted tool results, guarding a write tool, or scoping what an agent remembers.

commerce-ui-tools

The reference presentation-tool contract, covering server-side enrichment, suggestion chips, the event stream, progressive rendering, both roles' built-in components, and adding a vertical component. Load when building or reviewing how a commerce agent's output reaches a frontend.

customer-care

Help after a purchase or booking, covering the status of an order or delivery whether or not the customer names it, returns, refunds, exchanges, and cancellations, an item that arrived damaged, incomplete, or late, and questions about the store's terms or a membership. Not needed for finding, comparing, or choosing something new.

inventory-operations

Stock, capacity, and availability monitoring, acting on low-stock and slow-mover alerts, triaging order exceptions such as delays, return spikes, and complaints, and the operator's daily briefing; any start-of-day or what-needs-attention rundown is this flow, presented as a digest. Not needed for performance questions with no operational action attached.

marketing-campaigns

Drafting campaigns and ads as staged drafts, from acquisition and seasonal pushes to lifecycle sends such as win-backs, pre-arrival messages, and presale or last-call notices, choosing audiences and placements by intent, allocating budget across campaigns, and reviewing campaign results with their attribution caveats. Not needed for listing copy (catalog-listings) or overall performance questions (performance-insights).

memory-personalization

Requests about what is remembered, however short, from an ask to remember one thing to asks to say what is on file, correct it, or forget it; a bare save or an answer from the profile alone does not cover these. Also applying what the store already knows, recalling an older fact (a past recipient, a size, a recurring order) when it would change the pick, and deciding what should outlast the session. Not needed when the request carries no personal context to apply or keep.

performance-insights

Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.

planning-goals

Planning a coordinated set of items toward a goal, an event, a trip, or a project, where the request only comes together as several purchases with a structure between them, and later changes to a plan you have presented. Not needed when the customer wants a single item, however carefully chosen.

pricing-promotions

Price changes within the store's guardrails, rate recommendations from demand, occupancy, or sell-through pace, promotions with their scope, depth, and dates, the markdown option for stock or capacity that is not selling, and the margin preview before any of it is staged. Not needed for explaining why revenue moved (performance-insights) or writing promotional copy (marketing-campaigns).

purchase-research

Teaching a customer how to choose before any candidates appear, when they ask what matters in a category, how two approaches to it differ, or where to begin. Not needed once the customer has named the thing they want, however considered the purchase (that is search work), nor for outfitting a space or an event (planning-goals).

search-discovery

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Not needed when one search for the thing the customer named answers the request, or when the customer wants to learn what matters in a category first (purchase-research).