Commerce Agents plugin for Grok Build

Skills (10)

• 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
• 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 su
• 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 s
• 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 writi
• 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 sco
• 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 co
• add-commerce-flow — Add one shopping or merchant flow to an existing commerce agent, copying its skill from the reference, wiring the tools it calls, and authoring its first eval cases. Use when an agent on the reference packages is to take on another of the f
• author-commerce-evals — Build an eval suite for a shopping or merchant agent, with a runner, the first ten cases against the user's own catalog, and a replay gate for CI. Use when an agent has a working flow and no measurements.
• review-commerce-agent — Map a shopping or merchant agent the user already runs or is building, compare it with the reference row by row, and convert the rows the user picks. Use when an existing commerce agent, assistant, or chatbot is to be reviewed, or its laten
• scaffold-commerce-agent — Interview the user about their stack, play the plan back, and scaffold a shopping agent, a merchant agent, or both on the reference packages. Use when a shopping or merchant agent, assistant, or chatbot is being started; one that exists alr