agentsclimarketplace

Commerce protocol readiness

Skill wakqasahmed/agentic-commerce-skills/skills/agentic-commerce/commerce-protocol-readiness

Canonical agentic commerce skills, aggregated by wakqasahmed/skills

Install
npx -y skills add wakqasahmed/agentic-commerce-skills --skill commerce-protocol-readiness

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Audit an ecommerce storefront for agentic commerce protocols and action readiness. Use when checking ACP, UCP, AP2, x402, MPP, MCP, A2A, OAuth, checkout, order, and payment readiness.

SKILL.md

3.1 KB, as published. Nobody here has run it

Commerce Protocol Readiness

Workflow

  1. Classify the commerce goal: discovery only, assisted checkout, native agent checkout, account linking, order support, paid API/tool access, or machine-to-machine payment.
  2. Check only discovery signals defined by the protocol in scope: documented API catalogs, UCP business profiles, A2A Agent Cards, MCP authorization metadata, WebMCP tools in a supporting browser, Agent Skills, link headers, and developer docs. [SRC-UCP] [SRC-A2A] [SRC-MCP] [SRC-WEBMCP]
  3. Audit trust before action readiness. Identity and authority are independent checks: agent identity, user identity, delegated authority, payment authorization, and merchant policy do not substitute for one another. Use references/trust-and-order-lifecycle.md for the evidence gates.
  4. Check the complete checkout and order lifecycle: merchant-authoritative price, tax, shipping, and inventory recalculation; expiry and escalation; secure payment handoff; confirmation; authenticated events; cancellation, return, and refund boundaries; retry safety; and reconciliation. [SRC-UCP] [SRC-AP2]
  5. Map protocols to the goal:
    • ACP: agent-assisted discovery and checkout using the merchant's published feed and API artifacts. [SRC-ACP]
    • UCP: commerce lifecycle capabilities negotiated from the business profile at /.well-known/ucp. [SRC-UCP]
    • AP2: signed checkout and payment mandates that prove authorization for agent-performed payments. [SRC-AP2]
    • x402: HTTP 402 payment challenges for paid APIs or content. [SRC-X402]
    • MPP: HTTP machine payments for API requests, tool calls, or content. [SRC-MPP]
    • MCP: exposing merchant tools, catalog lookup, policy lookup, support tools, or order tools to agents; protected HTTP servers advertise authorization through OAuth metadata. [SRC-MCP]
    • A2A: delegating work to agents whose capabilities and interfaces are described by an Agent Card. [SRC-A2A]
    • WebMCP: exposing page tools through the draft browser document.modelContext API, not through a site-wide manifest. [SRC-WEBMCP]
    • Trusted Agent Protocol: verifying agent identity and commerce intent from signed HTTP requests; it is not a crawler allowlist by itself. [SRC-TAP]
  6. Score each protocol as not applicable, missing, partial, ready, or verified, with evidence. Endpoint or profile advertisement is discovery evidence only; it cannot establish action readiness.
  7. Recommend the smallest next implementation that improves buyer value and merchant control.

Guardrails

  • Do not treat a protocol as required just because it exists. Tie it to a concrete customer or agent workflow.
  • Do not recommend autonomous payments without identity verification, consent capture, audit logs, fraud controls, and human escalation.
  • See ../references/guardrails.md for shared cross-skill guardrails (autonomous action safety, evidence provenance, internal runtime disclosure).

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.