Install
$ agentstack add skill-wakqasahmed-agentic-commerce-skills-commerce-protocol-readiness ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Commerce Protocol Readiness
Workflow
- Classify the commerce goal: discovery only, assisted checkout, native agent checkout, account linking, order support, paid API/tool access, or machine-to-machine payment.
- Check public discovery signals: documented API catalog,
.well-knownendpoints, MCP server card, A2A agent card, WebMCP, Agent Skills, link headers, and developer docs. - Check checkout readiness: cart creation, pricing/tax/shipping recalculation, inventory reservation, checkout session handoff, order confirmation, returns/refunds, and support escalation.
- Map protocols to the goal:
- ACP: agent-initiated checkout where the merchant remains merchant of record.
- UCP: broader lifecycle coverage across search, cart, identity linking, checkout, order, and post-purchase support.
- AP2: cryptographic payment authorization and user-consent proof.
- x402 or MPP: paid API requests, content access, tool calls, or machine-to-machine payments.
- MCP: exposing merchant tools, catalog lookup, policy lookup, support tools, or order tools to agents.
- A2A: delegating work between agents using explicit capabilities.
- Score each protocol as
not applicable,missing,partial,ready, orverified, with evidence. - 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.
- See
../references/guardrails.mdfor shared cross-skill guardrails (autonomous action safety, evidence provenance, internal runtime disclosure).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: wakqasahmed
- Source: wakqasahmed/agentic-commerce-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.