Readiness audit

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

Canonical agentic commerce skills, aggregated by wakqasahmed/skills

Install

npx -y skills add wakqasahmed/agentic-commerce-skills --skill readiness-audit

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

Route an ecommerce storefront through an Agentic Commerce readiness audit. Use when assessing whether a store should move to Custom Agent, Verified Audit, Forward Deployed Engineering, or Not Qualified.

SKILL.md

3.5 KB, as published. Nobody here has run it

Readiness Audit

Workflow

Confirm the submitted URL is a public production storefront.
Score each dimension below from public signals only, citing at least one URL or check per score.
Label evidence as public-signal only unless verified exports are explicitly provided.
Route using the thresholds, then state next steps and limitations.

Scoring rubric

Score each dimension 0-3.

Dimension	0	1	2	3
SEO basics	Not indexable, or robots/canonical broken	Indexable but thin metadata, weak internal links	Solid metadata and sitemap, minor gaps	Clean indexing, canonicals, sitemap, crawlable pages
AEO/GEO content	No answerable content	Some FAQ or policy text, buried or vague	Clear FAQs, policies, comparisons on stable URLs	Rich answer-shaped content with evidence and dates
Product knowledge	No structured data, sparse product copy	Partial attributes, no variants or availability	Product schema with price and availability, variant gaps	Complete attributes, variants, stock, offers in structured data
Agent access	Crawlers or AI bots blocked	Accessible but client-side-only rendering	Server-rendered content and sitemap, no agent affordances	Explicit affordances: `llms.txt`, feeds, or API/protocol paths
Policy/support	Policies missing or contradictory	Policies vague on returns, shipping, refunds	Clear policies and findable support channels	Policies precise enough for an agent to answer or act on
Commerce/action readiness	No bounded actions possible	Checkout works for humans only	Supervised cart/checkout with bounded actions, explicit policy and escalation; trust, authority, or lifecycle verification remains incomplete	Tested protocol or API ordering path with verified agent identity, scoped delegated authority, secure payment handoff, retry safety, and authenticated order lifecycle

An advertised protocol or API endpoint alone cannot score 3. For action-capable goals, missing agent verification or delegated authority caps this dimension at 2; use commerce-protocol-readiness for the underlying trust and lifecycle evidence. This refines the existing dimension without changing dimensions or routing thresholds.

Routing thresholds

Any dimension at 0, or total ≤ 6 → Not Qualified. Fix blocking gaps first; hand off to ai-search-remediation-plan.
Total 7-11 → Verified Audit. Signals are mixed; verified exports (Search Console, analytics, order data) are needed before recommending a build.
Total ≥ 12 with agent access ≥ 2 and policy/support ≥ 2 → Custom Agent. Hand off to custom-agent-remediation-plan.
Total ≥ 12 but a standard setup cannot cover the platform, protocol, or integration gaps → Forward Deployed Engineering. Confirm with fde-opportunity-map.

A worked example with scores, evidence, and routing is in references/example-audit.md.

Guardrails

Do not imply access to Search Console, analytics, revenue, logs, rankings, or conversions unless the user provided verified exports.
See ../references/guardrails.md for shared cross-skill guardrails (autonomous action safety, evidence provenance, internal runtime disclosure).
Prefer practical remediation over generic score commentary.