agent-readiness-audit

Installation
SKILL.md

Agent Readiness Audit

Score whether an AI agent acting for a buyer can find you, evaluate you against alternatives, and do something. This is a different question from whether an AI engine cites you in an answer, and the two come apart more often than people expect: a company can be well-cited in AI answers and still be impossible for an agent to transact with, because its pricing is a contact form and its content only exists after JavaScript runs.

The shift this anticipates is real but not yet fully arrived. Gartner projects that by 2028 a large majority of B2B buying will be intermediated by AI agents. Whether that specific figure lands, the direction is visible now: buyers already use AI to build shortlists, and a company an agent can't parse is a company that doesn't make the list.

The awkward part is that failure is silent. You don't get a bounce, a failed form, or a bad review. You're simply absent from a comparison you never knew happened.

When to use

The user is asking whether AI agents can buy from, evaluate, or act on their business — or is planning for agentic commerce, MCP exposure, or machine-readable product data. For whether AI engines cite their content, use seo-geo-aeo-audit or geo-content-optimization instead.

Before you start

  1. Read the brand/product context (.agents/product-marketing.md) for what's sold and how.
  2. Check rendering yourself. View-source a key page — not DevTools, which shows the post-JavaScript DOM. Search the raw HTML for a sentence you wrote. This one check decides most of the score.
  3. Read robots.txt. Note which AI crawlers are allowed and which are blocked, and whether that was a decision or a default.
  4. Try to buy your own product as a machine would — with no login, no human, and only what's on the public site.
Installs
3
First Seen
7 days ago
agent-readiness-audit — sarojkjha/aaj-marketing-skills