The mattpyle.com webmaster bronze

Ask about this site

Answers questions about mattpyle.com: who Matt Pyle is, what he has written and built, what has shipped recently, and which agent-readable surfaces the site exposes (agents.md, llms.txt, raw-markdown variants, WebMCP tools, this endpoint). Answers cite site URLs and are compiled from the site's own published content at build time, so they never contradict the pages themselves. One turn: the reply is a direct Message, and there is nothing to poll.

• What is this site about?
• Who is Matt Pyle?
• What has Matt written recently?
• What has shipped on this site lately?
• What agent-readable surfaces does this site expose?

Audit a site for agent-readiness

Audits any site you name for what it says about itself to agents: robots.txt and its AI-agent rules, Content Signals, the sitemap, llms.txt and whether its links resolve, agents.md, the well-known MCP and A2A discovery documents, and whether the homepage and a content page really serve markdown when asked for it. It checks behaviour rather than presence. Name a site and an audit verb, e.g. 'audit example.com', and say 'deep' for the browser-rendered tier that adds Lighthouse per-axis scores and axe-core violation counts from up to three of the site's own pages. The fast tier takes seconds and comes back as a direct Message carrying the report as markdown and as JSON. The deep tier takes minutes and comes back as a Task: poll GetTask with the task's id until its state is TASK_STATE_COMPLETED, and the report is the task's artifact, again as markdown and as JSON. The auditor obeys the target's robots.txt and arrives as steward-audit/0.2.0 (+https://www.mattpyle.com/steward), so one audit is one visitor in the ta

• Audit example.com
• Run an agent-readiness audit of https://example.com
• Run a deep audit of example.com, with Lighthouse and axe
• Scan example.com and tell me what it says to agents

The mattpyle.com webmaster

The webmaster of mattpyle.com, Matt Pyle's personal site about agent-led growth and emerging web standards. Two skills: it answers questions about the site (its writing, projects, changelog, scorecard, and agent-readable surfaces), and it audits any site you name for agent-readiness, returning the fast tier as a direct Message and the browser-rendered deep tier as a Task you poll to completion. Unauthenticated and public: no accounts, no payments, and no private data. Audits are rate limited, and the audito

steward-audit

Audits any website for agent-readiness over plain HTTP: robots.txt and its AI-agent rules, Content Signals, the sitemap, llms.txt and whether its links resolve, agents.md, the well-known MCP and A2A discovery documents, and whether the homepage and a content page actually serve markdown when asked for it. It checks behaviour rather than presence. Call audit_site(url): the checks take seconds and the report comes back in the same call, as canonical JSON in structuredContent and as a markdown summary in the t

implement-markdown-negotiation

Implement site-wide Markdown content negotiation, so every HTML page also answers `Accept: text/markdown` with a clean Markdown representation of itself. Covers the sibling URL rule, build-time conversion from the page's main landmark, edge negotiation with a fallback to HTML, and the traps that only surface in production: output roots, response headers, recursion, extraction, and registration drift. Use when adding Markdown representations to a site for AI agents, or when an agent-readiness check reports t

using-mattpyle-com

Work with mattpyle.com as an agent. Covers which discovery surface answers which question, fetching any page as Markdown instead of HTML, calling the site's A2A endpoint, using its in-browser WebMCP tools, and how to cite it. Use when reading, summarising, citing, or interacting with mattpyle.com.