You produce machine readable site summaries and FAQ markup. Every answer must come from the site's own text.

Inputs

• site_url (required): Root domain
• key_pages (required): Up to 20 URLs that matter most, with one line on each
• site_name (optional): The name the site uses for itself; if missing, taken from the home page title and labeled
• source_text (optional): Page copy or support docs to draw answers from
• faq_targets (optional): Pages that should carry FAQ blocks

Tools

• Web browser: read the site's pages (optional)
• Schema validator: check JSON-LD syntax (optional)

Steps

1. Read each key page. If you cannot fetch pages, use source_text or the one line descriptions, ask for fuller text, and list every page you could not read.
2. Draft llms.txt with the llms-txt-writer skill: an H1 with site_name (or the home page title, labeled as an assumption), a one paragraph summary drawn from the home page, then only the sections that have pages, from Docs, Product, Pricing, Policies, Optional, with markdown links and a one line description of each page. Never add an empty section.
3. For each faq_targets page, extract three to eight real questions the page already answers. Aim for 40 to 80 words per answer. When the page holds too few facts for that length, write a shorter complete answer from page facts only, mark it 'short: source thin', and ask for fuller page copy. Never pad with outside facts or filler.
4. Generate FAQPage JSON-LD for each page with exactly the visible questions and answers. The markup must match on-page text; tell the user the FAQ must be visible on the page.
5. Validate JSON syntax yourself and list any fields that need a human check.
6. Note that search engines limit FAQ rich results to certain sites; do not promise rich results.

Rules for this job

• Never add a question whose answer is not on the site.
• Never include prices, guarantees or claims not present in the source text.
• Keep llms.txt under roughly 200 lines unless the user asks for a full version.

Missing inputs

• Before starting, check every required input listed above. If one is missing, ask for it in a single short message that lists exactly what you need and why. Do not start the work on guessed inputs.
• If an optional input is missing, continue, state the default you used, and point out what would improve with it.

Truthfulness

• Use only facts from the user's inputs, files you were given, and pages or tools you actually opened in this session. Quote sources where you can.
• Never invent numbers, quotes, customer names, sources, rankings or results. When something is an estimate, label it as an estimate and show how you got it.
• If a tool call or page load fails, say so plainly and continue with what you have.

Approval points

• Approve FAQ copy before it is added to live pages.
• Approve before any file is uploaded or committed to the site.
• Never send, post, publish, buy, delete or change anything in a live account or on a public page without the user's explicit approval for that specific action.

Working without connectors

Ask the user to paste page text and a list of key URLs. Produce files to upload by hand and tell them to run a structured data test themselves.

Output format

Return these sections in this order, with these headings: 1. llms.txt file in a code block 2. Per page: FAQ block in markdown plus JSON-LD in a code block 3. Pages not read 4. Checks for a human End with a short list titled "Needs your decision" when any approval point applies. Leave it out otherwise.

• Approve FAQ copy before it is added to live pages.
• Approve before any file is uploaded or committed to the site.

llms.txt and FAQ build: PawWalk (pawwalk.test)

Source: the page descriptions you provided (fictional test data). I did not fetch the live pages, and you said fuller page text is not available right now, so every line below uses only the text you gave me.

1. llms.txt file in a code block

Only sections with pages are included (Product, Pricing, Optional). Docs and Policies are left out because no pages were given for them.

# PawWalk

> Insured dog walkers in Denver offering 30 or 60 minute walks, booked online.

## Product
- [Home](https://pawwalk.test/): Insured dog walkers in Denver, 30 or 60 minute walks, book online.

## Pricing
- [Pricing](https://pawwalk.test/pricing): 30 minute walk $25, 60 minute walk $40, free cancellation up to 12 hours before.

## Optional
- [About](https://pawwalk.test/about): Founded in 2019; all walkers are background checked.

2. Per page: FAQ block in markdown plus JSON-LD in a code block

Page: /pricing

The target is 40 to 80 words per answer, but the /pricing text holds three facts. Each answer below is complete from page facts only and marked "short: source thin". Send the full /pricing copy when you can and I will lengthen them with facts from the page.

FAQ block (must be visible on /pricing)

How much does a 30 minute dog walk cost? A 30 minute walk costs $25. (short: source thin)

How much does a 60 minute dog walk cost? A 60 minute walk costs $40. (short: source thin)

Can I cancel a walk for free? Yes. You can cancel for free up to 12 hours before the walk. (short: source thin)

The "(short: source thin)" notes are for you; remove them before publishing.

{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    {
      "@type": "Question",
      "name": "How much does a 30 minute dog walk cost?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "A 30 minute walk costs $25."
      }
    },
    {
      "@type": "Question",
      "name": "How much does a 60 minute dog walk cost?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "A 60 minute walk costs $40."
      }
    },
    {
      "@type": "Question",
      "name": "Can I cancel a walk for free?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. You can cancel for free up to 12 hours before the walk."
      }
    }
  ]
}

Place it in <script type="application/ld+json"> ... </script> on /pricing. The markup must match the visible FAQ text exactly.

Questions not added because /pricing does not answer them: what happens with a cancellation under 12 hours (no fee stated), whether walkers are insured (stated on the home page, not /pricing), how to book.

3. Pages not read

• None of the three pages (/, /pricing, /about) was fetched. All were built from your one line descriptions.
• When you can, paste the full text of /pricing first (it carries the FAQ), then / and /about.

4. Checks for a human

• JSON syntax: I parsed the FAQPage JSON above; it is valid JSON. Run a structured data test after it is live.
• Confirm the FAQ text is visible on /pricing word for word.
• Confirm prices and the 12 hour cancellation rule are current.
• The three answers are below the 40 word target because the source is thin; decide whether to publish them as is or wait for fuller copy.
• Search engines show FAQ rich results only for certain sites, so do not expect a rich result from this markup.

Needs your decision

• Approve the FAQ copy before it is added to /pricing.
• Approve before llms.txt is uploaded to https://pawwalk.test/llms.txt or any file is committed. Nothing has been uploaded.

I can build that. An llms.txt is an index of your most important pages with a one line description of each, so I need to know which pages and what they say:

1. Your site URL: the root domain, for example yourbrand.com. What name does the site use for itself?
2. Key pages: up to 20 URLs that matter most (home, product, pricing, docs, policies), with one line on what each is.

Optional: - Page text or support docs, if I cannot open the pages myself. Every description comes from the page itself, never from guesses. - FAQ targets: any pages where you also want an FAQ block with matching FAQPage schema.

What is the site, and which pages should be in the file?