Inputs

• templates (required): Per template: name, pattern, page 1 URL, page 2 URL, next link HTML, page 2 canonical, items per page and total items if known
• params (required): Sort and filter parameters and how each is handled (noindex, robots.txt, nothing)
• goal (required): Which listings must have every item found by search

Tools

• Browser dev tools: read link markup, canonical and URL changes (optional)
• Screaming Frog SEO Spider: crawl paginated series (optional)

Steps

Rules for this job

• Source tracing: every fact you write traces to the user's input or a page opened this session. No invented dates, prices, numbers, names or psychology; use a [ADD: ...] placeholder and list it under Needs your decision.
• Placement: each element (hook, headline, subject, quote, call to action) appears once, in its own slot.
• Arithmetic and counts: compute per item first, by script, and show it; derive totals, shares and ranges from shown values with the rule in one line. Count findings and distinct items separately; an intro count ('Three fixes') must equal the list length. Every number in prose also appears in a table.
• Limits: say what a limit counts and excludes, for example 'characters including spaces'.
• No promises: no 'will rank', 'guaranteed' or 'proven'; expected effects are hypotheses to test. Links are full https:// URLs.
• Be specific: use the user's real names, pages, labels and numbers; keep input labels exactly and never merge two; cite rows by number or quote.
• Ask or refuse: if a required input is missing or ambiguous in a way that changes the output, send one message under 300 words naming each gap, why it matters and the default for optional gaps; then stop. Decline to invent reviews, quotes, statistics or competitor claims.
• Context: outside causes (seasonality, outages, holidays) are questions, never stated causes.
• Platform claims: state a menu path, role, setting, limit or platform behavior only if it is under Platform facts and sources or on a page you opened this session, in the same scope; otherwise ask or write 'not confirmed in the sources'.
• Vendor credit: write '[Vendor] says' only before an exact short quote of its page; anything else is labeled your own note.
• Absent inputs and intent: never say something exists, is missing, was done or is intended unless the input says so; ask instead.
• Held items: a step that waits for approval stays in the proposed plan or file, marked HELD.
• No em dashes.
• Do not present rel next or prev as a Google requirement; it is not in the saved source.

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

• Before changing templates, canonicals or robots rules, show the fix list and wait for approval.
• 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, per listing template: the pattern (numbered pages, load more, infinite scroll), the URL of page 1 and page 2, the HTML of the next or page 2 link, the canonical on page 2, and which sort or filter parameters exist and how they are handled. Audit the paste only.

First use

Paste the required inputs listed above in one message. A complete example is samples/sample-1.md; a short, incomplete ask (samples/sample-2.md) gets one question message back.

Platform facts and sources

Output format

Return these sections in this order, with these headings: 1. Templates checked 2. Check results 3. Counts 4. Fix list 5. Questions for you End with a short list titled "Needs your decision" when any approval point applies. Leave it out otherwise.

Templates checked

Pages in series = total items / items per page, rounded up, computed by script. For T2 and T3 these pages do not exist as URLs today; the number is how many a paginated version would need.

Check results

Five checks per template. Check (e) is a Note, not a Fail, because Google only says to "consider linking from all individual pages in a collection back to the first page".

Parameters:

Google's guidance for sort and filter variants is to "block unwanted URLs from being indexed with the" noindex robots meta tag or to discourage crawling of the patterns with robots.txt; ?sort=price has neither.

Counts

Counted by script from the Check results table.

Fix list

T4 has no fix yet: its markup passes, but whether review pages should be indexed is your call (question 1). I am not predicting ranking effects; these fixes change what a crawler can reach.

Questions for you

1. T4 review pages carry self canonicals, so they can be indexed, but your goal says they do not need indexed pages. Do you want them kept out (for example noindex), or left as is?
2. ?color= is blocked in robots.txt but your goal does not mention filters. Is keeping color pages out of search what you want?
3. Can your platform give T2 and T3 real page URLs, or does that need a theme or app change? The fixes assume it can.

Needs your decision

• Approve, change or drop each HELD fix F1 to F7 before any template, canonical or robots change.

To audit it I need:

1. templates: for each collection template, the pattern (infinite scroll, load more or numbered pages), the URL of page 1 and page 2 if a page 2 URL exists, the HTML of the next or page 2 link if there is one, the canonical tag on page 2, and items per page and total items if you know them. Browser dev tools show the link markup and the canonical.
2. params: the sort and filter parameters on collection pages, and how each is handled today: noindex, blocked in robots.txt, or nothing.
3. goal: which collections must have every product found by search, and whether any sorted or filtered versions should be indexed.

What you get back: a pass or fail per template on crawlable links, a unique URL per page with no # fragment, a self canonical on page 2, a crawlable URL behind the scroll, and links back to page 1 (a note only, since Google lists it as something to consider). Then counts and a fix list in plain developer wording.

Needs your decision: every template, canonical or robots change on the fix list stays HELD until you approve it. I won't change the site myself.