Query fan-out tool: see the searches behind your topic and which ones you cover

---
name: query-fan-out
description: Writes out the related searches behind a topic (a query fan-out), checks which ones the site already shows up for in Search Console, and turns the gaps into questions to answer or a section plan. Uses the MetaMonster connector's Search Console tool, plus keyword research on a MetaMonster plan. Use when someone asks for a query fan-out, related questions, AI search coverage, what a page is missing, or how to plan a new piece of content.
---

# Query fan-out

You map the related searches someone is likely to need around a topic, then measure which ones the site already covers. Be clear about which part is prediction and which is data: the fan-out is your prediction, and coverage comes from Search Console.

## Before you start

- This skill needs the MetaMonster connector. If its tools aren't available, tell the user to add MetaMonster from Claude's connector directory. You can still write the fan-out without it, but say that coverage can't be checked.
- Call `list_search_console_properties`. If there's more than one property, ask which site. If none is connected, give the user the link the tool returns.
- Without a MetaMonster plan, Search Console queries are capped at 100 a day. This skill uses 2 or 3.

## 1. Get the topic

If the user gave a topic, use it. If they gave a page, call `query_search_console` with `dimensions: ["query"]`, a page filter (`operator: "equals"` and the exact URL), `days: 90`, `sort: "impressions"` and `limit: 25`, and use the page's main search as the topic. Ask whether this is for a new piece of content or an existing page.

## 2. Write the fan-out

Write 15 to 30 searches, phrased the way people type or ask them, in these groups:

- definitions and basics
- how-to and steps
- comparisons and alternatives
- costs and pricing
- problems and mistakes
- examples and templates
- what to do next

Skip a group if it doesn't fit the topic.

## 3. Check coverage

Pick the 3 to 5 most distinctive words across the fan-out. Call `query_search_console` with `dimensions: ["query", "page"]`, a query filter (`operator: "includingRegex"` with those words joined by `|`), `days: 90`, `sort: "impressions"` and `limit: 200`.

Match each fan-out search to the closest real query in the results. Mark it covered (with the page and position), weak (the site shows up, but below position 20), or a gap (nothing close).

## 4. Add demand on a MetaMonster plan

If the user has a plan, call `keyword_research` once with the topic as the seed and `limit: 50`. Add volume and difficulty to the fan-out searches that match a related keyword. Keyword research has a daily cap, so don't run it for every search.

## 5. Show the results

Show a table with each search, its group, its coverage (page and position, or gap) and, on a plan, volume and difficulty.

Then, for new content, give a section plan with one heading per group that has gaps, and the searches each section should answer. For an existing page, list the 5 gaps it should answer first and where on the page each one fits. If another page on the site already covers a search, suggest linking to it rather than repeating it.

I want a query fan-out for this topic: [your topic]

1. Write 15 to 30 related searches that someone researching this topic is likely to need, phrased the way people type them. Group them into definitions and basics, how-to and steps, comparisons and alternatives, costs, problems and mistakes, examples and templates, and what to do next. Skip any group that doesn't fit.
2. Here's my Search Console query data for the last 90 days, with the page each query ranks for and its position:

[paste here]

Mark each fan-out search as covered (with the page and position), weak (below position 20) or a gap.
3. If this is a new piece of content, give me a section plan built from the gaps. If it's an existing page, list the 5 gaps it should answer first.

Be clear that the fan-out is your prediction and the coverage comes from my data.