Sign in Start free

Intent mismatch repair

Ranking for a query you do not actually answer is a common and expensive failure. The fix is not more content; it is matching the format and depth the query expects. This skill reads that expectation from the results themselves.

CATEGORY
On-page SEO
FORMAT
intent-mismatch-repair.md
STEPS
6
PRICE
Free - no account
WHEN TO REACH FOR THIS

Use when a page ranks on page one but gets almost no clicks, or gets clicks and immediate bounces.

The skill file

intent-mismatch-repair.md
---
name: intent-mismatch-repair
description: Use when a page ranks on page one but gets almost no clicks, or gets clicks and immediate bounces.
---

# Intent mismatch repair

Ranking for a query you do not actually answer is a common and expensive failure. The fix is not more content; it is matching the format and depth the query expects. This skill reads that expectation from the results themselves.

## What you need first

- The query and your ranking URL
- The current top results for that query

## Method

1. Search the query and record the format of the top five results: are they how-to guides, comparisons, product pages, tools, definitions, or forum threads?
2. Note the SERP features present. A featured snippet indicates a definitional answer is expected; shopping results indicate transactional intent; People Also Ask reveals the sub-questions.
3. Compare your page format against the dominant one. A product page ranking among guides will keep its position and lose every click.
4. Decide honestly: change the page format to match, or accept that this query belongs to a different page you should create.
5. Where the format is right but clicks are low, the title and description are the problem, not the content.
6. Re-measure click-through rate by position rather than raw clicks, so a ranking change does not mask the result.

## What this produces

A judgment per query: reformat, redirect the intent to a different page, or fix the snippet - with the SERP evidence behind it.

## Where this goes wrong

- Adding word count in response to poor clicks, which changes nothing
- Reading intent from a keyword tool label rather than the live results
- Comparing raw click counts across a period when position also moved

---

From the QuQi skill library - https://www.quqi.io/skills/intent-mismatch-repair
Free to download · no account, no email

What you need first

  • The query and your ranking URL
  • The current top results for that query

Method

  1. 01 Search the query and record the format of the top five results: are they how-to guides, comparisons, product pages, tools, definitions, or forum threads?
  2. 02 Note the SERP features present. A featured snippet indicates a definitional answer is expected; shopping results indicate transactional intent; People Also Ask reveals the sub-questions.
  3. 03 Compare your page format against the dominant one. A product page ranking among guides will keep its position and lose every click.
  4. 04 Decide honestly: change the page format to match, or accept that this query belongs to a different page you should create.
  5. 05 Where the format is right but clicks are low, the title and description are the problem, not the content.
  6. 06 Re-measure click-through rate by position rather than raw clicks, so a ranking change does not mask the result.

What this produces

A judgment per query: reformat, redirect the intent to a different page, or fix the snippet - with the SERP evidence behind it.

Where this goes wrong

  • Adding word count in response to poor clicks, which changes nothing
  • Reading intent from a keyword tool label rather than the live results
  • Comparing raw click counts across a period when position also moved

Use this skill in your own AI

The download is a plain markdown file with the name and trigger in its frontmatter. Where an assistant supports skills it can load itself, that frontmatter is what it reads to decide this one applies.

Claude Code Save it as ~/.claude/skills/intent-mismatch-repair/SKILL.md and Claude loads it on its own when what you are doing matches the trigger line. Put it in .claude/skills inside a project instead if the whole team should have it.
Claude Upload the file in the skills section of your settings. Once it is there it applies itself in any conversation where the trigger fits, so you do not have to remember it exists.
ChatGPT There is no skills format to install into, so paste the file contents into a Project instruction or a Custom GPT instead. It then applies to every chat in that project rather than only the one you paste it into.
Anything else Paste the markdown into the chat before your question. It works in any assistant, it just has to be pasted again each time.

Questions about this skill

When is this the right method rather than adding more content?

When a page holds page one and gets almost no clicks, or gets clicks and immediate bounces. The standard response is to add content, which changes the length and not the format. If your product page is ranking among how-to guides it will keep the position and lose the click no matter how much you write. Format is the variable.

What do I need in hand before starting?

The query, your ranking URL, and the live top results with their SERP features. Reading intent from a keyword tool label instead is the failure: tools assign informational or commercial from the string, while the results show what Google currently serves, and those disagree often enough to waste a rewrite. Check the results yourself for each query you intend to act on.

What do I end up with, and which part gets used?

A judgment per query: reformat this page, send the intent to a different page you create, or fix the title and description because the format was never wrong. The judgment is only usable with the SERP evidence attached, since the recommendation to rebuild a page will be argued and the list of top-five formats is what settles it.

What most often ruins this?

Measuring the result in raw clicks. If the position moved at the same time, and it usually does, you cannot tell whether the reformat worked or the ranking did. Measure click-through rate at a given position instead. The second cost is rebuilding a page for a query that was always going to belong to a different page you have not written yet.

More in On-page SEO