SEO & GEO/AEO

Verified against Gemini · 2026-07-30

Restructure a section specifically to win a featured snippet

Diagnoses which snippet format a query is actually pulling — paragraph, list, or table — from the current holder, then restructures your section to match that exact shape without turning the copy into a robotic answer nobody wants to read on the page itself.

ChatGPTClaudeGemini3 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

You are an on-page structure editor optimizing for featured-snippet capture, not just general readability.

TARGET QUERY: how long does a tattoo take to heal
CURRENT SNIPPET HOLDER'S CONTENT (paste what's currently shown in the box, if you can see it): "Most tattoos take 2 to 3 weeks to heal on the surface, and up to 6 months for the deeper skin layers to fully heal." (currently held by healthline.com)
YOUR EXISTING SECTION ON THIS TOPIC: Healing varies by person and by tattoo, but generally speaking most tattoos take a while to heal fully, with several stages involved in the process.

TASK

1. DIAGNOSE THE FORMAT. From "Most tattoos take 2 to 3 weeks to heal on the surface, and up to 6 months for the deeper skin layers to fully heal." (currently held by healthline.com), identify exactly which shape Google is currently rewarding for this query: a paragraph snippet (a direct 40-60 word answer), an ordered/unordered list snippet (steps or items), or a table snippet (comparative data across rows and columns). Do not guess a generic answer — name the specific shape shown.
2. MATCH THE SHAPE. Restructure Healing varies by person and by tattoo, but generally speaking most tattoos take a while to heal fully, with several stages involved in the process. into that exact shape.
   - Paragraph: the answer must be extractable in one 40-60 word block, self-contained, with the direct answer in its first sentence — no "it depends" as the opening clause.
   - List: format as an actual HTML-ready ordered or unordered list, each item as a short, scannable phrase, not a paragraph disguised as a bullet.
   - Table: build a real table with the same column structure the current holder uses, or a clearly better one if a column is obviously missing there.
3. DON'T LOSE THE HUMAN READER. The rewritten block should still read naturally as part of the page — this is not license to strip all context and voice from the section. Everything outside the extractable snippet-shaped block can stay as normal prose.
4. NAME THE GAP. If the current holder's answer is thin, outdated, or missing an obvious sub-point, name exactly what's missing and make sure your version includes it — a snippet gets replaced when a clearly better answer to the same query appears, not through effort alone.
5. FLAG IF NO SNIPPET EXISTS YET. If "Most tattoos take 2 to 3 weeks to heal on the surface, and up to 6 months for the deeper skin layers to fully heal." (currently held by healthline.com) is empty because no snippet currently shows for this query, say so, and note that this is often more winnable than displacing an entrenched one — build the paragraph-shaped block as the default bet unless the SERP shows a strong signal otherwise.

OUTPUT
The diagnosed format, the rewritten block in that exact shape, and one sentence naming the specific reason your version should outrank the current holder or claim the empty snippet slot.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Google selects a featured snippet from a specific passage on a page that's already ranking reasonably well, and it consistently favors passages that are already structurally shaped like the answer it wants to show — which is why diagnosing the exact current format before rewriting anything matters more than general "be concise" advice: a well-written paragraph competing against an entrenched table-format snippet is optimizing for the wrong shape entirely, no matter how clear the prose is. Naming the specific gap in the current holder's answer targets the actual mechanism by which snippets change hands — Google replaces a snippet when it finds a clearly better-structured or more complete answer to the same query, not on a schedule, so a rewrite that's merely equally good in a different shape rarely displaces an incumbent, while one that visibly closes a real gap (a missing time range, a missing step, a missing column) has an actual mechanism to win on. The instruction to preserve natural reading quality outside the extractable block exists because an over-optimized page that reads as a robotic list end to end can win a snippet and still hurt on-page engagement and time-on-page for the human reader who clicks through — the goal is a page that works for both audiences at once, with only the specific answerable unit shaped for extraction, not the whole page flattened into fragments.

What you get back

Diagnosed format: paragraph snippet, currently held by healthline.com with a two-stat structure (surface healing time + deep healing time). Rewritten block: "A tattoo typically takes 2-3 weeks to heal on the surface, and up to 4-6 months for the deeper skin layers underneath to fully settle. Healing speed depends most on tattoo size and aftercare consistency, not just individual skin type." Gap closed: added the size-and-aftercare factor the current holder omits entirely, and tightened the deep-healing range to 4-6 months based on the sourced range in your section rather than the current holder's flatter "up to 6 months."

Verified against

Gemini Gemini 3 Pro · 2026-07-30

Claude Claude Sonnet 5 · 2026-08-04

Changelog

  • 2026-07-30 Initial publish, verified against Gemini 3 Pro.
  • 2026-08-04 Re-verified against Claude Sonnet 5; added the "flag if no snippet exists yet" branch after realizing the original version assumed an incumbent snippet was always present.

Building this for real?

This is a free starting point. If you'd rather have SEO built and running for your business, that's Scult's day job.

EXPLORE SEO
All SEO & GEO/AEO prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY