Answer extractability pass

An assistant quotes a span it can lift without rewriting. Prose that buries the answer three clauses into a paragraph is readable by a human and useless to a model choosing what to cite. This skill restructures existing content so the answer is extractable, without turning it into a listicle.

The skill file

---
name: answer-extractability-pass
description: Use when a page ranks well but is never quoted by AI assistants, and you need to make its claims liftable rather than merely present.
---

# Answer extractability pass

An assistant quotes a span it can lift without rewriting. Prose that buries the answer three clauses into a paragraph is readable by a human and useless to a model choosing what to cite. This skill restructures existing content so the answer is extractable, without turning it into a listicle.

## What you need first

- A page that ranks but is not cited
- The questions it should answer, in the words people actually use

## Method

1. For each question the page addresses, find the sentence that answers it. If no single sentence does, that is the defect - write one.
2. Move that sentence to the first position under its heading. Assistants weight the opening of a section far more heavily than its middle.
3. Make the answer self-contained. A sentence beginning "it does this by" cannot be quoted, because the antecedent is in the previous paragraph and will not travel with it.
4. Convert the heading into the question itself where that is honest. A heading reading "Pricing" answers nothing; "What does it cost?" matches the query and marks the span that follows as its answer.
5. Attach a concrete figure, date or name to each claim. Assistants prefer citable specifics over adjectives, and a claim with a number is far more likely to be quoted verbatim.
6. Read each answer sentence in isolation, with no surrounding context. If it does not stand alone, it will not be quoted.

## What this produces

The same page with one self-contained answer sentence in first position under each question-shaped heading.

## Where this goes wrong

- Turning the page into bullet soup, which reads worse to humans and gains nothing
- Writing answer sentences that depend on a pronoun resolved elsewhere
- Adding a FAQ block at the bottom while leaving the body unchanged - the body is what gets read

---

From the QuQi skill library - https://www.quqi.io/skills/answer-extractability-pass

What you need first

• A page that ranks but is not cited
• The questions it should answer, in the words people actually use

Method

1. 01 For each question the page addresses, find the sentence that answers it. If no single sentence does, that is the defect - write one.
2. 02 Move that sentence to the first position under its heading. Assistants weight the opening of a section far more heavily than its middle.
3. 03 Make the answer self-contained. A sentence beginning "it does this by" cannot be quoted, because the antecedent is in the previous paragraph and will not travel with it.
4. 04 Convert the heading into the question itself where that is honest. A heading reading "Pricing" answers nothing; "What does it cost?" matches the query and marks the span that follows as its answer.
5. 05 Attach a concrete figure, date or name to each claim. Assistants prefer citable specifics over adjectives, and a claim with a number is far more likely to be quoted verbatim.
6. 06 Read each answer sentence in isolation, with no surrounding context. If it does not stand alone, it will not be quoted.

What this produces

The same page with one self-contained answer sentence in first position under each question-shaped heading.

Where this goes wrong

• Turning the page into bullet soup, which reads worse to humans and gains nothing
• Writing answer sentences that depend on a pronoun resolved elsewhere
• Adding a FAQ block at the bottom while leaving the body unchanged - the body is what gets read

More in AI search (GEO)