Sign in Start free

Quotable statistic sourcing

Models cite claims that carry a number, a date and an attributable source. Content built on adjectives - faster, better, more effective - offers nothing to quote. This skill converts vague assertions into citable ones, or removes them.

CATEGORY
AI search (GEO)
FORMAT
quotable-statistic-sourcing.md
STEPS
6
PRICE
Free - no account
WHEN TO REACH FOR THIS

Use when your content makes claims no assistant will repeat because nothing in it is specific enough to cite.

The skill file

quotable-statistic-sourcing.md 
---
name: quotable-statistic-sourcing
description: Use when your content makes claims no assistant will repeat because nothing in it is specific enough to cite.
---

# Quotable statistic sourcing

Models cite claims that carry a number, a date and an attributable source. Content built on adjectives - faster, better, more effective - offers nothing to quote. This skill converts vague assertions into citable ones, or removes them.

## What you need first

- A page making qualitative claims
- Whatever real data you hold: your own metrics, customer results, published research

## Method

1. List every claim on the page. Mark each as measurable or merely asserted.
2. For each measurable claim, attach the figure, the period it covers and where it came from. "Cut audit time" becomes "cut audit time from six hours to twenty minutes across 40 client sites in 2026".
3. For claims you cannot support, either find a citable source or delete them. An unsupported superlative costs credibility and gains no citation.
4. Prefer your own first-party data. It is unique, which makes it the only reason to cite you rather than a competitor repeating the same third-party study.
5. State the method in one line wherever you publish your own figure. An unexplained number is treated as marketing.
6. Put the figure in the answer sentence itself, not in a caption or chart alt text where it will not travel with the quote.

## What this produces

A claim inventory where every retained claim carries a number, a period and a source, and unsupportable claims have been cut.

## Where this goes wrong

- Citing a widely-repeated third-party statistic, which gives no reason to cite you over anyone else
- Burying the figure in an image, where it cannot be extracted
- Publishing a number with no method, which reads as a marketing claim

---

From the QuQi skill library - https://www.quqi.io/skills/quotable-statistic-sourcing
Free to download · no account, no email

What you need first

  • A page making qualitative claims
  • Whatever real data you hold: your own metrics, customer results, published research

Method

  1. 01 List every claim on the page. Mark each as measurable or merely asserted.
  2. 02 For each measurable claim, attach the figure, the period it covers and where it came from. "Cut audit time" becomes "cut audit time from six hours to twenty minutes across 40 client sites in 2026".
  3. 03 For claims you cannot support, either find a citable source or delete them. An unsupported superlative costs credibility and gains no citation.
  4. 04 Prefer your own first-party data. It is unique, which makes it the only reason to cite you rather than a competitor repeating the same third-party study.
  5. 05 State the method in one line wherever you publish your own figure. An unexplained number is treated as marketing.
  6. 06 Put the figure in the answer sentence itself, not in a caption or chart alt text where it will not travel with the quote.

What this produces

A claim inventory where every retained claim carries a number, a period and a source, and unsupportable claims have been cut.

Where this goes wrong

  • Citing a widely-repeated third-party statistic, which gives no reason to cite you over anyone else
  • Burying the figure in an image, where it cannot be extracted
  • Publishing a number with no method, which reads as a marketing claim

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/quotable-statistic-sourcing/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 does this beat simply writing more content?

When the page is plainly relevant but contains nothing a model could repeat, because every claim is an adjective. Adding length does not help: faster, better and more effective are unquotable at any word count. This converts the claims you can actually support into citable ones and removes the rest from the page.

What do I need in hand before starting?

A page making qualitative claims, plus whatever real data you hold: your own metrics, customer results, published research. The awkward part is discovering how little you can support. Pull the numbers before you start rewriting, or you will write around the gap with hedged phrasing, which is the same unquotable claim with more words in front of it.

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

A claim inventory where each surviving claim carries a figure, the period it covers and a source, with the unsupportable ones cut. First-party figures are the ones that pay, since a widely repeated third-party statistic gives nobody a reason to cite you over the competitor quoting the same study. Put the number in the answer sentence itself.

What ruins this most often?

Putting the figure in a chart. Images are not extracted, alt text is frequently dropped, and the one quotable thing on the page never travels with the quote. Publishing your own number with no method line is the other one: an unexplained figure reads as marketing, gets discounted, and the measurement effort buys you nothing.

More in AI search (GEO)

Answer extractability pass

Use when a page ranks well but is never quoted by AI assistants, and you need to make its claims...

AI citation monitoring

Use to find out whether assistants actually cite you, since this traffic is largely invisible in...

Entity consistency check

Use when assistants describe your company inaccurately, conflate you with another brand, or stat...

llms.txt authoring

Use when you want to tell assistants which of your pages are authoritative, and be honest with y...