---
name: avatar-fit-checker
description: Use when you have a buyer description, and ads or a product page, and want to know if the description is specific enough and if the ad and page really speak to that one buyer. It passes or fails each buyer field, scores the fit out of 100, and lists rewrites in the buyer's words.
---

# Avatar fit checker

You check two things, in order. Stage 1: is the buyer description a real person, backed by evidence, or only an age and a gender? Stage 2: do the ad, the page and the offer all speak to that one person? You give a pass or fail on each buyer field, a fit score out of 100, the mismatches by part, and a rewrite list in the buyer's own words.

<!-- needs: written by tools/add-needs.mjs from the blocks' inputs. Edit that tool, not this section. -->
## Before you start
This skill runs on its own. What's below makes the result better, but none of it is required.

**Works best with** (or they can paste their own instead):
- **Brand brain** (its buyers part), made by the [Website brand brain builder](https://useaiblocks.com/skills/website-brand-brain-builder): your facts, products, buyers, claims and voice, in one folder of eight files.

**Makes it better (optional):**
- **A draft** (yours): the ad, page, email or script you want checked or improved.
- **Your page** (yours): the landing page's link, or its text and a screenshot.
- **Customer words** (yours): reviews, testimonials, support tickets, survey answers or call transcripts. Export them or paste them in.

**Recommended steps before this one** (optional; do each once, then reuse what it makes):
1. **Brand brain** with the [Website brand brain builder](https://useaiblocks.com/skills/website-brand-brain-builder). Bring your website, customer words (optional), your results (optional).
2. This one.

**From the brand brain, read:** `00-start-here.md`, `proof-and-claims.md`, `offers.md`, `voice-and-look.md`. Take the claims list with each claim's status, the offer terms word for word, and the voice rules. Source notes and rejected ideas never go into the result.

How to start:
1. **Look first.** Use what they've already attached, pasted or put in their about-me note. In Claude Code, look in the project too: a brand brain is a folder with `00-start-here.md` in it (often `brand-brain/`). If it's there, read that file and the files above. Look for the other things by name.
2. **If something is missing, advise, don't block.** In one short message, say this skill works on its own and will be better with your brand brain, a draft, your page. They can attach them, paste them, or say where they are (in Claude Code, a file path). Name the recommended steps above as a suggestion, with their links. Then ask: "Add them, or shall I go ahead with what you've given me?" If their message already says to go ahead, skip this and start.
3. **When they say go ahead,** do the whole job with what you have. Mark each gap with `MISSING:` where it belongs and never invent a fact to fill it. Keep the answer tight: say each point once, merge steps that give the same thing, and aim for under 700 words unless the job truly needs more. In CHECKS MISSED, name only the checks that failed, or write “none”.

**Tools that do this best:**
- **Any good chat AI:** Reads your description, ad and page, and can read attached product photos.
- **Meta Ad Library:** Lets you compare your ad with rivals' to see who they speak to.
- **Google Forms:** A free way to survey buyers in the words they use, so the next check has more quotes.
<!-- /needs -->

## What you need
- **The buyer description** (required): notes, quotes, a sketch. Quotes or sources matter more than length.
- **Ad text or script** (optional): the hook, primary text and what is shown.
- **Product or landing page text** (optional), and a note of what the product photos show.
- **The offer** (optional): what is promised and on what terms.
- **Call transcripts, reviews or survey answers** (optional), only for the stand-in test at the end.

Stage 1 can run alone. Stage 2 needs at least one ad or page. Every part you are not given is left out of the score and listed.

Does not fit: no evidence about the buyer yet. This skill checks; it does not find the evidence. Use the Forum and review avatar digger first. Hook writing belongs to the ad copy skills. Expect fails on a first draft.

## Steps
**Stage 1. Is it a person?**
1. **Run the 30-second test.** Can the description say who they are, their hopes, their current situation, their problem, and the one wish if they could snap their fingers? If it cannot, stage 1 fails.
2. **Fail demographics.** A description that is only age and gender fails. It needs a person-level situation. A good one reads like: 55, third cat, lost two to kidney disease, children far away.
3. **Check the seven required fields** one by one: situation, daily struggle, deepest fear, mind state, dream outcome, failed fixes, exact words they use. Each needs a quote or a source. A field written from guesses is flagged as a guess.
4. **Check the fixes are named.** "Have you tried minoxidil" beats "have you tried supplements".
5. **List the hidden limiting beliefs**, for example "only surgery works".
6. **List the promises they are sick of hearing** in this market.
7. **Write the next research step for each gap.**

**Stage 2. Does everything fit that one person?**
8. **Check every part, not just the ad.** The ad creative, the primary text, the landing page, the product photos, and what the page says the product does for them. Everything is tailored to the one buyer.
9. **Hook check.** The hook has to show you understand their situation and touch the fear, not only name them. The source's contrast: a line about "your last companion" lands better than "are you tired of".
10. **Words check.** Use their words ("feel uglier"), not the marketer's ("look worse"). Use a named failed fix, not a general one. Wording also differs by age: a 50 year old and a 20 year old with the same problem do not talk the same.
11. **Outsider test.** Someone outside the group should feel they are in the wrong place. That is a pass. If everyone feels welcome, the message is too broad.
12. **Congruence check.** The problem in the ad is the same problem on the page: same scenario, same failed fixes. An ad about one thing that lands on a page about another fails.
13. **Belief order.** The page builds belief in this order: their scenario, why the old fixes failed, then the new answer.
14. **Targeting note.** The sources, who are agency owners, say to keep targeting broad and let the creative do the targeting. That is their view; test it on your own account.
15. **Content level.** Is the buyer a beginner (the 101 level) or already doing well (the 301 level)? Say which one the copy is written for.
16. **Optional stand-in test.** If you have five or more call transcripts, survey results and your own content results, you may use them as a "free focus group" in one AI project, with your product, price and features added. Ask it which lines would resonate or fail. Treat its answers as hypotheses and confirm with real buyers or an ad test. The idea comes from a business-to-business source, and the stand-in is only as good as the real transcripts.

## Score it
The score measures how well one buyer description is backed by evidence and how well the ad, page and offer speak to that buyer. It is not a prediction of sales.

Stage 1 is worth 50 points:
- Seven required fields, 5 points each: full 5 when filled with a quote or source, 2 when filled but guessed, 0 when empty.
- Limiting beliefs listed: 5 points, same rule.
- Promises they are sick of: 5 points, same rule.
- 30-second test passed: 5 points.

Stage 2 is worth 50 points, 10 for each part you were given (hook, primary text, product photos, landing page, offer):
- 10: speaks to this person's situation, touches the fear, uses their words, and matches the other parts.
- 5: right group, but generic wording or only names the group.
- 0: generic, or written for a different buyer.
- A page that tells a different story from the ad scores at most 5.

Score = points earned divided by points possible, times 100, rounded. Parts not given are not counted, so say what was scored. Write the sum on the score line. These point values are a starting set to adjust, not measured figures.

Stage 1 fails if the description is only age and gender, or if any required field is empty. A field marked as a guess is flagged, not passed.

## What you hand back
Use these labels in this order:

```
STAGE 1  BUYER DESCRIPTION  <PASS | FAIL>
30-second test: <pass/fail, what was missing>
Situation: <pass/fail/guess> | <evidence or "no quote">
Daily struggle: ...
Deepest fear: ...
Mind state: ...
Dream outcome: ...
Failed fixes (named): ...
Exact words: ...
Limiting beliefs: <list or none found>
Promises they are sick of: <list or none found>
Next research step per gap: <...>

STAGE 2  FIT BY PART
Hook: <0/5/10> | <mismatch> | rewrite: <in their words>
Primary text: ...
Product photos: ...
Landing page: ...
Offer: ...
Congruence (ad to page): <pass/fail, why>
Outsider test: <pass/fail>
Belief order: <pass/fail>
Wording by age: <pass/fail>
Content level: <101 | 301 | unclear>

SCORE  <n>/100 (<points earned> of <points possible> = <n>)
Not scored: <parts not given>
REWRITE LIST (buyer's words only)
1. <where> | now: <...> | change to: "<phrase from the evidence>"
NEXT: <the single most useful next step>
MISSING: <what would improve the check>
```

<!-- next: written by tools/add-needs.mjs from the blocks' outputs. Edit that tool, not this section. -->
## After this
When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own:
- **Understand your buyers** with the [Switch friction remover](https://useaiblocks.com/skills/switch-friction-remover). It takes the audit report.
- **Plan what to test** with the [Ad test brief writer](https://useaiblocks.com/skills/ad-test-brief-writer). It takes the audit report.
- **Read your ad results** with the [Campaign keep-or-change checker](https://useaiblocks.com/skills/campaign-keep-or-change-checker). It takes the audit report.
- The [AI recommendation gap finder](https://useaiblocks.com/skills/ai-recommendation-gap-finder). It takes the audit report.
- The [Test idea ranker](https://useaiblocks.com/skills/test-idea-ranker). It takes the audit report.
If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.
<!-- /next -->

## Checks
- Every pass is tied to a quote or source; every guess is flagged.
- Rewrites use words found in the buyer's evidence. If the evidence has no phrase for it, write `MISSING: buyer wording for <part>` and give the research step. Never invent a quote.
- The score line shows the sum and lists parts not scored.
- No rewrite adds a claim the product cannot support. Health, money and legal claims carry a line telling the owner to check with a qualified person.

## If something is missing
- No buyer evidence: Stage 1 fails with `MISSING: quotes or sources for the buyer`, and give the research step. Do not score Stage 2 against an unsupported buyer; list it as not run.
- No ad or page: run Stage 1 only and write `MISSING: ad or page text`.
- Photos described but not seen: say what could not be checked, and ask for the images (the AI can read attached images).

## Avoid
- Passing a description because it is long or well written. Evidence is what passes it.
- Rewriting the hook with marketing words. Use the buyer's.
- Judging a page by its headline alone.
- Treating the stand-in AI's answers as proof.
- Treating the broad-targeting advice as a rule for every account.
