1---2name: message-test3description: >-4 Pre-tests a B2B SaaS landing page, ad, email or homepage on 4 criteria (clarity, relevance, value and difference)5 as each buying group role in the company profile would read it, with every score tied to a quoted line, a6 competitor swap test for difference, and fixes drawn from the messaging house. Returns PASS, REVISE, FAIL or7 BLOCKED. It is a cheap screen before paying for a real buyer panel, and it says plainly that it does not replace8 one: no simulated buyer counts or percentages. Use it before a page or campaign goes live, or to compare 29 versions. Not for tone and banned words (use voice-check), facts and numbers (use claim-check) or a full10 conversion review of a page (use landing-page-critic).11license: MIT12compatibility: >-13 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads a page if the agent can browse,14 otherwise pasted copy or a screenshot's text. Python 3 is optional, for the mechanical signals and the verdict.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: check19 plugin: strategy-messaging20 homepage: https://www.shakeuphq.com/skills/message-test21---22 23# Message pre-test24 25Reads a page or an ad the way each buyer role would, scores what they'd get from it, and says what to fix before real buyers see it.26 27## Purpose28 29- One job: score one asset (or 2 versions of it) on clarity, relevance, value and difference for the profile's buyers, with fixes.30- Stage: check. It ends in a verdict with the rule that fired.31- It is a model reading as a buyer, not buyers. It catches clear problems cheaply. It can't say what real buyers think, so it never reports a share of buyers, a preference count or a simulated panel result.32- It suggests line fixes from the messaging house. It doesn't rewrite the asset.33 34## Use when / not35 36| Situation | Use |37| --- | --- |38| A page, ad, email or homepage is drafted and you want to know if buyers will get it | this skill |39| Choosing between 2 versions before a live test or a panel | this skill, both versions, same roles |40| The messaging house is new and you want to see if a page carries it | this skill |41| Tone, dashes, banned words | `voice-check` |42| Every number and claim backed | `claim-check` |43| Structure, proof, friction and the next step on a page | `landing-page-critic` |44| The core message itself isn't set | `messaging-house` |45 46## Inputs47 48| Input | Required | Ways to provide, in order | If missing |49| --- | --- | --- | --- |50| The asset: page copy, ad, email (or 2 versions) | yes | the URL if the agent can browse; pasted copy; a screenshot's text | `BLOCKED` |51| Where the buyer meets it: search ad click, cold feed, retargeting, email, direct | no | the reader's note; inferred from the asset type | infer and state the assumption |52| Who reads it: the primary role | yes | the reader's note; the champion in `### Buying group` (say you used it) | ask once only when there is neither; `BLOCKED` if still unknown |53| The buying moment it targets | no | the reader's note; `## Buying moments` | score relevance against the role only; coverage `partial` |54| Positioning and messaging house | no | `## Positioning` and `## Messaging house` in the profile | difference is scored without a main alternative or marked `not scored`; fixes can't point to pillars |55 56## Profile read57 58From `company-profile.md`: `## Company` (category), `## Buyers` with `### Buying group` (what each role cares about and their objection), `## Buying moments`, `## Positioning` (alternatives, unique attributes, best fit, category), `## Messaging house`, `## Competitors`, `## Claims and proof`, `### Words to avoid`, and every `## Learnings` entry for `message-test` with status `noted`, `fact` or `accepted`.59 60No profile: ask once for who reads the asset (role and company type) and what they use today instead. Continue with coverage `partial`; say `company-profile`, `positioning` and `messaging-house` make this sharper.61 62## Steps63 641. **Apply learnings.** Accepted learnings for this skill override the defaults (for example a tightened anchor after a panel disagreed). Name each one that fires.65 662. **Frame the test.** Write down before reading the asset: asset type, placement, the primary role and up to 2 secondary roles, the moment, and the alternative this reader uses today. Each comes from the reader, the profile, or an assumption labelled `assumed`.67 683. **Mechanical pass.** Run:69 70 ```71 python3 scripts/pretest.py --asset asset.txt --profile company-profile.md72 ```73 74 Mark the fold with a line `---fold---` if you know it; otherwise the first screen is the first 50 words (about a headline, a subhead and a button). Without Python, note by hand: the first screen's text; the category's key words in it; each role named word for word; each moment and alternative with 3 in 4 of its key words present (fewer usually means the category, not the moment); the share of the core message's and each pillar claim's key words present; empty words and words to avoid; every figure; counts of we/our/us against you/your; sentences over 30 words. Say which way you ran it. These are signals for the scores, not scores.75 764. **First-screen read.** As the primary role, from the placement, read only the first screen (the whole ad for an ad). Write one line each, using only words on the asset:77 - What is it?78 - Who is it for?79 - What do I get?80 - What do I do next?81 - What proves it, and where does the proof sit (first screen, below it, or nowhere)?82 83 A line you can't write from the text is a clarity gap; proof below the first screen is a value note. Don't fill it from the profile: the buyer hasn't read the profile.84 855. **Full read.** Read the whole asset as the role, at the moment. List the questions this role would still have, starting from their objection in the buying group and the worries in the buying moments. A question the asset answers is crossed off with the line that answers it.86 876. **Run the 2 tests.**88 - **Swap test (difference):** put each top alternative's name in place of the company's name in the headline and the 3 strongest lines. A line still true of the alternative doesn't count as difference. The status quo counts as an alternative ("a spreadsheet does this too").89 - **Measure test (value):** is the promised result something this role measures (from "cares about" in the buying group)? Is it big enough to beat the comfort of the current way?90 917. **Score each criterion 1 to 5** against the anchors in `references/rubric.md`, per role. Every score cites the line or lines it rests on and the gap that held it back.92 93 | Criterion | The question |94 | --- | --- |95 | Clarity | Can the buyer say what it is, who it's for, what they get and what to do, from the first screen? |96 | Relevance | Does it name this role's situation or moment, in words they use? |97 | Value | Is the result one they measure, with proof, and does it answer their main worry? |98 | Difference | After the swap test, is there a reason to pick this over what they use today? |99 100 Write `not scored` when the input it needs is missing (difference with no known alternative and none the reader can name). Never guess a score to fill the gap.101 1028. **Get the verdict.** Run `python3 scripts/pretest.py --scores scores.json`, or apply the table below by hand. The primary role decides it; secondary roles' gaps are notes.103 1049. **Write the fixes.** For every criterion at 3 or below: the line to change, what is missing, and where to draw the fix from (a pillar, the core message, a unique attribute, a buying moment phrase). Draw only on pillar parts that have proof; leave out a pillar's comparison or figure that has no source. Never add a claim missing from `## Claims and proof`; send every figure on the asset to `claim-check`.105 10610. **Write the panel brief.** What a real buyer test should ask: the audience (role, seniority, company type from the ideal customer, or from what the reader said), the versions, the 4 questions in step 7 in the buyer's terms, and the decision each answer drives. Options: a paid B2B message-testing panel, or 5 interviews with buyers who match the ideal customer.107 10811. **Comparing 2 versions:** score both for the same roles. Report the criteria where they differ by 2 or more points. A difference of 1 is within what a re-read changes, so call it a tie and let the panel decide.109 110## Check and verdict111 112| Verdict | Condition, for the primary role (first match wins) |113| --- | --- |114| `BLOCKED` | No asset; or no buyer role after asking once |115| `FAIL` | Any criterion scores 1 or 2 |116| `REVISE` | Any criterion scores 3, or any criterion is `not scored` |117| `PASS` | Every criterion scores 4 or 5: ready for a real buyer panel or a live test, not proof that buyers agree |118 119When clarity is 2 or less, mark the other scores provisional and put the clarity fix first: a buyer who can't tell what it is never reaches the value.120 121Named stop: `BLOCKED` asks for the asset or the role. No other stops; the skill that made the asset decides what to do with a `FAIL`.122 123Every output carries this line, unchanged in meaning: "This is a pre-test by a model reading as your buyers, not a test with buyers. Use it to fix clear problems before you pay for a real panel; don't report it as buyer research."124 125## Learn126 127Append to `## Learnings`:128 129- a real panel or a live test comes back for an asset this skill scored: a `fact` with both results side by side and the source;130- the panel scores a criterion 2 or more points below this skill on 2 assets: a `proposal` to tighten that criterion's anchor for this company;131- the reader rejects a finding: a `proposal` with their reason.132 133Example: `- 2026-10-24 | message-test | proposal | Score clarity 1 point lower when the first screen names no card provider | Why: panel clarity 2.1 vs pre-test 4 on 2 pages (buyer panel, 2026-10) | Status: proposed`134 135## Output136 137```138Verdict: <PASS | REVISE | FAIL | BLOCKED> · Coverage: <complete | partial (what's missing) | blocked> · Signals: <script | by hand>139This is a pre-test by a model reading as your buyers, not a test with buyers. ...140 141Frame: <asset type> · <placement> · primary role <role> (<from profile | reader | assumed>) · moment <moment> · alternative <alternative>142 143First screen, as <role>144What is it: <line or "can't tell">145Who is it for: <line or "can't tell">146What do I get: <line or "can't tell">147What do I do next: <line or "can't tell">148What proves it: <proof, and where it sits, or "none">149 150| Criterion | <primary role> | <secondary role> | Line it rests on | Gap |151| Clarity | n | n | "<quote>" | ... |152| Relevance | ... |153| Value | ... |154| Difference | ... (swap test: <lines that survived>) |155 156Questions the buyer still has: <list, with the objection each comes from>157 158Fixes (lowest criterion first)159| Line | Criterion | What's missing | Draw from |160 161Figures for claim-check: <list>162Panel brief: <audience, versions, 4 questions, decision each drives>163Learnings applied: <list, or none>164```165 166Then the handoff block.167 168## Hand off169 170```handoff171skill: message-test172version: 1.0.0173verdict: REVISE174coverage: partial (no buying moment named; placement assumed)175for: <asset name>176outputs:177 primary_role: Head of finance178 scores: {clarity: 5, relevance: 4, value: 3, difference: 4}179 lowest: value180 fixes_ready: true181 figures_to_check: ["3 days"]182next: [claim-check, landing-page-critic]183open: [run a buyer panel before scaling spend]184```185 186Made-up values for illustration. The skill that made the asset reads `lowest` and the fix table, rewrites, and runs this check again (its own loop, at most 2 rounds).187 188## Failure modes189 190| Problem | Do this |191| --- | --- |192| The reader asks for "what % of buyers would" or a simulated panel | Refuse that part plainly; give the scores and the panel brief instead |193| The asset is a screenshot with no text available | Ask for the copy; don't score from a description of an image |194| The role isn't in the profile's buying group | Score for the stated role, label it `assumed`, and suggest `buying-moments` |195| A score depends on knowledge only the company has | The buyer doesn't have it: score from the asset alone |196| The page is long | Score the first screen for clarity; the full read for the rest; say how much you read |197| 2 versions score the same | Call it a tie; the panel or the live test decides |198 199## Influenced by200 201- Wynter's message testing (Peep Laja), which asks real B2B buyers from a verified panel to rate a page's clarity, relevance, value and differentiation: https://wynter.com/post/message-testing202- What we changed: the same 4 questions are answered by a model reading as each role in the company profile, with anchored scores tied to quoted lines, a competitor swap test, a first-screen read and a verdict rule. It is a screen before a real panel, never a substitute, and it never reports buyer counts.