offer-clarity-diagnosis
Skill2 starsChanged 4 months agoMITView on GitHub
Tests whether the offer on the page is specific enough to be believed and acted on, or whether it is a category description wearing an offer's clothes. Use when traffic and message match are fine but the page still does not convert.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- above-the-fold-clarity-reviewSkill
- accessibility-conversion-blocker-checkSkill
- comparison-page-positioning-reviewSkill
- conversion-leak-finderSkill
- cta-clarity-checkSkill
- form-friction-finderSkill
- google-ads-landing-page-experience-reviewSkill
- hero-section-diagnosisSkill
- landing-page-ab-test-readoutSkill
- landing-page-copy-readability-passSkill
- landing-page-scale-readiness-checkSkill
- landing-page-triageSkill
- lead-form-sales-handoff-checkSkill
- mobile-conversion-reviewSkill
- objection-map-builderSkill
- page-length-fit-checkSkill
- page-speed-impact-reviewSkill
- paid-traffic-message-match-auditSkill
- popup-and-overlay-timing-reviewSkill
- pricing-page-clarity-reviewSkill
- social-proof-strength-auditSkill
- thank-you-page-opportunity-auditSkill
- traffic-temperature-match-reviewSkill
- trial-vs-demo-path-decisionSkill
- trust-signal-auditSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run message match first. An unclear offer and a mismatched offer look identical in the data and have opposite fixes.
- Distinctive: line 22
If message match has not been checked, run that first.
- Very specific: line 24
Not for: comparing ad to page (paid-traffic-message-match-audit), or measuring how the copy reads (landing-page-copy-readability-pass).
- Distinctive: line 28
Write the offer in one sentence: who gets what outcome, by what mechanism, with what commitment.
- Distinctive: line 29
Check whether the page explains deliverable, timeline, eligibility, cost/risk cue and next step.
- Distinctive: line 37
Test every noun for falsifiability.
- Distinctive: line 41
Do not propose a new offer.
- Distinctive: line 64
Do not invent a new offer, price or positioning.
- Distinctive: line 65
Do not confuse vague with short.
- Distinctive: line 66
Do not diagnose the offer before message match has been ruled out.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Offer Clarity Diagnosis
Use this skill when
- the page copy is available and the team suspects the problem is what is being offered rather than how the page looks.
- the copy was written by committee and every reviewer added a qualifier.
- the page reads like a description of a category rather than a thing you can buy.
Run message match first. An unclear offer and a mismatched offer look identical in the data and have opposite fixes.
Required input
- the offer as the page states it: headline, subhead, the benefit copy, and what the visitor gets.
- the price or the commitment, if the page names one.
- who the offer is for, as the page says it, not as the team knows it internally.
- optional: CVR, and whether message match against the ad has already been ruled out.
- If message match has not been checked, run that first. An unclear offer and a mismatched offer look identical in the conversion data and have opposite fixes.
Not for: comparing ad to page (paid-traffic-message-match-audit), or measuring how the copy reads (landing-page-copy-readability-pass).
Analysis workflow
- Write the offer in one sentence: who gets what outcome, by what mechanism, with what commitment.
- Check whether the page explains deliverable, timeline, eligibility, cost/risk cue and next step.
- Identify missing specifics that make visitors unable to decide if the offer is for them.
- Separate offer confusion from copy style, proof weakness and form friction.
- Recommend stronger offer framing or proof needed to make the offer believable.
Decision rules
- An offer that cannot be disbelieved cannot be believed. If no sentence on the page could be proven wrong, that is the finding.
- Test every noun for falsifiability. "Scale profitably with data-driven creative" survives being said about any competitor, which means it says nothing.
- A named audience beats an adjective. "For agencies running under 50k a month" is an offer; "for ambitious brands" is a mood.
- Count the photographable nouns in the hero. Abstraction concentrated where the visitor decides is the expensive kind.
- A booking, a call or a session is a cost to the visitor, not a benefit. If the only concrete thing on the page is the ask, say so.
- Do not propose a new offer. Diagnose the stated one and name the specific vagueness. Inventing an offer is a business decision, not a page fix.
Output format
| Claim on the page | Falsifiable | Names an audience | Carries a number or mechanism | Verdict |
| Quoted sentence | Yes / no | Yes / no | Yes / no | Specific / vague / interchangeable |
End with:
Would this survive a competitor's name swapped in:yes or no, with the sentence that proves itThe one concrete thing on the page:quoted, or noneDecision:sharpen the offer / test a specific variant / check message match first / ask for dataMissing data:what would change the diagnosis, usually the real audience definition
Practical example
User: "Copy reads: We help ambitious brands scale profitably with data-driven creative and full-funnel media buying. Book a strategy session. 1400 sessions, 0.6 percent CVR, message match with the ad is fine."
Assistant should note: every noun in that sentence is unfalsifiable, so the offer cannot be disbelieved and therefore cannot be believed either; there is no named audience, no mechanism a reader could repeat back, no time frame and no risk reversal, which leaves a strategy session as the only concrete thing on the page; a strategy session is a cost to the visitor, not a benefit, so the page asks for time and offers a category. Then: with message match already ruled out, the offer is the live hypothesis for 0.6 percent, and the smallest test is one specific outcome for one named audience with a number attached. Whether specificity lifts CVR is a hypothesis, and it needs the current baseline held for comparison.
Guardrails
- Do not invent a new offer, price or positioning.
- Do not confuse vague with short. Report vagueness, not length.
- Do not diagnose the offer before message match has been ruled out; say so if it has not.
- Quote the page. An unquoted vagueness finding is an opinion.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

