Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a messaging framework (message house) that the whole company can use consistently. Use when asked to create messaging, a value proposition, a message house, key messages, or to make marketing/sales/product say the same thing. Produces a messaging framework — audience & value proposition, the one-line positioning, 3 message pillars with proof points, objection handling, and a words-we-use/avoid list.
.claude/skills/mohitagw15856-messaging-framework/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -2% | 0% |
If marketing, sales, and the website all describe the product differently, customers can't form a clear picture — and confused buyers don't buy. This skill builds the "message house": one value proposition, a few proof-backed pillars, and the exact language everyone uses, so the story is consistent everywhere. (Positioning decides the category and frame; this decides the words.)
Ask for these only if they aren't already provided:
1. Audience & core problem — who it's for and the problem in their words.
2. Value proposition — one sentence: for audience] who need], product] is the category] that key benefit], unlike alternative], because reason to believe].
3. One-liner — the plain-language tagline a customer would repeat to a colleague.
4. The three pillars — the message house roof + columns:
| Pillar (benefit, not feature) | Why it matters to the buyer | Proof point(s) | |---|---|---| | Pillar 1 | | | | Pillar 2 | | | | Pillar 3 | | |
5. Objection handling — the top 3–5 objections and the honest, evidence-based response to each.
6. Language guide — words we use (the customer's vocabulary, the category we claim) and words we avoid (jargon, overclaimed superlatives, competitor framing). This is what keeps everyone consistent.
Message-house / value-proposition practice (incl. April Dunford-style positioning as the upstream input).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,296 | 14,469 | -5% | 1 | 1 | 0% | 2,739 | 3,315 | +21% | 0 | 0 | — |
case-02 | fail→pass | 16,856 | 13,509 | -20% | 1 | 1 | 0% | 2,997 | 3,288 | +10% | 0 | 0 | — |
case-03 | fail→pass | 19,363 | 14,438 | -25% | 1 | 1 | 0% | 3,229 | 3,138 | -3% | 0 | 0 | — |
case-04 | fail→pass | 22,199 | 15,856 | -29% | 1 | 1 | 0% | 3,632 | 3,469 | -4% | 0 | 0 | — |
case-05 | fail→pass | 18,081 | 13,439 | -26% | 1 | 1 | 0% | 3,021 | 2,947 | -2% | 0 | 0 | — |
case-06 | pass→pass | 25,603 | 15,690 | -39% | 1 | 1 | 0% | 4,170 | 3,372 | -19% | 0 | 0 | — |
case-07 | fail→pass | 15,335 | 13,034 | -15% | 1 | 1 | 0% | 2,271 | 2,829 | +25% | 0 | 0 | — |
case-08 | pass→pass | 17,794 | 21,615 | +21% | 1 | 1 | 0% | 2,894 | 2,910 | +1% | 0 | 0 | — |
case-09 | fail→pass | 21,671 | 13,995 | -35% | 1 | 1 | 0% | 3,366 | 3,010 | -11% | 0 | 0 | — |
case-10 | pass→pass | 19,471 | 17,476 | -10% | 1 | 1 | 0% | 2,675 | 3,098 | +16% | 0 | 0 | — |
case-11 | fail→pass | 16,032 | 21,907 | +37% | 1 | 1 | 0% | 2,707 | 3,050 | +13% | 0 | 0 | — |
case-12 | pass→pass | 11,685 | 14,552 | +25% | 1 | 1 | 0% | 2,127 | 3,286 | +54% | 0 | 0 | — |
case-13 | fail→pass | 15,375 | 13,227 | -14% | 1 | 1 | 0% | 2,747 | 3,036 | +11% | 0 | 0 | — |
case-14 | pass→pass | 12,372 | 16,191 | +31% | 1 | 1 | 0% | 2,120 | 3,511 | +66% | 0 | 0 | — |
case-15 | fail→pass | 18,324 | 15,152 | -17% | 1 | 1 | 0% | 3,308 | 3,522 | +6% | 0 | 0 | — |
case-16 | pass→pass | 16,314 | 12,655 | -22% | 1 | 1 | 0% | 2,894 | 2,926 | +1% | 0 | 0 | — |
case-17 | fail→fail | 15,459 | 14,775 | -4% | 1 | 1 | 0% | 2,592 | 3,254 | +26% | 0 | 0 | — |
case-18 | fail→pass | 19,466 | 16,153 | -17% | 1 | 1 | 0% | 3,177 | 3,505 | +10% | 0 | 0 | — |
case-19 | pass→fail | 16,927 | 19,548 | +15% | 1 | 1 | 0% | 2,879 | 4,068 | +41% | 0 | 0 | — |
case-20 | pass→pass | 15,935 | 17,358 | +9% | 1 | 1 | 0% | 2,955 | 3,740 | +27% | 0 | 0 | — |
case-21 | pass→pass | 25,132 | 20,943 | -17% | 1 | 1 | 0% | 6,101 | 5,798 | -5% | 0 | 0 | — |
case-22 | pass→pass | 10,647 | 12,549 | +18% | 1 | 1 | 0% | 1,924 | 2,854 | +48% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.