Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate value proposition statements for marketing, sales, and onboarding from existing value propositions. Use when writing marketing copy, creating sales messaging, or crafting onboarding messages.
.claude/skills/phuryn-value-prop-statements/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 0% | 0% |
| case-22 | ✓→✗ | ▼ Worse | -4% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 122% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 37% | 0% |
Generate value proposition statements from existing value propositions for marketing, sales, and onboarding. Creates statements that address target segments, emphasize benefits, and highlight capabilities. Perfect for crafting targeted marketing content, sales presentations, and customer onboarding messages.
You are an experienced product growth expert with expertise in value proposition development and targeted messaging.
Based on the following value proposition(s) for $ARGUMENTS, develop comprehensive value proposition statements that can be used across marketing, sales, and onboarding contexts.
For each statement, ensure it:
To illustrate the approach, here are value proposition statements for Canva:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 5,757 | 9,684 | +68% | 1 | 1 | 0% | 917 | 2,035 | +122% | 0 | 0 | — |
case-02 | pass→pass | 10,700 | 8,831 | -17% | 1 | 1 | 0% | 1,255 | 1,716 | +37% | 0 | 0 | — |
case-03 | pass→pass | 6,598 | 10,105 | +53% | 1 | 1 | 0% | 1,185 | 2,001 | +69% | 0 | 0 | — |
case-04 | pass→pass | 7,781 | 7,383 | -5% | 1 | 1 | 0% | 1,276 | 1,525 | +20% | 0 | 0 | — |
case-05 | fail→pass | 4,894 | 6,458 | +32% | 1 | 1 | 0% | 888 | 1,553 | +75% | 0 | 0 | — |
case-06 | pass→pass | 10,468 | 7,870 | -25% | 1 | 1 | 0% | 1,371 | 1,860 | +36% | 0 | 0 | — |
case-07 | pass→pass | 4,929 | 3,950 | -20% | 1 | 1 | 0% | 858 | 1,189 | +39% | 0 | 0 | — |
case-08 | pass→pass | 6,762 | 7,319 | +8% | 1 | 1 | 0% | 1,104 | 1,756 | +59% | 0 | 0 | — |
case-09 | pass→pass | 6,117 | 3,663 | -40% | 1 | 1 | 0% | 1,084 | 1,095 | +1% | 0 | 0 | — |
case-10 | pass→pass | 6,066 | 6,633 | +9% | 1 | 1 | 0% | 1,057 | 1,588 | +50% | 0 | 0 | — |
case-11 | pass→pass | 8,170 | 7,169 | -12% | 1 | 1 | 0% | 1,035 | 1,440 | +39% | 0 | 0 | — |
case-12 | fail→fail | 12,755 | 7,647 | -40% | 1 | 1 | 0% | 944 | 1,652 | +75% | 0 | 0 | — |
case-13 | fail→fail | 3,804 | 5,723 | +50% | 1 | 1 | 0% | 749 | 1,441 | +92% | 0 | 0 | — |
case-14 | pass→pass | 4,727 | 5,284 | +12% | 1 | 1 | 0% | 852 | 1,152 | +35% | 0 | 0 | — |
case-15 | fail→fail | 7,351 | 8,360 | +14% | 1 | 1 | 0% | 1,269 | 1,905 | +50% | 0 | 0 | — |
case-16 | fail→fail | 7,396 | 5,771 | -22% | 1 | 1 | 0% | 965 | 1,313 | +36% | 0 | 0 | — |
case-17 | pass→pass | 8,839 | 5,617 | -36% | 1 | 1 | 0% | 1,413 | 1,477 | +5% | 0 | 0 | — |
case-18 | pass→pass | 5,962 | 6,868 | +15% | 1 | 1 | 0% | 948 | 1,504 | +59% | 0 | 0 | — |
case-19 | fail→fail | 6,680 | 10,561 | +58% | 1 | 1 | 0% | 1,056 | 1,761 | +67% | 0 | 0 | — |
case-20 | pass→fail | 19,679 | 15,339 | -22% | 1 | 1 | 0% | 3,191 | 3,197 | +0% | 0 | 0 | — |
case-21 | pass→pass | 23,410 | 17,525 | -25% | 1 | 1 | 0% | 4,147 | 4,299 | +4% | 0 | 0 | — |
case-22 | pass→fail | 21,965 | 20,478 | -7% | 1 | 1 | 0% | 4,229 | 4,063 | -4% | 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 -33 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.