Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Brainstorm product positioning ideas differentiated from competitors. Identifies top competitors and generates positioning statements with rationale. Use when developing product positioning, differentiating from competitors, or crafting brand positioning strategy.
.claude/skills/phuryn-positioning-ideas/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 18% | 0% |
Brainstorm product positioning ideas differentiated from competitors. Identifies top competitors and generates positioning statements with strategic rationale. Use when developing product positioning, differentiating from competitors, or crafting brand positioning strategy.
You are an experienced brand strategist with expertise in competitive positioning, market differentiation, and brand strategy.
Given the following product and market context: $ARGUMENTS
Follow these steps:
Step 1: Competitive Landscape Analysis Identify and briefly describe the top 5 competitors in this market. For each, note:
Step 2: Positioning Brainstorm Generate 5 unique positioning ideas for this product that target the specified market segment. Each positioning idea should:
Step 3: Positioning Statements For each idea, provide:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 12,715 | 17,873 | +41% | 1 | 1 | 0% | 2,002 | 3,475 | +74% | 0 | 0 | — |
case-06 | fail→fail | 12,211 | 17,113 | +40% | 1 | 1 | 0% | 1,941 | 3,211 | +65% | 0 | 0 | — |
case-04 | fail→fail | 14,338 | 16,849 | +18% | 1 | 1 | 0% | 2,250 | 2,982 | +33% | 0 | 0 | — |
case-01 | fail→pass | 20,536 | 21,893 | +7% | 1 | 1 | 0% | 3,498 | 3,251 | -7% | 0 | 0 | — |
case-02 | fail→pass | 23,244 | 19,893 | -14% | 1 | 1 | 0% | 3,755 | 3,744 | -0% | 0 | 0 | — |
case-03 | fail→pass | 25,971 | 22,421 | -14% | 1 | 1 | 0% | 3,338 | 4,385 | +31% | 0 | 0 | — |
case-07 | pass→pass | 17,556 | 20,835 | +19% | 1 | 1 | 0% | 2,978 | 3,986 | +34% | 0 | 0 | — |
case-08 | pass→pass | 21,097 | 22,622 | +7% | 1 | 1 | 0% | 3,563 | 4,399 | +23% | 0 | 0 | — |
case-09 | fail→fail | 20,230 | 17,733 | -12% | 1 | 1 | 0% | 2,606 | 3,535 | +36% | 0 | 0 | — |
case-10 | pass→pass | 22,574 | 18,895 | -16% | 1 | 1 | 0% | 2,915 | 3,823 | +31% | 0 | 0 | — |
case-11 | fail→pass | 20,732 | 19,916 | -4% | 1 | 1 | 0% | 3,200 | 3,776 | +18% | 0 | 0 | — |
case-12 | fail→pass | 19,136 | 18,515 | -3% | 1 | 1 | 0% | 3,018 | 3,526 | +17% | 0 | 0 | — |
case-13 | fail→pass | 15,898 | 15,893 | -0% | 1 | 1 | 0% | 2,383 | 3,047 | +28% | 0 | 0 | — |
case-14 | fail→pass | 20,133 | 19,320 | -4% | 1 | 1 | 0% | 3,442 | 3,831 | +11% | 0 | 0 | — |
case-15 | fail→pass | 17,732 | 22,907 | +29% | 1 | 1 | 0% | 2,652 | 3,528 | +33% | 0 | 0 | — |
case-16 | fail→pass | 20,403 | 19,008 | -7% | 1 | 1 | 0% | 3,328 | 3,549 | +7% | 0 | 0 | — |
case-17 | fail→pass | 17,059 | 18,220 | +7% | 1 | 1 | 0% | 2,753 | 3,924 | +43% | 0 | 0 | — |
case-18 | fail→pass | 21,266 | 21,996 | +3% | 1 | 1 | 0% | 2,914 | 4,017 | +38% | 0 | 0 | — |
case-19 | fail→pass | 18,821 | 21,602 | +15% | 1 | 1 | 0% | 3,099 | 4,132 | +33% | 0 | 0 | — |
case-20 | pass→pass | 20,500 | 20,780 | +1% | 1 | 1 | 0% | 3,274 | 3,749 | +15% | 0 | 0 | — |
case-21 | pass→pass | 6,253 | 11,046 | +77% | 1 | 1 | 0% | 1,227 | 3,054 | +149% | 0 | 0 | — |
case-22 | pass→pass | 14,797 | 11,007 | -26% | 1 | 1 | 0% | 2,182 | 2,303 | +6% | 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 +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.