Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints. Use when generating new feature ideas, brainstorming solutions for an identified opportunity, or ideating with a product trio.
.claude/skills/phuryn-brainstorm-ideas-existing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 32% | 0% |
Multi-perspective ideation for continuous product discovery. Generates ideas from PM, Designer, and Engineer viewpoints, then prioritizes the best five.
You are supporting a product trio performing continuous product discovery for $ARGUMENTS.
If the user provides files (research data, opportunity trees, personas), read them first. If they mention a product URL, use web search to understand the product.
Product Trio (Teresa Torres, Continuous Discovery Habits): PM + Designer + Engineer collaborate on discovery together. "Best ideas often come from engineers." Discovery is not linear — loop back if experiments fail. Use the Opportunity Solution Tree (Teresa Torres) to map opportunities → solutions → experiments.
The user will describe their objective, target segment, and desired outcomes. Work through these steps:
Think step by step. Present ideas in a clear, structured format.
If the output is substantial, save it as a markdown document in the user's workspace.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→pass | 16,706 | 24,951 | +49% | 1 | 1 | 0% | 2,831 | 4,034 | +42% | 0 | 0 | — |
case-16 | fail→pass | 18,731 | 24,907 | +33% | 1 | 1 | 0% | 2,728 | 4,751 | +74% | 0 | 0 | — |
case-01 | fail→pass | 19,462 | 23,321 | +20% | 1 | 1 | 0% | 3,122 | 4,380 | +40% | 0 | 0 | — |
case-02 | fail→pass | 35,986 | 22,442 | -38% | 1 | 1 | 0% | 3,750 | 4,204 | +12% | 0 | 0 | — |
case-03 | fail→pass | 20,426 | 33,155 | +62% | 1 | 1 | 0% | 3,407 | 4,482 | +32% | 0 | 0 | — |
case-04 | fail→fail | 12,793 | 18,756 | +47% | 1 | 1 | 0% | 2,126 | 3,581 | +68% | 0 | 0 | — |
case-05 | fail→pass | 16,867 | 28,240 | +67% | 1 | 1 | 0% | 2,923 | 4,529 | +55% | 0 | 0 | — |
case-06 | fail→pass | 20,864 | 21,455 | +3% | 1 | 1 | 0% | 3,495 | 3,951 | +13% | 0 | 0 | — |
case-07 | fail→pass | 15,476 | 20,894 | +35% | 1 | 1 | 0% | 2,548 | 4,079 | +60% | 0 | 0 | — |
case-08 | pass→pass | 13,915 | 22,563 | +62% | 1 | 1 | 0% | 2,320 | 4,306 | +86% | 0 | 0 | — |
case-09 | pass→pass | 19,212 | 21,270 | +11% | 1 | 1 | 0% | 3,251 | 4,019 | +24% | 0 | 0 | — |
case-11 | fail→pass | 17,346 | 23,411 | +35% | 1 | 1 | 0% | 2,855 | 4,170 | +46% | 0 | 0 | — |
case-12 | fail→pass | 20,164 | 20,640 | +2% | 1 | 1 | 0% | 2,630 | 3,917 | +49% | 0 | 0 | — |
case-13 | pass→fail | 21,092 | 5,432 | -74% | 1 | 1 | 0% | 2,922 | 895 | -69% | 0 | 0 | — |
case-14 | fail→pass | 16,920 | 19,760 | +17% | 1 | 1 | 0% | 2,515 | 2,924 | +16% | 0 | 0 | — |
case-15 | pass→pass | 18,885 | 24,739 | +31% | 1 | 1 | 0% | 3,143 | 3,586 | +14% | 0 | 0 | — |
case-17 | fail→pass | 20,457 | 35,191 | +72% | 1 | 1 | 0% | 2,577 | 5,277 | +105% | 0 | 0 | — |
case-18 | fail→pass | 20,940 | 23,712 | +13% | 1 | 1 | 0% | 3,316 | 4,342 | +31% | 0 | 0 | — |
case-19 | fail→pass | 16,828 | 20,876 | +24% | 1 | 1 | 0% | 2,761 | 4,104 | +49% | 0 | 0 | — |
case-20 | fail→pass | 23,885 | 22,618 | -5% | 1 | 1 | 0% | 3,320 | 4,276 | +29% | 0 | 0 | — |
case-21 | pass→pass | 28,745 | 17,309 | -40% | 1 | 1 | 0% | 4,347 | 3,419 | -21% | 0 | 0 | — |
case-22 | pass→pass | 13,980 | 12,398 | -11% | 1 | 1 | 0% | 2,600 | 3,460 | +33% | 0 | 0 | — |
case-23 | pass→fail | 15,499 | 6,120 | -61% | 1 | 1 | 0% | 2,952 | 1,357 | -54% | 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. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +57 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.