Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provide proven marketing strategies and growth ideas for SaaS and software products, prioritized using a marketing feasibility scoring system.
.claude/skills/dokhacgiakhoa-marketing-ideas/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 42% | 0% |
| case-20 | ✓→✓ | = Same ✓ | 67% | 0% |
You are a marketing strategist and operator with a curated library of 140 proven marketing ideas.
Your role is not to brainstorm endlessly — it is to select, score, and prioritize the right marketing ideas based on feasibility, impact, and constraints.
This skill helps users decide:
When a user asks for marketing ideas:
> ❌ Do not dump long lists > ✅ Act as a decision filter
Every recommended idea must be scored.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→fail | 17,209 | 11,983 | -30% | 1 | 1 | 0% | 3,115 | 2,835 | -9% | 0 | 0 | — |
case-13 | fail→pass | 19,645 | 22,621 | +15% | 1 | 1 | 0% | 2,545 | 3,343 | +31% | 0 | 0 | — |
case-01 | fail→fail | 11,706 | 29,864 | +155% | 1 | 1 | 0% | 1,945 | 4,192 | +116% | 0 | 0 | — |
case-02 | fail→pass | 31,995 | 20,490 | -36% | 1 | 1 | 0% | 4,241 | 3,800 | -10% | 0 | 0 | — |
case-03 | pass→pass | 20,051 | 28,353 | +41% | 1 | 1 | 0% | 3,207 | 4,565 | +42% | 0 | 0 | — |
case-04 | fail→fail | 19,929 | 25,157 | +26% | 1 | 1 | 0% | 2,987 | 4,105 | +37% | 0 | 0 | — |
case-05 | fail→fail | 21,553 | 15,068 | -30% | 1 | 1 | 0% | 2,955 | 3,297 | +12% | 0 | 0 | — |
case-06 | fail→fail | 15,482 | 21,145 | +37% | 1 | 1 | 0% | 2,066 | 3,634 | +76% | 0 | 0 | — |
case-07 | fail→fail | 16,594 | 14,802 | -11% | 1 | 1 | 0% | 2,545 | 2,876 | +13% | 0 | 0 | — |
case-09 | fail→fail | 20,233 | 22,499 | +11% | 1 | 1 | 0% | 2,877 | 4,574 | +59% | 0 | 0 | — |
case-10 | fail→fail | 14,685 | 24,097 | +64% | 1 | 1 | 0% | 2,330 | 4,671 | +100% | 0 | 0 | — |
case-11 | fail→fail | 18,149 | 18,507 | +2% | 1 | 1 | 0% | 2,693 | 3,473 | +29% | 0 | 0 | — |
case-12 | fail→fail | 18,019 | 15,187 | -16% | 1 | 1 | 0% | 2,419 | 2,914 | +20% | 0 | 0 | — |
case-14 | fail→pass | 25,304 | 10,536 | -58% | 1 | 1 | 0% | 3,881 | 2,171 | -44% | 0 | 0 | — |
case-15 | fail→fail | 20,214 | 24,746 | +22% | 1 | 1 | 0% | 2,751 | 3,953 | +44% | 0 | 0 | — |
case-16 | fail→fail | 22,797 | 20,692 | -9% | 1 | 1 | 0% | 3,257 | 4,023 | +24% | 0 | 0 | — |
case-17 | fail→fail | 18,212 | 20,486 | +12% | 1 | 1 | 0% | 2,975 | 3,961 | +33% | 0 | 0 | — |
case-18 | fail→fail | 56,923 | 31,813 | -44% | 1 | 1 | 0% | 8,241 | 5,141 | -38% | 0 | 0 | — |
case-19 | fail→fail | 20,781 | 18,515 | -11% | 1 | 1 | 0% | 3,261 | 3,252 | -0% | 0 | 0 | — |
case-20 | pass→pass | 13,384 | 14,884 | +11% | 1 | 1 | 0% | 1,931 | 3,217 | +67% | 0 | 0 | — |
case-21 | pass→pass | 15,098 | 16,172 | +7% | 1 | 1 | 0% | 2,590 | 2,883 | +11% | 0 | 0 | — |
case-22 | pass→pass | 7,208 | 7,536 | +5% | 1 | 1 | 0% | 1,479 | 2,033 | +37% | 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 +14 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.