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/sickn33-marketing-ideas/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -10% | 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.
Each idea is scored across five dimensions, each from 1–5.
| Dimension | Question | | ------------------- | ------------------------------------------------- | | Impact | If this works, how meaningful is the upside? | | Effort | How much execution time/complexity is required? | | Cost | How much cash is required to test meaningfully? | | Speed to Signal | How quickly will we know if it’s working? | | Fit | How well does this match product, ICP, and stage? |
Marketing Feasibility Score (MFS)
= (Impact + Fit + Speed) − (Effort + Cost)Score Range: -7 → +13
| MFS Score | Meaning | Action | | --------- | ----------------------- | ---------------- | | 10–13 | Extremely high leverage | Do now | | 7–9 | Strong opportunity | Prioritize | | 4–6 | Viable but situational | Test selectively | | 1–3 | Marginal | Defer | | ≤ 0 | Poor fit | Do not recommend |
Idea: Programmatic SEO (Early-stage SaaS)
| Factor | Score | | ------ | ----- | | Impact | 5 | | Fit | 4 | | Speed | 2 | | Effort | 4 | | Cost | 3 |
MFS = (5 + 4 + 2) − (4 + 3) = 4➡️ Viable, but not a short-term win
When recommending ideas:
> Each idea is a pattern, not a tactic. > Feasibility depends on context — that’s why scoring exists.
(Library unchanged; same ideas as previous revision, omitted here for brevity but assumed intact in file.)
When recommending ideas, always use this format:
MFS: +6 (Viable – prioritize after quick wins)
Large keyword surface, repeatable structure, long-term traffic compounding
Consistent non-brand traffic within 3–6 months
SEO expertise, content templates, engineering support
Slow feedback loop and upfront content investment
Use these biases when scoring:
This skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 24,790 | 20,122 | -19% | 1 | 1 | 0% | 4,017 | 4,885 | +22% | 0 | 0 | — |
case-02 | fail→pass | 24,172 | 17,230 | -29% | 1 | 1 | 0% | 4,089 | 4,543 | +11% | 0 | 0 | — |
case-03 | fail→pass | 27,660 | 20,818 | -25% | 1 | 1 | 0% | 4,695 | 5,038 | +7% | 0 | 0 | — |
case-04 | pass→pass | 16,632 | 17,620 | +6% | 1 | 1 | 0% | 2,741 | 4,487 | +64% | 0 | 0 | — |
case-05 | fail→pass | 13,973 | 6,314 | -55% | 1 | 1 | 0% | 2,430 | 2,362 | -3% | 0 | 0 | — |
case-10 | fail→pass | 11,041 | 2,604 | -76% | 1 | 1 | 0% | 2,111 | 1,906 | -10% | 0 | 0 | — |
case-06 | fail→pass | 18,034 | 19,656 | +9% | 1 | 1 | 0% | 2,999 | 4,823 | +61% | 0 | 0 | — |
case-07 | pass→pass | 16,778 | 16,670 | -1% | 1 | 1 | 0% | 2,511 | 4,511 | +80% | 0 | 0 | — |
case-08 | pass→pass | 15,787 | 15,590 | -1% | 1 | 1 | 0% | 2,497 | 4,069 | +63% | 0 | 0 | — |
case-09 | fail→pass | 14,349 | 4,104 | -71% | 1 | 1 | 0% | 2,843 | 2,137 | -25% | 0 | 0 | — |
case-11 | fail→pass | 11,933 | 3,592 | -70% | 1 | 1 | 0% | 2,373 | 2,043 | -14% | 0 | 0 | — |
case-12 | fail→pass | 7,880 | 3,026 | -62% | 1 | 1 | 0% | 1,548 | 1,969 | +27% | 0 | 0 | — |
case-13 | fail→pass | 11,963 | 13,535 | +13% | 1 | 1 | 0% | 2,044 | 3,783 | +85% | 0 | 0 | — |
case-14 | fail→pass | 9,672 | 3,574 | -63% | 1 | 1 | 0% | 1,621 | 1,969 | +21% | 0 | 0 | — |
case-20 | pass→fail | 16,135 | 14,882 | -8% | 1 | 1 | 0% | 2,526 | 3,934 | +56% | 0 | 0 | — |
case-15 | pass→pass | 10,766 | 9,141 | -15% | 1 | 1 | 0% | 1,881 | 3,150 | +67% | 0 | 0 | — |
case-16 | pass→pass | 5,971 | 5,618 | -6% | 1 | 1 | 0% | 1,120 | 2,463 | +120% | 0 | 0 | — |
case-17 | pass→pass | 15,224 | 14,349 | -6% | 1 | 1 | 0% | 2,347 | 3,893 | +66% | 0 | 0 | — |
case-18 | pass→pass | 9,056 | 4,568 | -50% | 1 | 1 | 0% | 1,560 | 2,251 | +44% | 0 | 0 | — |
case-19 | fail→pass | 10,379 | 2,813 | -73% | 1 | 1 | 0% | 1,948 | 2,001 | +3% | 0 | 0 | — |
case-21 | pass→fail | 15,437 | 13,754 | -11% | 1 | 1 | 0% | 2,493 | 3,760 | +51% | 0 | 0 | — |
case-22 | pass→pass | 9,412 | 11,188 | +19% | 1 | 1 | 0% | 2,028 | 3,819 | +88% | 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. 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.