Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan a full-funnel marketing strategy from awareness to retention. Use when asked to build a marketing funnel, map the customer journey to tactics, plan demand generation, or diagnose where a funnel leaks. Produces a funnel plan — stage definitions, the metric and conversion target per stage, channels & tactics, the biggest leak, and a 90-day focus.
.claude/skills/mohitagw15856-marketing-funnel-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 21% | 0% |
Most marketing plans are a list of tactics with no theory of how they connect. This skill builds the funnel as a system: each stage has a definition, a metric, a conversion rate, and the tactics that move people to the next stage — so you can see where the funnel actually leaks and spend there, not everywhere.
Ask for these only if they aren't already provided:
1. Funnel map — a stage-by-stage table (the spine of the plan):
| Stage | Definition (entry → exit) | Metric | Current | Target | Primary channels/tactics | |---|---|---|---|---|---| | Awareness | | reach / visits | | | | | Acquisition | | signups | | | | | Activation | | first value moment | | | | | Revenue | | paid conversion | | | | | Retention | | active / renewed | | | | | Referral | | invites / shares | | | |
2. The biggest leak — the stage with the worst conversion vs. benchmark, and why fixing it beats adding top-of-funnel volume.
3. Channel strategy — which channels serve which stage, and the one or two channels to go deep on (not all of them).
4. Measurement — how each stage is tracked, attribution approach (and its limits), and the leading indicator you'll watch weekly.
5. 90-day focus — the 2–3 bets that move the biggest-leak stage, sequenced, with the success metric for each.
Pirate Metrics (AARRR — Dave McClure) and full-funnel demand-generation practice.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 27,122 | 15,840 | -42% | 1 | 1 | 0% | 5,136 | 3,646 | -29% | 0 | 0 | — |
case-02 | fail→pass | 29,195 | 17,043 | -42% | 1 | 1 | 0% | 5,135 | 3,889 | -24% | 0 | 0 | — |
case-03 | fail→pass | 33,048 | 14,915 | -55% | 1 | 1 | 0% | 5,696 | 3,457 | -39% | 0 | 0 | — |
case-04 | pass→pass | 10,508 | 10,166 | -3% | 1 | 1 | 0% | 1,660 | 2,395 | +44% | 0 | 0 | — |
case-05 | pass→pass | 15,684 | 20,901 | +33% | 1 | 1 | 0% | 2,648 | 4,211 | +59% | 0 | 0 | — |
case-10 | pass→pass | 17,868 | 18,563 | +4% | 1 | 1 | 0% | 3,121 | 3,524 | +13% | 0 | 0 | — |
case-06 | pass→pass | 11,572 | 11,396 | -2% | 1 | 1 | 0% | 2,187 | 2,726 | +25% | 0 | 0 | — |
case-07 | pass→pass | 22,440 | 21,908 | -2% | 1 | 1 | 0% | 4,039 | 4,645 | +15% | 0 | 0 | — |
case-08 | fail→pass | 20,097 | 20,183 | +0% | 1 | 1 | 0% | 3,313 | 3,882 | +17% | 0 | 0 | — |
case-09 | fail→fail | 12,708 | 12,810 | +1% | 1 | 1 | 0% | 2,119 | 2,829 | +34% | 0 | 0 | — |
case-11 | pass→pass | 24,147 | 21,803 | -10% | 1 | 1 | 0% | 3,208 | 2,742 | -15% | 0 | 0 | — |
case-12 | pass→pass | 12,328 | 17,778 | +44% | 1 | 1 | 0% | 1,923 | 3,535 | +84% | 0 | 0 | — |
case-13 | pass→pass | 16,734 | 22,157 | +32% | 1 | 1 | 0% | 2,657 | 3,889 | +46% | 0 | 0 | — |
case-14 | pass→pass | 21,535 | 21,457 | -0% | 1 | 1 | 0% | 2,925 | 3,253 | +11% | 0 | 0 | — |
case-15 | fail→pass | 19,158 | 20,154 | +5% | 1 | 1 | 0% | 3,033 | 3,672 | +21% | 0 | 0 | — |
case-16 | pass→pass | 24,027 | 15,190 | -37% | 1 | 1 | 0% | 3,554 | 3,292 | -7% | 0 | 0 | — |
case-17 | fail→pass | 16,975 | 15,675 | -8% | 1 | 1 | 0% | 2,953 | 3,203 | +8% | 0 | 0 | — |
case-18 | pass→pass | 17,529 | 13,645 | -22% | 1 | 1 | 0% | 2,921 | 2,999 | +3% | 0 | 0 | — |
case-19 | fail→pass | 16,838 | 17,603 | +5% | 1 | 1 | 0% | 2,973 | 3,695 | +24% | 0 | 0 | — |
case-20 | pass→pass | 12,637 | 12,622 | -0% | 1 | 1 | 0% | 2,439 | 3,273 | +34% | 0 | 0 | — |
case-21 | fail→pass | 19,820 | 15,572 | -21% | 1 | 1 | 0% | 3,189 | 3,144 | -1% | 0 | 0 | — |
case-22 | pass→pass | 17,175 | 13,818 | -20% | 1 | 1 | 0% | 2,899 | 2,977 | +3% | 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 +36 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.