Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan a co-marketing partnership — two brands reaching each other's audiences for mutual gain. Use when asked to plan a partnership, joint campaign, co-branded content/webinar, integration launch, or partner outreach. Produces the partner fit rationale, a fair value exchange, the joint campaign plan, the partner pitch, and how success is split and measured.
.claude/skills/mohitagw15856-co-marketing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 31% | 0% |
Co-marketing pairs two non-competing brands with overlapping audiences to do something together — a webinar, co-branded content, a bundle, an integration launch — so each reaches the other's customers at near-zero CAC. It works only when the audience overlap is real and the value exchange is fair. This skill plans that: the fit, the deal, the campaign, and the pitch.
Ask for these only if they aren't already provided:
1. Partner fit — why this pairing: the shared audience (who overlaps), why you're complementary not competitive, and what each side uniquely brings. If a profile, name 3–5 candidate partners.
2. Value exchange — what each side gives and gets, made fair and balanced (mismatched reach is the #1 killer — address it):
| | You give | You get | |---|---|---| | Partner | | |
3. The campaign — the joint activity (co-webinar / co-branded guide / bundle / integration launch / newsletter swap), the assets needed, owners, and a rough timeline.
4. Promotion & lead split — how each side promotes (email, social, site), and how leads/credit are shared and followed up — agreed up front to avoid the post-campaign fight.
5. The partner pitch — a short outreach message a partner would say yes to: lead with their benefit (your audience, your asset), make the lift small, propose one concrete first activity.
6. Success metrics — what you each measure (leads, signups, attributed pipeline, reach), and a quick post-mortem plan.
Partnership / co-marketing practice (audience-overlap fit, balanced value exchange, joint campaign + lead-sharing, partner-first pitch).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 10,162 | 12,736 | +25% | 1 | 1 | 0% | 1,696 | 2,797 | +65% | 0 | 0 | — |
case-01 | fail→pass | 23,316 | 18,538 | -20% | 1 | 1 | 0% | 4,036 | 3,969 | -2% | 0 | 0 | — |
case-02 | fail→pass | 22,839 | 19,569 | -14% | 1 | 1 | 0% | 4,290 | 4,405 | +3% | 0 | 0 | — |
case-03 | fail→pass | 19,522 | 19,462 | -0% | 1 | 1 | 0% | 3,564 | 4,084 | +15% | 0 | 0 | — |
case-04 | pass→fail | 20,617 | 18,668 | -9% | 1 | 1 | 0% | 3,747 | 3,924 | +5% | 0 | 0 | — |
case-05 | pass→pass | 13,259 | 13,323 | +0% | 1 | 1 | 0% | 2,452 | 3,282 | +34% | 0 | 0 | — |
case-06 | pass→pass | 13,724 | 16,535 | +20% | 1 | 1 | 0% | 2,376 | 3,583 | +51% | 0 | 0 | — |
case-07 | pass→pass | 15,881 | 16,657 | +5% | 1 | 1 | 0% | 2,651 | 3,748 | +41% | 0 | 0 | — |
case-09 | pass→pass | 15,654 | 14,689 | -6% | 1 | 1 | 0% | 2,760 | 3,129 | +13% | 0 | 0 | — |
case-10 | pass→pass | 19,719 | 14,765 | -25% | 1 | 1 | 0% | 3,491 | 3,155 | -10% | 0 | 0 | — |
case-11 | fail→pass | 16,957 | 16,409 | -3% | 1 | 1 | 0% | 2,842 | 3,721 | +31% | 0 | 0 | — |
case-12 | pass→pass | 14,669 | 12,868 | -12% | 1 | 1 | 0% | 2,503 | 3,035 | +21% | 0 | 0 | — |
case-13 | pass→pass | 13,469 | 10,995 | -18% | 1 | 1 | 0% | 2,565 | 2,517 | -2% | 0 | 0 | — |
case-14 | pass→pass | 16,321 | 20,143 | +23% | 1 | 1 | 0% | 2,787 | 4,065 | +46% | 0 | 0 | — |
case-15 | pass→pass | 10,774 | 14,926 | +39% | 1 | 1 | 0% | 1,757 | 3,200 | +82% | 0 | 0 | — |
case-16 | pass→pass | 11,673 | 17,868 | +53% | 1 | 1 | 0% | 1,899 | 3,615 | +90% | 0 | 0 | — |
case-17 | pass→pass | 17,624 | 16,755 | -5% | 1 | 1 | 0% | 2,990 | 3,518 | +18% | 0 | 0 | — |
case-18 | pass→pass | 18,149 | 17,858 | -2% | 1 | 1 | 0% | 3,140 | 3,691 | +18% | 0 | 0 | — |
case-19 | fail→pass | 14,954 | 16,311 | +9% | 1 | 1 | 0% | 2,641 | 3,523 | +33% | 0 | 0 | — |
case-20 | pass→pass | 12,727 | 14,020 | +10% | 1 | 1 | 0% | 2,098 | 2,917 | +39% | 0 | 0 | — |
case-21 | pass→pass | 18,240 | 16,971 | -7% | 1 | 1 | 0% | 3,112 | 3,459 | +11% | 0 | 0 | — |
case-22 | fail→pass | 16,866 | 15,231 | -10% | 1 | 1 | 0% | 2,666 | 3,345 | +25% | 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 +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.