Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive marketing strategy across 25 disciplines — positioning, copywriting frameworks, buyer psychology, SEO, CRO, paid ads, funnel architecture, content strategy, growth loops, analytics, pricing, product launches, and competitive intelligence. Use when the user needs marketing strategy, campaign planning, copy review, landing page audits, ad creation, GTM plans, or growth advice.
.claude/skills/cowork-os-marketing-strategist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
Comprehensive marketing strategy across 25 disciplines — positioning, copywriting frameworks, buyer psychology, SEO, CRO, paid ads, funnel architecture, content strategy, growth loops, analytics, pricing, product launches, and competitive intelligence. Use when the user needs marketing strategy, campaign planning, copy review, landing page audits, ad creation, GTM plans, or growth advice.
| Name | Type | Required | Description | |---|---|---|---| | task | string | No | What to do (e.g., 'audit my landing page', 'write ad copy', 'build a GTM plan', 'improve SEO', 'create pricing strategy') | | channel | select | No | Focus channel or discipline | | stage | select | No | Business stage for tailored advice |
../marketing-strategist.json.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,411 | 14,498 | +1% | 1 | 1 | 0% | 2,446 | 2,862 | +17% | 0 | 0 | — |
case-02 | fail→fail | 11,302 | 11,178 | -1% | 1 | 1 | 0% | 1,819 | 2,041 | +12% | 0 | 0 | — |
case-03 | fail→fail | 17,028 | 18,902 | +11% | 1 | 1 | 0% | 2,630 | 3,188 | +21% | 0 | 0 | — |
case-04 | pass→pass | 11,239 | 10,069 | -10% | 1 | 1 | 0% | 1,822 | 2,022 | +11% | 0 | 0 | — |
case-05 | pass→pass | 11,982 | 11,044 | -8% | 1 | 1 | 0% | 2,071 | 2,307 | +11% | 0 | 0 | — |
case-06 | fail→pass | 15,939 | 16,647 | +4% | 1 | 1 | 0% | 2,401 | 3,006 | +25% | 0 | 0 | — |
case-07 | pass→pass | 11,751 | 13,369 | +14% | 1 | 1 | 0% | 2,039 | 2,674 | +31% | 0 | 0 | — |
case-08 | pass→pass | 16,252 | 15,317 | -6% | 1 | 1 | 0% | 2,585 | 2,918 | +13% | 0 | 0 | — |
case-09 | pass→pass | 11,433 | 12,328 | +8% | 1 | 1 | 0% | 1,852 | 2,328 | +26% | 0 | 0 | — |
case-10 | pass→pass | 13,604 | 11,400 | -16% | 1 | 1 | 0% | 2,445 | 2,494 | +2% | 0 | 0 | — |
case-11 | fail→pass | 21,857 | 23,027 | +5% | 1 | 1 | 0% | 3,418 | 4,194 | +23% | 0 | 0 | — |
case-12 | pass→pass | 20,577 | 21,893 | +6% | 1 | 1 | 0% | 3,006 | 3,732 | +24% | 0 | 0 | — |
case-13 | pass→pass | 7,158 | 7,362 | +3% | 1 | 1 | 0% | 1,108 | 1,683 | +52% | 0 | 0 | — |
case-14 | pass→pass | 16,119 | 18,368 | +14% | 1 | 1 | 0% | 2,617 | 3,428 | +31% | 0 | 0 | — |
case-15 | pass→pass | 16,053 | 12,069 | -25% | 1 | 1 | 0% | 2,356 | 2,416 | +3% | 0 | 0 | — |
case-16 | pass→pass | 22,748 | 21,331 | -6% | 1 | 1 | 0% | 3,375 | 3,851 | +14% | 0 | 0 | — |
case-17 | pass→pass | 10,830 | 9,913 | -8% | 1 | 1 | 0% | 1,719 | 1,980 | +15% | 0 | 0 | — |
case-18 | fail→fail | 18,912 | 19,828 | +5% | 1 | 1 | 0% | 3,038 | 3,620 | +19% | 0 | 0 | — |
case-19 | pass→pass | 17,477 | 19,019 | +9% | 1 | 1 | 0% | 2,788 | 2,722 | -2% | 0 | 0 | — |
case-20 | pass→pass | 12,030 | 12,199 | +1% | 1 | 1 | 0% | 1,829 | 2,394 | +31% | 0 | 0 | — |
case-21 | pass→pass | 8,738 | 8,671 | -1% | 1 | 1 | 0% | 1,349 | 1,818 | +35% | 0 | 0 | — |
case-22 | fail→fail | 20,558 | 20,389 | -1% | 1 | 1 | 0% | 3,051 | 3,430 | +12% | 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 +9 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.