Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Elite content marketing strategist specializing in AI-powered content creation, omnichannel distribution, SEO optimization, and data-driven performance marketing. Masters modern content tools, social media automation, and conversion optimization with 2024/2025 best practices. Use PROACTIVELY for comprehensive content marketing.
.claude/skills/dokhacgiakhoa-content-marketer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | -8% | 0% |
resources/implementation-playbook.md.You are an elite content marketing strategist specializing in AI-powered content creation, omnichannel marketing, and data-driven content optimization.
Master content marketer focused on creating high-converting, SEO-optimized content across all digital channels using cutting-edge AI tools and data-driven strategies. Combines deep understanding of audience psychology, content optimization techniques, and modern marketing automation to drive engagement, leads, and revenue through strategic content initiatives.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→pass | 19,283 | 16,481 | -15% | 1 | 1 | 0% | 3,627 | 3,329 | -8% | 0 | 0 | — |
case-14 | fail→fail | 18,327 | 21,497 | +17% | 1 | 1 | 0% | 2,602 | 3,695 | +42% | 0 | 0 | — |
case-01 | fail→fail | 23,786 | 30,098 | +27% | 1 | 1 | 0% | 3,858 | 4,812 | +25% | 0 | 0 | — |
case-02 | fail→fail | 30,813 | 25,040 | -19% | 1 | 1 | 0% | 5,084 | 4,736 | -7% | 0 | 0 | — |
case-03 | fail→pass | 11,541 | 8,082 | -30% | 1 | 1 | 0% | 2,067 | 1,917 | -7% | 0 | 0 | — |
case-04 | fail→fail | 13,504 | 13,991 | +4% | 1 | 1 | 0% | 2,545 | 3,063 | +20% | 0 | 0 | — |
case-05 | fail→fail | 25,047 | 21,512 | -14% | 1 | 1 | 0% | 3,971 | 4,372 | +10% | 0 | 0 | — |
case-06 | fail→fail | 20,236 | 21,188 | +5% | 1 | 1 | 0% | 3,210 | 3,293 | +3% | 0 | 0 | — |
case-08 | pass→pass | 19,796 | 13,310 | -33% | 1 | 1 | 0% | 3,173 | 2,656 | -16% | 0 | 0 | — |
case-09 | fail→fail | 19,787 | 19,485 | -2% | 1 | 1 | 0% | 2,739 | 3,147 | +15% | 0 | 0 | — |
case-10 | pass→pass | 21,862 | 21,022 | -4% | 1 | 1 | 0% | 3,558 | 3,331 | -6% | 0 | 0 | — |
case-11 | pass→pass | 17,241 | 24,170 | +40% | 1 | 1 | 0% | 2,848 | 4,640 | +63% | 0 | 0 | — |
case-12 | pass→pass | 20,945 | 16,877 | -19% | 1 | 1 | 0% | 2,715 | 2,963 | +9% | 0 | 0 | — |
case-13 | pass→pass | 19,859 | 20,445 | +3% | 1 | 1 | 0% | 3,248 | 2,810 | -13% | 0 | 0 | — |
case-15 | fail→pass | 19,022 | 17,491 | -8% | 1 | 1 | 0% | 3,022 | 3,047 | +1% | 0 | 0 | — |
case-16 | fail→fail | 17,509 | 16,527 | -6% | 1 | 1 | 0% | 2,835 | 2,669 | -6% | 0 | 0 | — |
case-17 | pass→pass | 16,163 | 15,813 | -2% | 1 | 1 | 0% | 2,235 | 2,979 | +33% | 0 | 0 | — |
case-18 | fail→pass | 17,346 | 17,620 | +2% | 1 | 1 | 0% | 2,494 | 2,923 | +17% | 0 | 0 | — |
case-19 | fail→pass | 20,497 | 16,350 | -20% | 1 | 1 | 0% | 2,730 | 2,998 | +10% | 0 | 0 | — |
case-20 | fail→fail | 48,589 | 44,415 | -9% | 1 | 1 | 0% | 8,219 | 6,668 | -19% | 0 | 0 | — |
case-21 | fail→fail | 18,630 | 20,986 | +13% | 1 | 1 | 0% | 2,688 | 3,482 | +30% | 0 | 0 | — |
case-22 | fail→fail | 15,579 | 15,242 | -2% | 1 | 1 | 0% | 2,038 | 2,684 | +32% | 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 +18 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.