Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →You are a TikTok culture native who understands the platform's viral mechanics, algorithm intricacies, and generational nuances. You think in micro-content, speak in trends, and create with viralit...
.claude/skills/dev-dennis-040-marketing-tiktok-strategist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 65% | 0% |
name: TikTok Strategist description: Expert TikTok marketing specialist focused on viral content creation, algorithm optimization, and community building. Masters TikTok's unique culture and features for brand growth. color: "#000000"
You are a TikTok culture native who understands the platform's viral mechanics, algorithm intricacies, and generational nuances. You think in micro-content, speak in trends, and create with virality in mind. Your expertise combines creative storytelling with data-driven optimization, always staying ahead of the rapidly evolving TikTok landscape.
Core Identity: Viral content architect who transforms brands into TikTok sensations through trend mastery, algorithm optimization, and authentic community building.
Drive brand growth on TikTok through:
Remember: You're not just creating TikTok content - you're engineering viral moments that capture cultural attention and transform brand awareness into measurable business growth through authentic community connection.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 12,761 | 16,477 | +29% | 1 | 1 | 0% | 2,627 | 3,809 | +45% | 0 | 0 | — |
case-01 | fail→fail | 17,306 | 17,136 | -1% | 1 | 1 | 0% | 3,324 | 3,834 | +15% | 0 | 0 | — |
case-03 | fail→pass | 21,867 | 20,623 | -6% | 1 | 1 | 0% | 4,327 | 5,557 | +28% | 0 | 0 | — |
case-04 | pass→fail | 12,999 | 15,410 | +19% | 1 | 1 | 0% | 2,443 | 3,643 | +49% | 0 | 0 | — |
case-05 | pass→pass | 14,124 | 14,063 | -0% | 1 | 1 | 0% | 2,692 | 3,848 | +43% | 0 | 0 | — |
case-06 | pass→pass | 9,346 | 7,660 | -18% | 1 | 1 | 0% | 2,283 | 3,174 | +39% | 0 | 0 | — |
case-07 | pass→pass | 6,740 | 5,731 | -15% | 1 | 1 | 0% | 1,373 | 2,631 | +92% | 0 | 0 | — |
case-08 | fail→pass | 9,530 | 5,440 | -43% | 1 | 1 | 0% | 1,889 | 2,499 | +32% | 0 | 0 | — |
case-09 | fail→pass | 9,991 | 8,874 | -11% | 1 | 1 | 0% | 1,988 | 3,110 | +56% | 0 | 0 | — |
case-10 | fail→fail | 9,973 | 12,494 | +25% | 1 | 1 | 0% | 1,911 | 3,173 | +66% | 0 | 0 | — |
case-11 | fail→pass | 10,226 | 11,746 | +15% | 1 | 1 | 0% | 1,942 | 3,206 | +65% | 0 | 0 | — |
case-12 | fail→pass | 11,150 | 9,476 | -15% | 1 | 1 | 0% | 2,304 | 3,315 | +44% | 0 | 0 | — |
case-13 | fail→pass | 17,947 | 10,455 | -42% | 1 | 1 | 0% | 2,641 | 3,439 | +30% | 0 | 0 | — |
case-14 | fail→pass | 10,666 | 7,833 | -27% | 1 | 1 | 0% | 2,068 | 3,035 | +47% | 0 | 0 | — |
case-15 | fail→pass | 10,494 | 8,516 | -19% | 1 | 1 | 0% | 2,132 | 3,060 | +44% | 0 | 0 | — |
case-16 | pass→pass | 9,052 | 5,278 | -42% | 1 | 1 | 0% | 1,891 | 2,427 | +28% | 0 | 0 | — |
case-17 | pass→pass | 9,855 | 4,619 | -53% | 1 | 1 | 0% | 1,884 | 2,307 | +22% | 0 | 0 | — |
case-18 | fail→pass | 11,531 | 3,236 | -72% | 1 | 1 | 0% | 2,215 | 2,042 | -8% | 0 | 0 | — |
case-19 | fail→fail | 9,928 | 12,326 | +24% | 1 | 1 | 0% | 2,046 | 3,851 | +88% | 0 | 0 | — |
case-20 | pass→pass | 12,274 | 12,504 | +2% | 1 | 1 | 0% | 2,376 | 3,755 | +58% | 0 | 0 | — |
case-21 | fail→fail | 13,490 | 12,176 | -10% | 1 | 1 | 0% | 2,537 | 3,607 | +42% | 0 | 0 | — |
case-22 | pass→pass | 15,566 | 14,531 | -7% | 1 | 1 | 0% | 2,691 | 4,187 | +56% | 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 +41 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.