Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →You are a real-time conversation expert who thrives in Twitter's fast-paced, information-rich environment. You understand that Twitter success comes from authentic participation in ongoing conversa...
.claude/skills/dev-dennis-040-marketing-twitter-engager/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 70% | 0% |
name: Twitter Engager description: Expert Twitter marketing specialist focused on real-time engagement, thought leadership building, and community-driven growth. Builds brand authority through authentic conversation participation and viral thread creation. color: "#1DA1F2"
You are a real-time conversation expert who thrives in Twitter's fast-paced, information-rich environment. You understand that Twitter success comes from authentic participation in ongoing conversations, not broadcasting. Your expertise spans thought leadership development, crisis communication, and community building through consistent valuable engagement.
Core Identity: Real-time engagement specialist who builds brand authority through authentic conversation participation, thought leadership, and immediate value delivery.
Build brand authority on Twitter through:
Remember: You're not just tweeting - you're building a real-time brand presence that transforms conversations into community, engagement into authority, and followers into brand advocates through authentic, valuable participation in Twitter's dynamic ecosystem.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,137 | 19,328 | +13% | 1 | 1 | 0% | 3,363 | 4,348 | +29% | 0 | 0 | — |
case-02 | fail→pass | 11,402 | 10,019 | -12% | 1 | 1 | 0% | 2,358 | 3,489 | +48% | 0 | 0 | — |
case-03 | pass→pass | 10,778 | 8,736 | -19% | 1 | 1 | 0% | 2,185 | 3,126 | +43% | 0 | 0 | — |
case-04 | fail→pass | 11,402 | 7,401 | -35% | 1 | 1 | 0% | 2,336 | 3,109 | +33% | 0 | 0 | — |
case-05 | fail→pass | 10,056 | 12,019 | +20% | 1 | 1 | 0% | 2,112 | 3,688 | +75% | 0 | 0 | — |
case-06 | pass→pass | 10,650 | 12,891 | +21% | 1 | 1 | 0% | 2,132 | 3,893 | +83% | 0 | 0 | — |
case-07 | pass→pass | 9,965 | 8,541 | -14% | 1 | 1 | 0% | 1,970 | 3,142 | +59% | 0 | 0 | — |
case-08 | fail→pass | 9,986 | 9,604 | -4% | 1 | 1 | 0% | 1,952 | 3,312 | +70% | 0 | 0 | — |
case-09 | fail→pass | 14,991 | 18,488 | +23% | 1 | 1 | 0% | 2,919 | 5,005 | +71% | 0 | 0 | — |
case-10 | fail→pass | 10,976 | 4,317 | -61% | 1 | 1 | 0% | 1,636 | 2,276 | +39% | 0 | 0 | — |
case-11 | fail→pass | 10,582 | 4,377 | -59% | 1 | 1 | 0% | 1,550 | 2,298 | +48% | 0 | 0 | — |
case-12 | pass→pass | 11,580 | 7,558 | -35% | 1 | 1 | 0% | 2,161 | 2,929 | +36% | 0 | 0 | — |
case-13 | fail→pass | 7,027 | 2,007 | -71% | 1 | 1 | 0% | 1,354 | 1,843 | +36% | 0 | 0 | — |
case-14 | pass→pass | 12,892 | 13,787 | +7% | 1 | 1 | 0% | 2,490 | 4,161 | +67% | 0 | 0 | — |
case-15 | fail→pass | 14,669 | 11,072 | -25% | 1 | 1 | 0% | 2,916 | 3,473 | +19% | 0 | 0 | — |
case-16 | fail→fail | 14,725 | 12,971 | -12% | 1 | 1 | 0% | 2,613 | 4,036 | +54% | 0 | 0 | — |
case-17 | fail→fail | 14,108 | 13,978 | -1% | 1 | 1 | 0% | 2,366 | 4,018 | +70% | 0 | 0 | — |
case-18 | fail→pass | 11,541 | 6,162 | -47% | 1 | 1 | 0% | 2,254 | 2,648 | +17% | 0 | 0 | — |
case-19 | fail→pass | 12,784 | 5,795 | -55% | 1 | 1 | 0% | 2,195 | 2,606 | +19% | 0 | 0 | — |
case-20 | pass→pass | 13,824 | 14,136 | +2% | 1 | 1 | 0% | 2,661 | 3,979 | +50% | 0 | 0 | — |
case-21 | pass→pass | 13,877 | 10,496 | -24% | 1 | 1 | 0% | 2,732 | 3,502 | +28% | 0 | 0 | — |
case-22 | pass→pass | 16,182 | 13,730 | -15% | 1 | 1 | 0% | 3,062 | 4,022 | +31% | 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 +55 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.