Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Transform webinar recordings into multiple content assets including blog post series, social media snippets, infographic ideas, email sequences, and sales one-pagers. Extracts key moments, quotes, and insights for maximum content ROI. Use when users need to repurpose webinars, video content, or live presentations into multi-channel marketing materials.
.claude/skills/onewave-ai-webinar-content-repurposer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 241% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 3226% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 159% | 0% |
Turn one webinar into 20+ pieces of content across multiple channels.
references/asset-catalog.md - Full inventory of asset types, funnel mapping, and creation priority.references/output-template.md - The complete Markdown repurposing-plan template to fill in.references/best-practices.md - Best practices, trigger phrases, and example request/response.references/asset-catalog.md.references/asset-catalog.md for the full inventory.references/output-template.md, replacing every bracketed placeholder with content from the source. Attribute quotes and include timestamps throughout.See references/best-practices.md for quality rules, trigger phrases, and a worked example.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 42,255 | 48,163 | +14% | 1 | 1 | 0% | 6,644 | 8,632 | +30% | 0 | 0 | — |
case-02 | fail→pass | 31,398 | 48,360 | +54% | 1 | 1 | 0% | 5,082 | 8,636 | +70% | 0 | 0 | — |
case-03 | fail→pass | 45,598 | 45,621 | +0% | 1 | 1 | 0% | 7,762 | 8,477 | +9% | 0 | 0 | — |
case-04 | fail→fail | 7,424 | 12,217 | +65% | 1 | 1 | 0% | 1,077 | 2,293 | +113% | 0 | 0 | — |
case-05 | fail→fail | 2,411 | 8,509 | +253% | 1 | 1 | 0% | 375 | 1,649 | +340% | 0 | 0 | — |
case-06 | fail→fail | 17,049 | 46,705 | +174% | 1 | 1 | 0% | 2,648 | 8,033 | +203% | 0 | 0 | — |
case-07 | fail→fail | 17,084 | 31,780 | +86% | 1 | 1 | 0% | 2,719 | 5,195 | +91% | 0 | 0 | — |
case-08 | fail→pass | 14,492 | 44,275 | +206% | 1 | 1 | 0% | 2,337 | 7,979 | +241% | 0 | 0 | — |
case-09 | fail→fail | 13,251 | 43,312 | +227% | 1 | 1 | 0% | 2,157 | 8,040 | +273% | 0 | 0 | — |
case-10 | fail→fail | 2,595 | 8,516 | +228% | 1 | 1 | 0% | 360 | 1,605 | +346% | 0 | 0 | — |
case-11 | fail→fail | 9,504 | 13,692 | +44% | 1 | 1 | 0% | 1,573 | 2,249 | +43% | 0 | 0 | — |
case-12 | fail→fail | 11,303 | 19,204 | +70% | 1 | 1 | 0% | 1,896 | 3,608 | +90% | 0 | 0 | — |
case-13 | fail→fail | 14,533 | 24,533 | +69% | 1 | 1 | 0% | 2,224 | 4,566 | +105% | 0 | 0 | — |
case-14 | fail→fail | 18,089 | 36,319 | +101% | 1 | 1 | 0% | 2,894 | 6,526 | +126% | 0 | 0 | — |
case-15 | fail→fail | 17,335 | 32,155 | +85% | 1 | 1 | 0% | 2,840 | 5,893 | +108% | 0 | 0 | — |
case-16 | fail→fail | 16,193 | 31,517 | +95% | 1 | 1 | 0% | 2,575 | 5,505 | +114% | 0 | 0 | — |
case-17 | fail→pass | 1,997 | 47,080 | +2258% | 1 | 1 | 0% | 258 | 8,582 | +3226% | 0 | 0 | — |
case-18 | fail→pass | 15,943 | 39,764 | +149% | 1 | 1 | 0% | 2,602 | 6,744 | +159% | 0 | 0 | — |
case-19 | fail→fail | 16,036 | 35,076 | +119% | 1 | 1 | 0% | 2,635 | 6,712 | +155% | 0 | 0 | — |
case-20 | pass→fail | 28,939 | 46,610 | +61% | 1 | 1 | 0% | 4,878 | 8,227 | +69% | 0 | 0 | — |
case-21 | pass→pass | 18,261 | 19,004 | +4% | 1 | 1 | 0% | 2,802 | 3,344 | +19% | 0 | 0 | — |
case-22 | pass→pass | 13,429 | 14,303 | +7% | 1 | 1 | 0% | 2,297 | 2,827 | +23% | 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. 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.