Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/repurpose <content_title> [--platforms <list>]
.claude/skills/miosa-osa-repurpose/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 153% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 152% | 0% |
| case-15 | ✓→✓ | ＝ Same ✓ | 49% | 0% |
| case-16 | ✓→✓ | ＝ Same ✓ | 33% | 0% |
| case-17 | ✓→✓ | ＝ Same ✓ | 43% | 0% |
/repurpose <content_title> --platforms <list>]
Adapt a pillar piece of content into platform-native derivatives across social channels.
| Arg | Type | Required | Description | |-----|------|----------|-------------| | content_title | string | Yes | Title of the source content to repurpose | | --platforms | string | No | Comma-separated platform list. Default: all active platforms |
Genre: social-package Format: Markdown with platform-specific content + visual briefs
Produces:
1. Analyze source content for repurposable elements (stats, tips, quotes, frameworks)
2. Social media manager creates platform-native adaptations
3. Designer creates visual briefs for each platform format
4. Schedule across platforms with optimal timing
5. Target: 1 pillar piece -> 5+ derivative posts/repurpose "The Complete Guide to B2B Content Marketing"
/repurpose "Q1 Results Case Study" --platforms linkedin,x| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,318 | 21,825 | +93% | 1 | 1 | 0% | 1,569 | 3,969 | +153% | 0 | 0 | — |
case-02 | fail→fail | 45,771 | 35,400 | -23% | 1 | 1 | 0% | 3,717 | 5,815 | +56% | 0 | 0 | — |
case-03 | fail→fail | 19,745 | 16,528 | -16% | 1 | 1 | 0% | 2,665 | 2,871 | +8% | 0 | 0 | — |
case-04 | fail→fail | 7,958 | 9,607 | +21% | 1 | 1 | 0% | 1,011 | 1,421 | +41% | 0 | 0 | — |
case-05 | fail→fail | 24,665 | 24,981 | +1% | 1 | 1 | 0% | 2,781 | 4,514 | +62% | 0 | 0 | — |
case-06 | fail→fail | 24,131 | 23,651 | -2% | 1 | 1 | 0% | 3,112 | 3,687 | +18% | 0 | 0 | — |
case-07 | fail→fail | 24,449 | 28,720 | +17% | 1 | 1 | 0% | 3,133 | 4,822 | +54% | 0 | 0 | — |
case-08 | fail→fail | 13,781 | 15,393 | +12% | 1 | 1 | 0% | 1,903 | 2,596 | +36% | 0 | 0 | — |
case-09 | fail→fail | 12,814 | 21,174 | +65% | 1 | 1 | 0% | 1,987 | 3,614 | +82% | 0 | 0 | — |
case-10 | fail→pass | 8,462 | 21,305 | +152% | 1 | 1 | 0% | 1,424 | 3,583 | +152% | 0 | 0 | — |
case-11 | fail→fail | 10,369 | 15,669 | +51% | 1 | 1 | 0% | 1,683 | 2,380 | +41% | 0 | 0 | — |
case-12 | fail→fail | 19,044 | 27,191 | +43% | 1 | 1 | 0% | 1,495 | 2,240 | +50% | 0 | 0 | — |
case-13 | fail→fail | 45,274 | 31,889 | -30% | 1 | 1 | 0% | 8,189 | 5,051 | -38% | 0 | 0 | — |
case-14 | fail→fail | 15,707 | 19,665 | +25% | 1 | 1 | 0% | 2,401 | 3,627 | +51% | 0 | 0 | — |
case-15 | pass→pass | 12,977 | 18,834 | +45% | 1 | 1 | 0% | 2,237 | 3,326 | +49% | 0 | 0 | — |
case-16 | pass→pass | 18,404 | 19,805 | +8% | 1 | 1 | 0% | 2,720 | 3,612 | +33% | 0 | 0 | — |
case-17 | pass→pass | 16,743 | 21,312 | +27% | 1 | 1 | 0% | 2,599 | 3,712 | +43% | 0 | 0 | — |
case-18 | fail→fail | 13,842 | 37,590 | +172% | 1 | 1 | 0% | 2,189 | 3,760 | +72% | 0 | 0 | — |
case-19 | fail→fail | 13,373 | 18,187 | +36% | 1 | 1 | 0% | 2,314 | 3,695 | +60% | 0 | 0 | — |
case-20 | fail→fail | 30,381 | 34,334 | +13% | 1 | 1 | 0% | 2,893 | 5,083 | +76% | 0 | 0 | — |
case-21 | fail→fail | 9,286 | 15,930 | +72% | 1 | 1 | 0% | 1,067 | 2,549 | +139% | 0 | 0 | — |
case-22 | pass→pass | 49,143 | 31,199 | -37% | 1 | 1 | 0% | 7,042 | 4,763 | -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 +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.