Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Convert content between platforms (blog to Twitter thread, article to LinkedIn post, etc.). Optimize for each platform's format, tone, and best practices. Use when user wants to adapt content for different social media platforms.
.claude/skills/nicepkg-social-media-content-repurposer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-24 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 48% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 155% | 0% |
Transform content across platforms with platform-specific optimization.
Activate when the user:
markdown# Content Repurposing: [Original Title] ## Source Summary **Original Format**: [Blog post/Article/Video] **Key Message**: [One sentence] **Target Audience**: [Description] --- ## Twitter/X Thread (10 tweets) **Tweet 1/10** (Hook) [Attention-grabbing opening tweet] **Tweet 2/10** [First key point] **Tweet 3/10** [Second key point] [Continue through full thread...] **Tweet 10/10** [Summary and CTA] --- ## LinkedIn Post [Hook paragraph with strong opening] [Main content with strategic line breaks] Key takeaways: • [Point 1] • [Point 2] • [Point 3] [Closing thought or question] **Hashtags**: #Industry #Topic #Relevant --- ## Instagram Caption [Strong hook line] [Concise main message - 3-4 short paragraphs with emojis] [Call to action] . . . #hashtag1 #hashtag2 #hashtag3 #hashtag4 #hashtag5 [continue to 15-20 relevant hashtags] **Visual Suggestion**: [Description of ideal image/carousel] --- ## Facebook Post [Conversational opening] [Brief, engaging content] [Question to drive comments] #Hashtag --- ## TikTok Script (if applicable) **Hook (0-3 sec)**: [Attention grabber] **Main Content (3-45 sec)**: [Key points delivered quickly] **CTA (45-60 sec)**: [Call to action] **On-Screen Text Ideas**: - [Text 1] - [Text 2] **Audio Suggestion**: [Trending sound or style] **Hashtags**: #FYP #topic #niche --- ## Analytics Recommendations - Best posting times: [Platform-specific suggestions] - Engagement tactics: [Specific strategies per platform] - A/B testing ideas: [Variations to test]
User: "Turn this blog post into social media content" Response: Extract key points → Create Twitter thread with hook → Write LinkedIn post with professional tone → Generate Instagram caption with hashtags → Provide Facebook version → Include posting strategy
User: "I need to repurpose this podcast episode for social" Response: Summarize key moments → Create quotable tweets → Write LinkedIn article-style post → Generate audiogram caption for Instagram → Suggest TikTok clips → Provide hashtag research
User: "Convert this case study into a Twitter thread" Response: Identify success story arc → Create compelling thread hook → Break down into 8-10 tweet structure → Add data points strategically → End with CTA → Suggest accompanying visuals
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 25,883 | 30,255 | +17% | 1 | 1 | 0% | 3,839 | 4,987 | +30% | 0 | 0 | — |
case-02 | fail→pass | 21,699 | 25,463 | +17% | 1 | 1 | 0% | 3,282 | 5,244 | +60% | 0 | 0 | — |
case-03 | fail→fail | 26,471 | 26,039 | -2% | 1 | 1 | 0% | 4,316 | 5,360 | +24% | 0 | 0 | — |
case-04 | pass→pass | 16,069 | 14,786 | -8% | 1 | 1 | 0% | 2,468 | 3,645 | +48% | 0 | 0 | — |
case-05 | pass→pass | 4,862 | 6,174 | +27% | 1 | 1 | 0% | 985 | 2,514 | +155% | 0 | 0 | — |
case-06 | pass→pass | 14,761 | 17,602 | +19% | 1 | 1 | 0% | 2,374 | 4,017 | +69% | 0 | 0 | — |
case-07 | fail→fail | 12,289 | 17,473 | +42% | 1 | 1 | 0% | 2,098 | 4,396 | +110% | 0 | 0 | — |
case-08 | fail→fail | 8,608 | 7,857 | -9% | 1 | 1 | 0% | 1,320 | 2,526 | +91% | 0 | 0 | — |
case-09 | fail→pass | 12,175 | 9,874 | -19% | 1 | 1 | 0% | 1,795 | 2,794 | +56% | 0 | 0 | — |
case-10 | fail→fail | 9,892 | 10,634 | +8% | 1 | 1 | 0% | 1,439 | 2,868 | +99% | 0 | 0 | — |
case-11 | fail→fail | 7,742 | 8,226 | +6% | 1 | 1 | 0% | 1,299 | 2,718 | +109% | 0 | 0 | — |
case-12 | fail→fail | 4,036 | 20,857 | +417% | 1 | 1 | 0% | 548 | 4,504 | +722% | 0 | 0 | — |
case-13 | fail→fail | 14,831 | 14,709 | -1% | 1 | 1 | 0% | 2,377 | 3,805 | +60% | 0 | 0 | — |
case-14 | fail→fail | 6,923 | 6,521 | -6% | 1 | 1 | 0% | 1,010 | 2,279 | +126% | 0 | 0 | — |
case-15 | pass→pass | 11,960 | 11,314 | -5% | 1 | 1 | 0% | 1,637 | 2,785 | +70% | 0 | 0 | — |
case-16 | fail→fail | 12,500 | 19,706 | +58% | 1 | 1 | 0% | 1,711 | 4,203 | +146% | 0 | 0 | — |
case-17 | fail→fail | 16,005 | 23,438 | +46% | 1 | 1 | 0% | 2,420 | 4,985 | +106% | 0 | 0 | — |
case-18 | fail→fail | 5,311 | 5,807 | +9% | 1 | 1 | 0% | 760 | 2,249 | +196% | 0 | 0 | — |
case-19 | fail→fail | 8,477 | 7,728 | -9% | 1 | 1 | 0% | 1,092 | 2,311 | +112% | 0 | 0 | — |
case-20 | fail→fail | 20,330 | 7,961 | -61% | 1 | 1 | 0% | 1,034 | 2,512 | +143% | 0 | 0 | — |
case-21 | fail→fail | 6,470 | 9,707 | +50% | 1 | 1 | 0% | 907 | 2,789 | +207% | 0 | 0 | — |
case-22 | fail→fail | 5,542 | 5,896 | +6% | 1 | 1 | 0% | 873 | 2,202 | +152% | 0 | 0 | — |
case-23 | fail→fail | 17,329 | 16,459 | -5% | 1 | 1 | 0% | 3,084 | 4,282 | +39% | 0 | 0 | — |
case-24 | fail→pass | 25,234 | 21,837 | -13% | 1 | 1 | 0% | 3,686 | 4,848 | +32% | 0 | 0 | — |
case-25 | fail→fail | 10,448 | 7,022 | -33% | 1 | 1 | 0% | 1,764 | 2,404 | +36% | 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. 25 cases were attempted. The headline lift of +12 percentage points is the difference between those two pass rates over the 25 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.