Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SNS投稿の作成・スケジュール・最適化を支援するスキル。 「SNS投稿を作って」「LinkedInの投稿を書いて」「コンテンツカレンダーを作成」等のリクエストで発動。
.claude/skills/minicoohei-social-content/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 66% | 0% |
You are an expert social media strategist. Your goal is to help create engaging content that builds audience, drives engagement, and supports business goals.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
| Platform | Best For | Frequency | Key Format | |----------|----------|-----------|------------| | LinkedIn | B2B, thought leadership | 3-5x/week | Carousels, stories | | Twitter/X | Tech, real-time, community | 3-10x/day | Threads, hot takes | | Instagram | Visual brands, lifestyle | 1-2 posts + Stories daily | Reels, carousels | | TikTok | Brand awareness, younger audiences | 1-4x/day | Short-form video | | Facebook | Communities, local businesses | 1-2x/day | Groups, native video |
For detailed platform strategies: See references/platforms.md
Build your content around 3-5 pillars that align with your expertise and audience interests.
| Pillar | % of Content | Topics | |--------|--------------|--------| | Industry insights | 30% | Trends, data, predictions | | Behind-the-scenes | 25% | Building the company, lessons learned | | Educational | 25% | How-tos, frameworks, tips | | Personal | 15% | Stories, values, hot takes | | Promotional | 5% | Product updates, offers |
For each pillar, ask:
The first line determines whether anyone reads the rest.
For post templates and more hooks: See references/post-templates.md
Turn one piece of content into many:
| Platform | Format | |----------|--------| | LinkedIn | Key insight + link in comments | | LinkedIn | Carousel of main points | | Twitter/X | Thread of key takeaways | | Instagram | Carousel with visuals | | Instagram | Reel summarizing the post |
| Day | LinkedIn | Twitter/X | Instagram | |-----|----------|-----------|-----------| | Mon | Industry insight | Thread | Carousel | | Tue | Behind-scenes | Engagement | Story | | Wed | Educational | Tips tweet | Reel | | Thu | Story post | Thread | Educational | | Fri | Hot take | Engagement | Story |
Awareness: Impressions, Reach, Follower growth rate
Engagement: Engagement rate, Comments (higher value than likes), Shares/reposts, Saves
Conversion: Link clicks, Profile visits, DMs received, Leads attributed
If engagement is low:
If reach is declining:
Schedule: Core content posts, Threads, Carousels, Evergreen content
Post live: Real-time commentary, Responses to news/trends, Engagement with others
Instead of guessing, analyze what's working for top creators in your niche:
For the complete framework: See references/reverse-engineering.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,605 | 14,464 | -22% | 1 | 1 | 0% | 3,235 | 4,265 | +32% | 0 | 0 | — |
case-02 | fail→fail | 17,785 | 15,109 | -15% | 1 | 1 | 0% | 2,824 | 4,622 | +64% | 0 | 0 | — |
case-03 | pass→pass | 17,037 | 13,734 | -19% | 1 | 1 | 0% | 2,713 | 3,980 | +47% | 0 | 0 | — |
case-04 | pass→pass | 27,046 | 23,777 | -12% | 1 | 1 | 0% | 4,351 | 6,101 | +40% | 0 | 0 | — |
case-05 | pass→pass | 13,301 | 13,762 | +3% | 1 | 1 | 0% | 2,087 | 3,944 | +89% | 0 | 0 | — |
case-06 | pass→pass | 12,364 | 8,520 | -31% | 1 | 1 | 0% | 1,986 | 3,278 | +65% | 0 | 0 | — |
case-07 | pass→pass | 15,153 | 11,856 | -22% | 1 | 1 | 0% | 2,351 | 3,797 | +62% | 0 | 0 | — |
case-08 | pass→pass | 11,271 | 12,146 | +8% | 1 | 1 | 0% | 1,842 | 3,891 | +111% | 0 | 0 | — |
case-09 | fail→pass | 11,272 | 9,164 | -19% | 1 | 1 | 0% | 1,767 | 3,399 | +92% | 0 | 0 | — |
case-10 | fail→pass | 12,556 | 14,058 | +12% | 1 | 1 | 0% | 2,141 | 4,234 | +98% | 0 | 0 | — |
case-11 | fail→pass | 13,696 | 8,332 | -39% | 1 | 1 | 0% | 2,151 | 3,220 | +50% | 0 | 0 | — |
case-12 | fail→pass | 13,970 | 8,071 | -42% | 1 | 1 | 0% | 2,294 | 3,229 | +41% | 0 | 0 | — |
case-13 | fail→pass | 12,131 | 7,058 | -42% | 1 | 1 | 0% | 1,869 | 3,097 | +66% | 0 | 0 | — |
case-14 | fail→pass | 10,367 | 8,328 | -20% | 1 | 1 | 0% | 1,678 | 3,335 | +99% | 0 | 0 | — |
case-15 | pass→pass | 9,527 | 1,811 | -81% | 1 | 1 | 0% | 1,629 | 2,215 | +36% | 0 | 0 | — |
case-16 | pass→pass | 14,240 | 15,233 | +7% | 1 | 1 | 0% | 2,202 | 4,198 | +91% | 0 | 0 | — |
case-17 | fail→fail | 14,101 | 10,121 | -28% | 1 | 1 | 0% | 2,371 | 3,605 | +52% | 0 | 0 | — |
case-18 | pass→pass | 14,477 | 13,535 | -7% | 1 | 1 | 0% | 2,229 | 4,058 | +82% | 0 | 0 | — |
case-19 | fail→pass | 14,182 | 3,105 | -78% | 1 | 1 | 0% | 2,291 | 2,464 | +8% | 0 | 0 | — |
case-20 | pass→pass | 15,239 | 10,996 | -28% | 1 | 1 | 0% | 2,440 | 3,564 | +46% | 0 | 0 | — |
case-21 | pass→pass | 12,034 | 5,924 | -51% | 1 | 1 | 0% | 1,824 | 2,791 | +53% | 0 | 0 | — |
case-22 | fail→pass | 5,637 | 1,600 | -72% | 1 | 1 | 0% | 958 | 2,182 | +128% | 0 | 0 | — |
case-23 | pass→pass | 13,740 | 10,425 | -24% | 1 | 1 | 0% | 2,130 | 3,476 | +63% | 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. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 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.