メニュー
Fetch viral AI content from TikTok and Facebook using Apify scrapers. USE WHEN you need to scrape TikTok creator videos or Facebook page posts about AI topics.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/hoanghd218/claude-ai-mastery --skill mkt-social-content-fetcherコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Find breakout YouTube videos with 2x+ view-to-subscriber ratio. USE WHEN user says 'find breakout videos', 'search for breakout video ideas', 'find viral video angles', 'youtube breakout research', 'find videos that overperformed', 'research video ideas for breakout potential', 'find underperforming videos that went viral', 'youtube video opportunity research'.
Tìm top GitHub trending repositories (daily/weekly/monthly) để làm content AI/tech. Scrape github.com/trending, lọc theo language, lưu JSON + Markdown. USE WHEN user says 'github trend hôm nay', 'top github trending', 'tìm github trending', 'github trending daily', 'top 10 github repo', 'research github trend', 'github trend for content', 'lấy github trending', 'github hot hôm nay', 'trending repo'.
Phân tích nội dung bài viết Facebook, đưa ra prompt tạo ảnh minh họa bằng Nano Banana Pro. Hỗ trợ dạng: các bước, so sánh, ẩn dụ, concept.
| name | mkt-social-content-fetcher |
| description | Fetch viral AI content from TikTok and Facebook using Apify scrapers. USE WHEN you need to scrape TikTok creator videos or Facebook page posts about AI topics. |
Fetch viral AI content from TikTok and Facebook pages/creators using Apify REST API.
Used by the mkt-ai-content-researcher agent as data collection sub-agents.
APIFY_API_TOKEN in .envuv installeduv run .claude/skills/mkt-social-content-fetcher/scripts/fetch_tiktok.py \
--handles "handle1,handle2" \
--min-views 10000 \
--period week \
--output research/ai-content/YYYY-MM-DD/tiktok.json
Args:
--handles — comma-separated TikTok handles (from sources.json or override)--min-views — minimum view count filter (default: 10000)--period — day, week, month (default: week)--output — output file path (optional, default: stdout)--sources-file — path to sources.json (default: auto-detect)Output:
{
"source": "tiktok",
"date": "YYYY-MM-DD",
"period": "week",
"items": [
{
"title": "video description",
"url": "https://tiktok.com/@handle/video/...",
"author": "@handle",
"views": 123456,
"likes": 5000,
"shares": 200,
"published_at": "YYYY-MM-DD",
"tags": ["ai", "automation"],
"thumbnail_url": "..."
}
]
}
uv run .claude/skills/mkt-social-content-fetcher/scripts/fetch_facebook.py \
--pages "PageName1,PageName2" \
--date-from YYYY-MM-DD \
--min-likes 100 \
--output research/ai-content/YYYY-MM-DD/facebook.json
Args:
--pages — comma-separated Facebook page names/URLs--date-from — fetch posts from this date (default: 7 days ago)--min-likes — minimum likes filter (default: 100)--output — output file path (optional, default: stdout)--sources-file — path to sources.json (default: auto-detect)Output: Same format as TikTok but source = "facebook".
Edit .claude/skills/mkt-social-content-fetcher/sources.json to configure which channels to monitor per platform.
clockworks/tiktok-scraperapify/facebook-posts-scraper