Viral TikTok Pattern Miner

SKILL: Viral TikTok Pattern Miner
Sorting TikTok by most_liked over a recent window surfaces proven winners, while the most_recent feed reveals which formats and sounds are still fresh enough to ride rather than already played out; optionally cross-checking YouTube Shorts and Instagram Reels confirms which hooks actually travel across platforms versus being TikTok-only flukes.

You are running this skill on API Direct via its MCP tools. Execute the steps below yourself by calling the named tools in order — values in <angle brackets> come from a previous step. Then deliver the result described at the end.

INPUTS:
  - niche (required): <niche — ASK THE USER>
      The content niche to mine for winning patterns
  - region (optional): (optional — e.g. us)
      Two-letter region code to scope the TikTok feed (TikTok only; YouTube and Instagram passes are global)
  - platforms (optional): (optional — e.g. tiktok, youtube, instagram)
      Comma-separated list of platforms to run — options: tiktok, youtube, instagram. Omit to run all of them; name specific platforms to limit the run.
  - window (optional): 7 (default — override if you like)
      Lookback window in days for the TikTok feed, mapping to publish_time (valid values 7, 30, 90, 180). Smaller catches patterns earlier; larger builds a deeper winners list. Defaults to 7.
  - depth (optional): 3 (default — override if you like)
      How many result pages to pull per platform search; higher means a deeper scan and more candidate videos. Defaults to a shallow pass.

PLATFORM SELECTION: some steps are gated with "Only run if {platforms} includes X". If the user supplied a `platforms` value, run only the steps whose platform is listed. If the user did NOT supply `platforms`, run ALL steps — every platform the skill supports.

STEPS:
  1. Tool `search_tiktok` — search_tiktok(query={niche}, sort_by=most_liked, publish_time=7, get_sentiment=true, pages=3)
     Take the top-liked videos of the window and log each one's music_title/author, hook, and format, keeping the positively-received winners.
  2. Tool `search_tiktok` — search_tiktok(query={niche}, sort_by=most_recent, publish_time=7, pages=3)
     Compare against the freshest uploads to flag which winning formats and sounds are still emerging versus already saturated.
  3. Tool `search_tiktok_users` — search_tiktok_users(query=<winning_creator>, pages=2)
     Resolve the creators behind the top videos and capture follower and video counts to identify who to model or partner with.
  4. Tool `search_youtube` — search_youtube(query={niche}, upload_date=this_week, get_sentiment=true, pages=3)
     Only run if {platforms} includes youtube: Pull this week's short-form YouTube videos for the niche and log the hooks, title patterns, and formats of the high-view, positively-received winners to confirm which TikTok patterns also win as YouTube Shorts.
  5. Tool `search_instagram` — search_instagram(query={niche}, get_sentiment=true, pages=3)
     Only run if {platforms} includes instagram: Capture the same niche on Instagram to see which hooks and Reel formats are also winning there, reinforcing the cross-platform patterns worth briefing your editor over the TikTok-only flukes.

DELIVER: A content playbook of the period's winning hooks, sounds, and formats plus the creators driving them, with each pattern flagged as confirmed across TikTok, YouTube, and Instagram versus emerging or already saturated.

Note: each underlying tool call is billed at its normal endpoint price; get_sentiment adds a small per-page surcharge. Page through results as needed but stop once you have enough to deliver the outcome.