All skills
Content & Influencer
Rising-Creator Early Detector
Find undervalued creators by engagement-to-follower ratio before they blow up.
Run this skill with your agent
1. Connect the MCP server
https://apidirect.io/mcp?token=YOUR_API_KEY
2. Then just say to your agent
Find up-and-coming {niche} creators on TikTok who get way more engagement than their follower count suggests.
In clients that support MCP prompts (Claude Desktop, Claude Code, Cursor) this skill appears as a prompt named
rising-creator-early-detector.
Any agent can also call get_skill(skill_id="rising-creator-early-detector") to pull these steps on demand.
What it does
Surfaces the most-liked recent videos in a niche, then divides likes by follower count to flag creators punching far above their size — cheap partnerships before prices rise.
Who it's for: Influencer marketers, talent scouts and brand partnerships.
Inputs
| Input | Required | Description | Example |
|---|---|---|---|
niche |
Yes | The content niche to scan. | home cooking gadgets |
region |
No | 2-letter region code to scope to. | us |
How your agent runs it
-
1
search_tiktok(query="{niche}", sort_by=most_liked, publish_time=30, region="{region}")Get the most-liked videos from the last 30 days. Collect each author and the video's like count.
-
2
search_tiktok_users(query=<author>)Pull each creator's follower count and video_count.
-
3
(compute) likes ÷ followers per creatorFlag outliers: huge engagement but a modest following = a rising creator to lock in early.
Delivers: A shortlist of undervalued creators with their engagement-to-follower ratio and contact-worthiness.
Tools used
The full playbook
This is exactly what the MCP returns to your agent (via the rising-creator-early-detector prompt or get_skill tool), with your inputs filled in.
SKILL: Rising-Creator Early Detector
Surfaces the most-liked recent videos in a niche, then divides likes by follower count to flag creators punching far above their size — cheap partnerships before prices rise.
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>
- region (optional): (optional — e.g. us)
STEPS:
1. Tool `search_tiktok` — search_tiktok(query="<niche>", sort_by=most_liked, publish_time=30, region="<region>")
Get the most-liked videos from the last 30 days. Collect each author and the video's like count.
2. Tool `search_tiktok_users` — search_tiktok_users(query=<author>)
Pull each creator's follower count and video_count.
3. Tool `search_tiktok_users` — (compute) likes ÷ followers per creator
Flag outliers: huge engagement but a modest following = a rising creator to lock in early.
DELIVER: A shortlist of undervalued creators with their engagement-to-follower ratio and contact-worthiness.
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.