Douyin Similar Creators

Map the creators Douyin considers most similar to one account, tier them by size and pick benchmarks and collaboration candidates.

v0.1.0

View example draft · How to use

Example draft

Lookalikes of a Chengdu home-cooking account

Seed 周幺姑家常菜 (5.59 M followers, 33,515 likes per post).

Read

Same tier, far more likes per post: 川味盐太婆 (8.77 M, 136,177 likes per post) and 七哥民间菜 (6.09 M, 120,803) earn 3.6–4× the seed with half the posts. 杨队长 has 3.78 M followers and 34.4 likes per follower, three times the seed. Tags: 美食教程 10, 乡村美食 7.

Shortlist

Benchmark: 川味盐太婆, 七哥民间菜 Study for engagement: 杨队长 Not a benchmark: 火筵家常, 陈龙美食 (volume without engagement)

Excerpt from an actual run on 2026-11-06.

What you get

  • Lookalikes with followers, posts, likes per post and likes per follower
  • Size tiers and category tags
  • A shortlist: benchmark, collaborate, not a benchmark

Good fit

  • Choosing benchmark accounts before a content plan
  • Finding similar creators for a campaign

Not for

  • Recent performance or prices; vet shortlisted accounts with douyin-kol-vetting
  • Contacting creators

How to use

An Agent that can read the complete Skill folder. Live research also needs a SandBase connection; supplied material can be used without a lookup.

Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.

Download Skill v0.1.0

Ask your Agent

Use douyin-similar-creators for 周幺姑家常菜. Tier the lookalikes, compare likes per post with the seed and shortlist benchmarks and collaboration candidates.

  1. Resolve the seed

    Get the seed’s uid and its followers, posts and likes.

  2. Pull lookalikes

    Read Douyin’s similar-creator list through SandBase.

  3. Tier and compare

    Compute likes per post and per follower, tier by size and shortlist.

FAQ

How do I use this Skill?

Download and unpack the whole Skill folder, including references, into your Agent’s supported Skill directory. You can also ask the Agent to read its SKILL.md and follow the instructions. Run it locally with your own material.

How does Douyin decide similarity?

The response does not say. Treat rank as how similar, not how good.