create shardingsphere yml,use three databases,auto choose master and slave

Sure, I understand your question. To create a ShardingSphere YAML file for using three databases and auto-choosing master and slave, you can refer to the following example:

spring:
  sharding:
    datasource:
      names: ds0, ds1, ds2
      ds0:
        url: jdbc:mysql://localhost:3306/db0
        username: root
        password: root
      ds1:
        url: jdbc:mysql://localhost:3306/db1
        username: root
        password: root
      ds2:
        url: jdbc:mysql://localhost:3306/db2
        username: root
        password: root
    master-slave-rules:
      ms0:
        master-data-source-name: ds0
        slave-data-source-names: ds1,ds2
        load-balance-algorithm-type: ROUND_ROBIN

In this YAML file, we define three data sources `ds0`, `ds1`, and `ds2`, with their respective URLs, usernames, and passwords. We also define a master-slave rule `ms0`, which specifies that the master database is `ds0`, and the two slave databases are `ds1` and `ds2`. The `load-balance-algorithm-type` is set to `ROUND_ROBIN`, which means that the system will randomly choose a slave database for each query.

I hope this helps! Let me know if you have any other questions.